Detecting Ship Targets in Spaceborne Infrared Image based on Modeling Radiation Anomalies

Size: px
Start display at page:

Download "Detecting Ship Targets in Spaceborne Infrared Image based on Modeling Radiation Anomalies"

Transcription

1 Detecting Ship Targets in Spaceborne Infrared Image based on Modeling Radiation Anomalies Haibo Wang a,b, Zhengxia Zou c,, Zhenwei Shi c,, Bo Li a a Beijing Key Laboratory of Digital Media, School of Computer Science and Engineering, Beihang University, Beijing , PR China b China Centre for Resources Satellite Data and Application, Beijing , PR China c Image Processing Center, School of Astronautics, Beihang University, Beijing , PR China Abstract Using infrared imaging sensors to detect ship target in the ocean environment has many advantages compared to other sensor modalities, such as better thermal sensitivity and all-weather detection capability. We propose a new ship detection method by modeling radiation anomalies for spaceborne infrared image. The proposed method can be decomposed into two stages, where in the first stage, a test infrared image is densely divided into a set of image patches and the radiation anomaly of each patch is estimated by a Gaussian Mixture Model (GMM), and thereby target candidates are obtained from anomaly image patches. In the second stage, target candidates are further checked by a more discriminative criterion to obtain the final detection result. The main innovation of the proposed method is inspired by the biological mechanism that human eyes are sensitive to the unusual and anomalous patches among complex background. The experimental result on short wavelength infrared band (1.560µm 2.300µm) and long wavelength infrared band (10.30µm 12.50µm) of Landsat-8 satellite shows the proposed method achieves a desired ship detection accuracy with higher recall The work was supported by the National Natural Science Foundation of China under the Grants and the Beijing Natural Science Foundation under the Grant (Corresponding author: Zhengxia Zou and Zhenwei Shi.) Corresponding author: Image Processing Center, School of Astronautics, Beihang University, Beijing , PR China. Tel: ; Fax: addresses: zhengxiazou@buaa.edu.cn (Zhengxia Zou), shizhenwei@buaa.edu.cn (Zhenwei Shi) Preprint submitted to Elsevier May 16, 2017

2 than other classical ship detection methods. Keywords: Ship detection, Infrared spaceborne image, Radiation Anomaly, Gaussian Mixture Model 1. Introduction Ship detection with spaceborne remote sensing image has long been a hot issue in the remote sensing image processing field due to both its civil and military use. While most of the earlier researches for ship detection are designed for synthetic aperture radar image and high resolution optical image, with the rapid development of infrared sensor technology, it is now possible to explore ship detection method with spaceborne infrared image. Detecting ship target with infrared image has many advantages over other sensor modalities, such as better thermal sensitivity and all-weather detection capability. For the most of the previous ship detection methods, a coarse-to-fine detection strategy is usually used. Their algorithm flow can be divided into the following two stages: 1) ship candidate extraction and 2) ship verification. In the first stage, all the candidate regions that possibly contain a ship target are extracted. Some classical image processing methods like image threshhold segmentation based methods [Xia et al. 2011, Chen et al. 2011, Jubelin et al. 2014, Bi et al. 2012, Qi et al. 2015, Zhu et al. 2010] and the saliency detection based methods [Qi et al. 2015, Ding et al. 2012] are commonly used in this stage. In the second stage, a more discriminative algorithm will further check each of the individual candidate to verify whether it really contains a ship target. Previous works of this stage [Xia et al. 2011, Bi et al. 2012, Zhu et al. 2010, Tang et al. 2015, Yu et al. 2014, Zou et al. 2016] mainly transform this operation into a feature extraction and a binary classification process (targets and backgrounds). In this paper, a new detection strategy is studied compared to the previous ones. Our method is inspired by the biological mechanism that human eyes are sensitive to the unusual and anomalous patterns in an image [Tsotsos et al. 1995, Itti et al. 1998]. We assume that any image patterns in an infrared image can be decompensated as a group of similar or dissimilar patches. On one hand, some of these patches share a high degree of similarity and have a vast number of quantities. These patches build up the background region of an image. On the other hand, some patches show strong rarity and 2

3 specificity thus we call these patches radiation anomalies. In most cases, anomalous patches can be a reflection of some specific edge and textures, where these patterns cannot be well explained by their surroundings. We further assume that a ship candidate region shows a high degree of radiation anomaly in an infrared image and usually appears as an outlier in the probability distribution of the image data. To evaluate the anomaly degree of the image and better exploit their nonlinear statistical characteristics, a Gaussian Mixture Model (GMM) based evaluation method is proposed as an effective ship candidate detection method. The rest of this paper is organized as follows. In section 2 and 3, we will introduce the radiation anomaly evaluation method and details of our detection framework. Some experimental results will be given in section 4, and the conclusions are drawn in Section Proposed Method The proposed candidate detection method can be summarized into two steps: 1) feature representation; 2) radiation anomaly evaluation. Fig.1 illustrates the detection pipeline. The details of each step are given as follows. 1). feature representation. Suppose there is an infrared image with the size of H W pixels and D bands. We first densely divide this image into a N overlapping patches with p p patch-size and s s patch-stride. Since the raw pixel value of an infrared image reflects the radiation characteristic of the ground elements while the shape of a ship target can be well described by the gradients or edge directions, here we simply take a modified approach of a classical feature extraction method, the Histograms of Oriented Gradients (HOG) [Dalal et al. 2015] as a description of the image data. Concretely, we still follow a traditional processing flow of HOG where each individual image patch is further divided into M uniform spatial cell regions and for each cell, a histogram of gradient directions over 9 orientation bins which is evenly spaced over is accumulated. To reduce the interference of high frequency noise in the image, each image patch is convoluted with a 3 3 Gaussian mask before accumulating the feature histograms. For simplicity, we do not take the block-wise normalization strategy in the original HOG algorithm. The final feature description of a image patch is connected with the histograms h and their raw pixel values r of each cell in an end-to-end 3

4 Fig. 1: Framework of the proposed method: feature representation and radiation anomaly evaluation. The original feature has been projected to a two-dimension plane by principle component analysis for better illustration. 4

5 manner x = [h 1, r 1,... h M, r M ] T R L 1. (1) where L is the final dimension of the feature space. 2.) radiation anomaly evaluation. We use a GMM to evaluate the radiation anomaly of a patch extracted from a test image. A GMM can be basically formulated as p(x) = K ϕ k N (µ k, Σ k ), k=1 K ϕ k = 1 (2) where the kth component is characterized by normal distributions with weights ϕ k, means vector µ k and covariance matrices Σ k. Since ship targets usually show high degree of anomaly and rarity and are distributed as the outliers (with low probability density) of any mixture Gaussian clusters, while those background patches share high degree of similarity and are usually distributed near the cluster center (with high probability density), we define the anomaly of an image patch x based on the probabilistic density: k=1 A(x) = 1 ˆp(x) = 1 K ϕ k N ( ˆµ k, ˆΣ k ) (3) i=k where ˆµ k and ˆΣ k represent the estimation of the means and covariance matrices. After anomaly evaluation, a patch that possibly contains a target will get a large response, while a background patch will get a small one. The final anomaly score of pixel location (x, y) of a test image can be obtained by simply averaging anomaly score of the overlapped patches covered on this position. The score map of the test image can be compared with a threshold T (0, 1) and the final ship candidate region refers to those pixels with their responses larger than the threshold. To determine the parameters ϕ k, ˆµ k and ˆΣ k with an a priori given number of components K, we use the Expectation Maximization (EM) algorithm [Bishop. 2006], which is a particular way of implementing maximum likelihood estimation for such problem. EM gives iterative estimation of these parameters where a closed-form solution is possible at each iteration. Detailed iteration process is given as follows: E step: Evaluate the responsibilities using the current parameter values γ(z nk ) = ϕ k N (x n µ k, Σ k ) K j=1 ϕ jn (x n µ j, Σ j ) (4) 5

6 M step. Re-estimate the parameters using the current responsibilities µ k 1 N γ(z nk )x n N k Σ k 1 N k n=1 N n=1 ϕ k N k N, where N k = γ(z nk )(x n µ k )(x n µ k ) T N γ(z nk ). n=1 (5) The above iteration should be stopped when the posterior probability distribution convergence to a constant. Afterwards in the ship verification stage, each individual ship candidate will be further checked to verify whether if it really contains a target. Here we follow a classical processing strategy that converting this process to a binary classification operations which discriminates the targets from backgrounds. To design a proper classification algorithm for this task, accuracy and processing speed are both important. Linear SVM [Vapnik et al. 1998, Fan et al. 2008] is popular for its good generalization ability and its low computational cost. Linear SVM is a supervised classification method that constructs a linear hyperplane to separate data points into two classes. In this stage, we still take the modified HOG as we have used in the previous stage as our feature descriptor. The only difference lies that the anomaly evaluation is unsupervised, while the linear SVM is supervised. By this way, we finally obtain the ship detection result. 3. Relationship with RX Algorithm [Reed et al. 1990] It can be noticed that in GMM if we take the component number K = 1, it will collapse into a single Gaussian distribution model and our anomaly evaluation (3) will simply degenerate to the square of the Mahalanobis distance metric D M (x) between the input patch x and the Gaussian clutter 6

7 Fig. 2: Snythetic data and (a) the proposed mixture model with components K = 2, (b) single Gaussian model. center µ A(x) = 1 N (µ, Σ ) 1 1 =1 exp( (x µ )T Σ 1 (x µ )) ND 2 T 1 (x µ ) Σ (x µ ) = DM (x) (6) where ND is a normalization factor and means the two functions have the same monotony. We also notice that DM (x) have the same form as the classical Reed-Xiaoli (RX) algorithm [Reed et al. 1990], which has been extensively used for hyperspectral image anomaly detection. RX algorithm defines the anomaly of a spectral vector x as follows RX(x) = (x µ )T Σ 1 (x µ ). (7) Therefore, the Mahalanobis distance metric DM (x) and RX algorithm can be seen as two special cases of our model. Fig. 2 shows the difference between the proposed method with components K = 2 (a) and single Gaussian model (b) on a group of toy data, where the former one can better catch the nonlinearity and better positioning outliers. 7

8 4. Experimental Results and Analysis We use a set of Landsat-8 satellite images to demonstrate the efficiency of our method. In our experiments, we focus on detecting off-shore ships. Before ship detection, we remove the land regions of the input image by using land masks that are generated by GSHHG database [GSHHG Online]. We use the near infrared band, short wavelength infrared band and long wavelength infrared band of Landsat-8 satellite to detect ship targets Experimental Setup Our algorithm is evaluated on 64 image slices of Landsat-8 satellite image with the slice size of pixels, where 45 of them are used for train and the rest are used for test. A detailed information of these images are listed in table 1. We build an image pyramid before detecting ship candidates for each input image to enhance the detection robustness of different scales. Each image is down-scaled at a rate of 1.0, 1.5, 2, and 2.5 while keeping other detection parameters fixed including the patch size and cell size. Some ships which is too small (whose length are smaller than 6 pixels) have been eliminated. Since we only focus on off-shore ships, the ships that is adjacent with the land are also eliminated. The detection and miss-detection of all the above targets are not included in the statistics. There are 115 ship targets labeled in all for experiments. Since the number of individuals are too small to obtained statistically meaningful training results, we have also collected 2000 individual ship samples from Google Earth images as extra training samples. It should be noticed that also the google earth samples Landsat 8 samples have different sources, the former one can still provide the essential shape and structure information which can be well captured by HOG descriptor for training an SVM model. We set the patch size p = 11, the cell size c = 5 and the patch stride s = 1. We set the component number of GMM K = Overall Results Statistics To test the robustness on different degrees of fringe noise interference, a- mong the five infrared bands of Landsat 8 (5th, 6th, 7th, 10th and 11th), the 7th (short wavelength infrared) and 11th (long wavelength infrared) band are manually corrupted with fringe noise of SNR=10dB and SNR=20dB, respectively. Fig. 3 shows some typical detection results of our proposed method. The yellow bounding-boxes refers to final detected targets. To quantitatively 8

9 Table 1: Detailed information of the experimental images: Landsat-8 Band ID Wavelength Resolution µm 30m µm 30m µm 30m µm 100m µm 100m Solar Irradiance 955W/(m2 µm) 242W/(m2 µm) 82.5W/(m2 µm) - Fig. 3: Some typical detection results of Landsat-8 infrared band image slices. (a)-(b): Near Infrared, (c)-(d): Short Wavelength Infrared, (e)-(f): Long Wavelength Infrared, (g)-(h): Short Wavelength Infrared (SNR=20db), (i): Long Wavelength Infrared (SNR=10db). 9

10 evaluate our method, the precision and recall rate of the detection results are counted. Precision and recall are defined as follows precision = N tp /(N tp + N fp ), recall = N tp /(N tp + N fn ), (8) where N tp represents number of true-positives, N fp represents number of false-positives and N fn represents number of false-negatives. Statistical results are listed in table 2, which suggests an overall high accuracy and stability of our method. Table 2: The precision and recall rate of Landsat-8 detection results Band ID Band Type Noise SNR Precision Recall 5 Near Infrared Short Wavelength Infrared Short Wavelength Infrared 10dB Long Wavelength Infrared Long Wavelength Infrared 20dB average Comparison and Parameter Analysis We compare our ship candidate detection method with two classical methods including spectral-residual saliency detection method (SpecRes) [Hou et al. 2007] and adaptive threshold method (AdaThresh) [Bradski. 2000]. These two methods and their variants have been widely used for detection ship candidates in previous literatures. The spectral-residual saliency detection method analyzes the log-spectrum of an input image and construct the corresponding saliency map based on the spectral residual of the spectral domain. The adaptive threshold method applies an adaptive threshold to an input grayscale image I and transforms it to a binary image BW according to the formulate: { 1 if I(x, y) > M(x, y) BW (x, y) = (9) 0 otherwise, where M(x, y) is the average pixel value of a local square region calculated individually for each pixel. The pixels with values of 1 forms the ship 10

11 recall AdaThresh SpecRes Anomaly-1 Anomaly-2 Anomaly number of candidates Fig. 4: Recall rates of five different ship candidate detection methods under different number of candidates. candidate regions. Parameters of these methods have been carefully tuned to obtain their best detection results. Since the number of component K in our model is an important parameter, detection results under different K are also compared. The single component Gaussian model (K = 1) can be seen as a baseline. Finally, five methods are compared with each other including SpecRes [Hou et al. 2007], AdaThresh [Bradski. 2000], Anomaly-1, Anomaly-2 and Anomaly-3, where 1, 2, 3 represent the component number. Fig. 4 shows recall rates of the above methods under different candidate target number. Clearly, a higher recall rate under a certain candidate number means a better performance. Our radiation anomaly based methods outperform than other two classical methods. Anomaly-3 outperforms than its single-gaussian baseline method Anomaly-1 and is slightly better than Anomaly-2. Considering the computational cost, we do not try more complex model with more than 3 components. We also compare the performance of the three different feature design strategies: HOG+RAW, HOG-only and RAW-only. For a fair comparison, we use the same parameters of feature extraction and the same linear SVM 11

12 precision HOG-only RAW-only HOG+RAW recall Fig. 5: Precision-recall curves of three different features: HOG-only, RAWonly and HOG-RAW. penalty coefficient C=1. We randomly choose half samples for training and the rest for test. Fig. 5 shows the precision-recall curves of the three types of features. We can see a clear advantage of the feature combination. Since the raw pixel value reflects the radiation characteristic of the ground elements while shape of a ship target can be well described by the gradients or edge directions, the raw pixel and HOG combination provide complementary information with each other. This experiment has verified the rationality of our choice. 5. Conclusion We propose a new ship detection method for spaceborne infrared image which is inspired by the biological attention mechanism. The proposed method is designed based on modeling radiation anomalies of an infrared image by converting it into a probability density estimation and outlier detection problem. GMM is used as a probability density estimation model and the EM algorithm is used for parameter estimation. Experimental results for detecting ship targets in Landsat-8 infrared band images are presented and 12

13 analyzed. Compared with other classical ship detection methods, the proposed method suggests higher robustness and higher detection recall rate under the same number of detection candidates. References [Xia et al. 2011] Xia, Y., Wan, S. H., Yue, L. H., A novel algorithm for ship detection based on dynamic fusion model of multi-feature and support vector machine. in Proc. ICIG, [Chen et al. 2011] Chen, F., Yu, W., Liu, X., Wang, K., Gong, L., Lv, W., Graph-based ship extraction scheme for optical satellite image. in Proc. IEEE IGARSS, [Jubelin et al. 2014] Jubelin, G., Khenchaf, A., Multiscale algorithm for ship detection in mid, high and very high resolution optical imagery. in Proc. IEEE IGARSS, [Bi et al. 2012] Bi, F. K., Zhu, B. C., Gao,L. N., Bian, M. M., A visual search inspired computational model for ship detection in optical satellite images. IEEE Geosci. Remote Sens. Lett., 9(4), [Qi et al. 2015] Qi, S., Ma, J., Lin, J., Li, Y., Tian, J., Unsupervised ship detection based on saliency and S-HOG descriptor from optical satellite images. IEEE Geosci. Remote Sens. Lett., 12(7), [Zhu et al. 2010] Zhu, C., Zhou, H., Wang, R., Guo, J., A novel hierarchical method of ship detection from spaceborne optical image based on shape and texture features. IEEE Trans. Geosci. Remote Sens., 48(9), [Ding et al. 2012] Ding, Z., Yu, Y., Wang, B., Zhang, L., An approach for visual attention based on biquaternion and its application for ship detection in multispectral imagery Neurocomputing, 76(1) [Tang et al. 2015] Tang, J., Deng, C., Huang, G.-B., Zhao, B., Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine. IEEE Trans. Geosci. Remote Sens., 53(3), 1174C

14 [Yu et al. 2014] Shi, Z., Yu, X., Jiang, Z., Li, B., Ship detection in high-resolution optical imagery based on anomaly detector and local shape feature, IEEE Trans. Geosci. Remote Sens., 52(8), [Zou et al. 2016] Zou, Z., Shi, Z., Ship Detection in Spaceborne Optical Image with SVD Networks. IEEE Trans. Geosci. Remote Sens., 54(10), [Tsotsos et al. 1995] Tsotsos, J. K., Culhane, S. M., Wai, W. Y. K., Lai, Y. H., Davis, N., Nuflo, F., Modelling Visual Attention via Selective Tuning, Artif. Intell., 78(1-2), 507C545. [Itti et al. 1998] Itti L., Koch C., Niebur E., A Model of Saliency- Based Visual Attention for Rapid Scene Analysis, IEEE Trans. Pattern Anal. Mach. Intell., 20(11), [Dalal et al. 2015] Dalal, N., Triggs, B., Histograms of oriented gradients for human detection in Proc. IEEE CVPR, [Bishop. 2006] Bishop., C. M, Pattern recognition and machine learning. Springer. [Vapnik et al. 1998] Vapnik, V. N., Vapnik, V., Statistical learning theory (Vol. 1). New York: Wiley. [Fan et al. 2008] Fan, R. E., Chang, K. W., Hsieh, C. J., Wang, X. R., Lin, C. J., Liblinear: A library for large linear classification, J. Mach. Learn. Res., 9, [Reed et al. 1990] Reed, I. S., Yu, X., Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution, IEEE Trans. Acoust. Speech. Signal. Process., 38(10), [Hou et al. 2007] Hou, X., Zhang, L., Saliency detection: A spectral residual approach. in Proc. IEEE CVPR, 1-8. [Bradski. 2000] Bradski, G., OpenCV Library., Dr. Dobb s Journal of Software Tools. [GSHHG Online] GSHHG - A Global Self-consistent, Hierarchical, Highresolution Geography Database. [Online]. Available: noaa.gov/mgg/shorelines/gshhs.html. 14

2 Proposed Methodology

2 Proposed Methodology 3rd International Conference on Multimedia Technology(ICMT 2013) Object Detection in Image with Complex Background Dong Li, Yali Li, Fei He, Shengjin Wang 1 State Key Laboratory of Intelligent Technology

More information

Small Object Segmentation Based on Visual Saliency in Natural Images

Small Object Segmentation Based on Visual Saliency in Natural Images J Inf Process Syst, Vol.9, No.4, pp.592-601, December 2013 http://dx.doi.org/10.3745/jips.2013.9.4.592 pissn 1976-913X eissn 2092-805X Small Object Segmentation Based on Visual Saliency in Natural Images

More information

HYPERSPECTRAL imagery has been increasingly used

HYPERSPECTRAL imagery has been increasingly used IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 14, NO. 5, MAY 2017 597 Transferred Deep Learning for Anomaly Detection in Hyperspectral Imagery Wei Li, Senior Member, IEEE, Guodong Wu, and Qian Du, Senior

More information

Tri-modal Human Body Segmentation

Tri-modal Human Body Segmentation Tri-modal Human Body Segmentation Master of Science Thesis Cristina Palmero Cantariño Advisor: Sergio Escalera Guerrero February 6, 2014 Outline 1 Introduction 2 Tri-modal dataset 3 Proposed baseline 4

More information

A NOVEL SHIP DETECTION METHOD FOR LARGE-SCALE OPTICAL SATELLITE IMAGES BASED ON VISUAL LBP FEATURE AND VISUAL ATTENTION MODEL

A NOVEL SHIP DETECTION METHOD FOR LARGE-SCALE OPTICAL SATELLITE IMAGES BASED ON VISUAL LBP FEATURE AND VISUAL ATTENTION MODEL A NOVEL SHIP DETECTION METHOD FOR LARGE-SCALE OPTICAL SATELLITE IMAGES BASED ON VISUAL LBP FEATURE AND VISUAL ATTENTION MODEL Sui Haigang a, *, Song Zhina b a State Key Laboratory of Information Engineering

More information

An efficient face recognition algorithm based on multi-kernel regularization learning

An efficient face recognition algorithm based on multi-kernel regularization learning Acta Technica 61, No. 4A/2016, 75 84 c 2017 Institute of Thermomechanics CAS, v.v.i. An efficient face recognition algorithm based on multi-kernel regularization learning Bi Rongrong 1 Abstract. A novel

More information

SHIP WAKE DETECTION FOR SAR IMAGES WITH COMPLEX BACKGROUNDS BASED ON MORPHOLOGICAL DICTIONARY LEARNING

SHIP WAKE DETECTION FOR SAR IMAGES WITH COMPLEX BACKGROUNDS BASED ON MORPHOLOGICAL DICTIONARY LEARNING SHIP WAKE DETECTION FOR SAR IMAGES WITH COMPLEX BACKGROUNDS BASED ON MORPHOLOGICAL DICTIONARY LEARNING Guozheng Yang 1, 2, Jing Yu 3, Chuangbai Xiao 3, Weidong Sun 1 1 State Key Laboratory of Intelligent

More information

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009 Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer

More information

SAR Image Target Classification: A Feature Fusion Approach

SAR Image Target Classification: A Feature Fusion Approach SAR Image Target Classification: A Fusion Approach 1 Sivaranjani Rajamanickam; S.Mohamed Mansoor Roomi 1 Dept of ECE,Sethu Institute of Technology Virudhunagar, India Dept of ECE, Thiagarjar College of

More information

Adaptive Doppler centroid estimation algorithm of airborne SAR

Adaptive Doppler centroid estimation algorithm of airborne SAR Adaptive Doppler centroid estimation algorithm of airborne SAR Jian Yang 1,2a), Chang Liu 1, and Yanfei Wang 1 1 Institute of Electronics, Chinese Academy of Sciences 19 North Sihuan Road, Haidian, Beijing

More information

NTHU Rain Removal Project

NTHU Rain Removal Project People NTHU Rain Removal Project Networked Video Lab, National Tsing Hua University, Hsinchu, Taiwan Li-Wei Kang, Institute of Information Science, Academia Sinica, Taipei, Taiwan Chia-Wen Lin *, Department

More information

Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach

Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach Vandit Gajjar gajjar.vandit.381@ldce.ac.in Ayesha Gurnani gurnani.ayesha.52@ldce.ac.in Yash Khandhediya khandhediya.yash.364@ldce.ac.in

More information

Hyperspectral Image Anomaly Targets Detection with Online Deep Learning

Hyperspectral Image Anomaly Targets Detection with Online Deep Learning This full text paper was peer-reviewed at the direction of IEEE Instrumentation and Measurement Society prior to the acceptance and publication. Hyperspectral Image Anomaly Targets Detection with Online

More information

Color Image Segmentation

Color Image Segmentation Color Image Segmentation Yining Deng, B. S. Manjunath and Hyundoo Shin* Department of Electrical and Computer Engineering University of California, Santa Barbara, CA 93106-9560 *Samsung Electronics Inc.

More information

Hyperspectral and Multispectral Image Fusion Using Local Spatial-Spectral Dictionary Pair

Hyperspectral and Multispectral Image Fusion Using Local Spatial-Spectral Dictionary Pair Hyperspectral and Multispectral Image Fusion Using Local Spatial-Spectral Dictionary Pair Yifan Zhang, Tuo Zhao, and Mingyi He School of Electronics and Information International Center for Information

More information

A Novel Extreme Point Selection Algorithm in SIFT

A Novel Extreme Point Selection Algorithm in SIFT A Novel Extreme Point Selection Algorithm in SIFT Ding Zuchun School of Electronic and Communication, South China University of Technolog Guangzhou, China zucding@gmail.com Abstract. This paper proposes

More information

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation M. Blauth, E. Kraft, F. Hirschenberger, M. Böhm Fraunhofer Institute for Industrial Mathematics, Fraunhofer-Platz 1,

More information

Bus Detection and recognition for visually impaired people

Bus Detection and recognition for visually impaired people Bus Detection and recognition for visually impaired people Hangrong Pan, Chucai Yi, and Yingli Tian The City College of New York The Graduate Center The City University of New York MAP4VIP Outline Motivation

More information

Detecting Salient Contours Using Orientation Energy Distribution. Part I: Thresholding Based on. Response Distribution

Detecting Salient Contours Using Orientation Energy Distribution. Part I: Thresholding Based on. Response Distribution Detecting Salient Contours Using Orientation Energy Distribution The Problem: How Does the Visual System Detect Salient Contours? CPSC 636 Slide12, Spring 212 Yoonsuck Choe Co-work with S. Sarma and H.-C.

More information

Human-Robot Interaction

Human-Robot Interaction Human-Robot Interaction Elective in Artificial Intelligence Lecture 6 Visual Perception Luca Iocchi DIAG, Sapienza University of Rome, Italy With contributions from D. D. Bloisi and A. Youssef Visual Perception

More information

Unsupervised Change Detection in Optical Satellite Images using Binary Descriptor

Unsupervised Change Detection in Optical Satellite Images using Binary Descriptor Unsupervised Change Detection in Optical Satellite Images using Binary Descriptor Neha Gupta, Gargi V. Pillai, Samit Ari Department of Electronics and Communication Engineering, National Institute of Technology,

More information

Multiple-Person Tracking by Detection

Multiple-Person Tracking by Detection http://excel.fit.vutbr.cz Multiple-Person Tracking by Detection Jakub Vojvoda* Abstract Detection and tracking of multiple person is challenging problem mainly due to complexity of scene and large intra-class

More information

Saliency Detection for Videos Using 3D FFT Local Spectra

Saliency Detection for Videos Using 3D FFT Local Spectra Saliency Detection for Videos Using 3D FFT Local Spectra Zhiling Long and Ghassan AlRegib School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA ABSTRACT

More information

Engineering And Technology (affiliated to Anna University, Chennai) Tamil. Nadu, India

Engineering And Technology (affiliated to Anna University, Chennai) Tamil. Nadu, India International Journal of Advances in Engineering & Scientific Research, Vol.2, Issue 2, Feb - 2015, pp 08-13 ISSN: 2349 3607 (Online), ISSN: 2349 4824 (Print) ABSTRACT MULTI-TEMPORAL SAR IMAGE CHANGE DETECTION

More information

Video Inter-frame Forgery Identification Based on Optical Flow Consistency

Video Inter-frame Forgery Identification Based on Optical Flow Consistency Sensors & Transducers 24 by IFSA Publishing, S. L. http://www.sensorsportal.com Video Inter-frame Forgery Identification Based on Optical Flow Consistency Qi Wang, Zhaohong Li, Zhenzhen Zhang, Qinglong

More information

Efficient Acquisition of Human Existence Priors from Motion Trajectories

Efficient Acquisition of Human Existence Priors from Motion Trajectories Efficient Acquisition of Human Existence Priors from Motion Trajectories Hitoshi Habe Hidehito Nakagawa Masatsugu Kidode Graduate School of Information Science, Nara Institute of Science and Technology

More information

Fast Anomaly Detection Algorithms For Hyperspectral Images

Fast Anomaly Detection Algorithms For Hyperspectral Images Vol. Issue 9, September - 05 Fast Anomaly Detection Algorithms For Hyperspectral Images J. Zhou Google, Inc. ountain View, California, USA C. Kwan Signal Processing, Inc. Rockville, aryland, USA chiman.kwan@signalpro.net

More information

OBJECT RECOGNITION ALGORITHM FOR MOBILE DEVICES

OBJECT RECOGNITION ALGORITHM FOR MOBILE DEVICES Image Processing & Communication, vol. 18,no. 1, pp.31-36 DOI: 10.2478/v10248-012-0088-x 31 OBJECT RECOGNITION ALGORITHM FOR MOBILE DEVICES RAFAŁ KOZIK ADAM MARCHEWKA Institute of Telecommunications, University

More information

Car Detecting Method using high Resolution images

Car Detecting Method using high Resolution images Car Detecting Method using high Resolution images Swapnil R. Dhawad Department of Electronics and Telecommunication Engineering JSPM s Rajarshi Shahu College of Engineering, Savitribai Phule Pune University,

More information

Category vs. instance recognition

Category vs. instance recognition Category vs. instance recognition Category: Find all the people Find all the buildings Often within a single image Often sliding window Instance: Is this face James? Find this specific famous building

More information

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging 1 CS 9 Final Project Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging Feiyu Chen Department of Electrical Engineering ABSTRACT Subject motion is a significant

More information

DETECTION OF IMAGE PAIRS USING CO-SALIENCY MODEL

DETECTION OF IMAGE PAIRS USING CO-SALIENCY MODEL DETECTION OF IMAGE PAIRS USING CO-SALIENCY MODEL N S Sandhya Rani 1, Dr. S. Bhargavi 2 4th sem MTech, Signal Processing, S. J. C. Institute of Technology, Chickballapur, Karnataka, India 1 Professor, Dept

More information

A MAXIMUM NOISE FRACTION TRANSFORM BASED ON A SENSOR NOISE MODEL FOR HYPERSPECTRAL DATA. Naoto Yokoya 1 and Akira Iwasaki 2

A MAXIMUM NOISE FRACTION TRANSFORM BASED ON A SENSOR NOISE MODEL FOR HYPERSPECTRAL DATA. Naoto Yokoya 1 and Akira Iwasaki 2 A MAXIMUM NOISE FRACTION TRANSFORM BASED ON A SENSOR NOISE MODEL FOR HYPERSPECTRAL DATA Naoto Yokoya 1 and Akira Iwasaki 1 Graduate Student, Department of Aeronautics and Astronautics, The University of

More information

Graph Matching Iris Image Blocks with Local Binary Pattern

Graph Matching Iris Image Blocks with Local Binary Pattern Graph Matching Iris Image Blocs with Local Binary Pattern Zhenan Sun, Tieniu Tan, and Xianchao Qiu Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of

More information

Change Detection in Remotely Sensed Images Based on Image Fusion and Fuzzy Clustering

Change Detection in Remotely Sensed Images Based on Image Fusion and Fuzzy Clustering International Journal of Electronics Engineering Research. ISSN 0975-6450 Volume 9, Number 1 (2017) pp. 141-150 Research India Publications http://www.ripublication.com Change Detection in Remotely Sensed

More information

Supplementary Material for Ensemble Diffusion for Retrieval

Supplementary Material for Ensemble Diffusion for Retrieval Supplementary Material for Ensemble Diffusion for Retrieval Song Bai 1, Zhichao Zhou 1, Jingdong Wang, Xiang Bai 1, Longin Jan Latecki 3, Qi Tian 4 1 Huazhong University of Science and Technology, Microsoft

More information

Introduction to digital image classification

Introduction to digital image classification Introduction to digital image classification Dr. Norman Kerle, Wan Bakx MSc a.o. INTERNATIONAL INSTITUTE FOR GEO-INFORMATION SCIENCE AND EARTH OBSERVATION Purpose of lecture Main lecture topics Review

More information

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN 2016 International Conference on Artificial Intelligence: Techniques and Applications (AITA 2016) ISBN: 978-1-60595-389-2 Face Recognition Using Vector Quantization Histogram and Support Vector Machine

More information

Aggregating Descriptors with Local Gaussian Metrics

Aggregating Descriptors with Local Gaussian Metrics Aggregating Descriptors with Local Gaussian Metrics Hideki Nakayama Grad. School of Information Science and Technology The University of Tokyo Tokyo, JAPAN nakayama@ci.i.u-tokyo.ac.jp Abstract Recently,

More information

Adaptive Learning of an Accurate Skin-Color Model

Adaptive Learning of an Accurate Skin-Color Model Adaptive Learning of an Accurate Skin-Color Model Q. Zhu K.T. Cheng C. T. Wu Y. L. Wu Electrical & Computer Engineering University of California, Santa Barbara Presented by: H.T Wang Outline Generic Skin

More information

A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery

A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery K. Borna 1, A. B. Moore 2, P. Sirguey 3 School of Surveying University of Otago PO Box 56, Dunedin,

More information

Object detection using non-redundant local Binary Patterns

Object detection using non-redundant local Binary Patterns University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2010 Object detection using non-redundant local Binary Patterns Duc Thanh

More information

PEOPLE IN SEATS COUNTING VIA SEAT DETECTION FOR MEETING SURVEILLANCE

PEOPLE IN SEATS COUNTING VIA SEAT DETECTION FOR MEETING SURVEILLANCE PEOPLE IN SEATS COUNTING VIA SEAT DETECTION FOR MEETING SURVEILLANCE Hongyu Liang, Jinchen Wu, and Kaiqi Huang National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science

More information

Normalized Texture Motifs and Their Application to Statistical Object Modeling

Normalized Texture Motifs and Their Application to Statistical Object Modeling Normalized Texture Motifs and Their Application to Statistical Obect Modeling S. D. Newsam B. S. Manunath Center for Applied Scientific Computing Electrical and Computer Engineering Lawrence Livermore

More information

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation Object detection using Region Proposals (RCNN) Ernest Cheung COMP790-125 Presentation 1 2 Problem to solve Object detection Input: Image Output: Bounding box of the object 3 Object detection using CNN

More information

Learning based face hallucination techniques: A survey

Learning based face hallucination techniques: A survey Vol. 3 (2014-15) pp. 37-45. : A survey Premitha Premnath K Department of Computer Science & Engineering Vidya Academy of Science & Technology Thrissur - 680501, Kerala, India (email: premithakpnath@gmail.com)

More information

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Classification Vladimir Curic Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Outline An overview on classification Basics of classification How to choose appropriate

More information

High Resolution Remote Sensing Image Classification based on SVM and FCM Qin LI a, Wenxing BAO b, Xing LI c, Bin LI d

High Resolution Remote Sensing Image Classification based on SVM and FCM Qin LI a, Wenxing BAO b, Xing LI c, Bin LI d 2nd International Conference on Electrical, Computer Engineering and Electronics (ICECEE 2015) High Resolution Remote Sensing Image Classification based on SVM and FCM Qin LI a, Wenxing BAO b, Xing LI

More information

Latest development in image feature representation and extraction

Latest development in image feature representation and extraction International Journal of Advanced Research and Development ISSN: 2455-4030, Impact Factor: RJIF 5.24 www.advancedjournal.com Volume 2; Issue 1; January 2017; Page No. 05-09 Latest development in image

More information

A Background Modeling Approach Based on Visual Background Extractor Taotao Liu1, a, Lin Qi2, b and Guichi Liu2, c

A Background Modeling Approach Based on Visual Background Extractor Taotao Liu1, a, Lin Qi2, b and Guichi Liu2, c 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2015) A Background Modeling Approach Based on Visual Background Extractor Taotao Liu1, a, Lin Qi2, b

More information

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane

More information

Remote Sensed Image Classification based on Spatial and Spectral Features using SVM

Remote Sensed Image Classification based on Spatial and Spectral Features using SVM RESEARCH ARTICLE OPEN ACCESS Remote Sensed Image Classification based on Spatial and Spectral Features using SVM Mary Jasmine. E PG Scholar Department of Computer Science and Engineering, University College

More information

Evaluation of regions-of-interest based attention algorithms using a probabilistic measure

Evaluation of regions-of-interest based attention algorithms using a probabilistic measure Evaluation of regions-of-interest based attention algorithms using a probabilistic measure Martin Clauss, Pierre Bayerl and Heiko Neumann University of Ulm, Dept. of Neural Information Processing, 89081

More information

Selection of Scale-Invariant Parts for Object Class Recognition

Selection of Scale-Invariant Parts for Object Class Recognition Selection of Scale-Invariant Parts for Object Class Recognition Gy. Dorkó and C. Schmid INRIA Rhône-Alpes, GRAVIR-CNRS 655, av. de l Europe, 3833 Montbonnot, France fdorko,schmidg@inrialpes.fr Abstract

More information

Sketchable Histograms of Oriented Gradients for Object Detection

Sketchable Histograms of Oriented Gradients for Object Detection Sketchable Histograms of Oriented Gradients for Object Detection No Author Given No Institute Given Abstract. In this paper we investigate a new representation approach for visual object recognition. The

More information

Land-use scene classification using multi-scale completed local binary patterns

Land-use scene classification using multi-scale completed local binary patterns DOI 10.1007/s11760-015-0804-2 ORIGINAL PAPER Land-use scene classification using multi-scale completed local binary patterns Chen Chen 1 Baochang Zhang 2 Hongjun Su 3 Wei Li 4 Lu Wang 4 Received: 25 April

More information

Supervised Learning approach to Object Identification and Recognition

Supervised Learning approach to Object Identification and Recognition Volume 119 No. 10 2108, 463-470 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu ijpam.eu Supervised Learning approach to Object Identification and Recognition

More information

Spatial Information Based Image Classification Using Support Vector Machine

Spatial Information Based Image Classification Using Support Vector Machine Spatial Information Based Image Classification Using Support Vector Machine P.Jeevitha, Dr. P. Ganesh Kumar PG Scholar, Dept of IT, Regional Centre of Anna University, Coimbatore, India. Assistant Professor,

More information

BiTS A Biologically-Inspired Target Screener for Detecting Manmade Objects in Natural Clutter Backgrounds

BiTS A Biologically-Inspired Target Screener for Detecting Manmade Objects in Natural Clutter Backgrounds BiTS A Biologically-Inspired Target Screener for Detecting Manmade Objects in Natural Clutter Backgrounds Mark J. Carlotto 1 General Dynamics, Advanced Information Systems Abstract Motivated by biologically-inspired

More information

Det De e t cting abnormal event n s Jaechul Kim

Det De e t cting abnormal event n s Jaechul Kim Detecting abnormal events Jaechul Kim Purpose Introduce general methodologies used in abnormality detection Deal with technical details of selected papers Abnormal events Easy to verify, but hard to describe

More information

Generic Object Detection Using Improved Gentleboost Classifier

Generic Object Detection Using Improved Gentleboost Classifier Available online at www.sciencedirect.com Physics Procedia 25 (2012 ) 1528 1535 2012 International Conference on Solid State Devices and Materials Science Generic Object Detection Using Improved Gentleboost

More information

This is an author produced version of Accurate Reconstruction and Suppression for Azimuth Ambiguities in Spaceborne Stripmap SAR Images.

This is an author produced version of Accurate Reconstruction and Suppression for Azimuth Ambiguities in Spaceborne Stripmap SAR Images. This is an author produced version of Accurate Reconstruction and Suppression for Azimuth Ambiguities in Spaceborne Stripmap SAR Images. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/38/

More information

A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation

A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation , pp.162-167 http://dx.doi.org/10.14257/astl.2016.138.33 A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation Liqiang Hu, Chaofeng He Shijiazhuang Tiedao University,

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational

More information

Visible and Long-Wave Infrared Image Fusion Schemes for Situational. Awareness

Visible and Long-Wave Infrared Image Fusion Schemes for Situational. Awareness Visible and Long-Wave Infrared Image Fusion Schemes for Situational Awareness Multi-Dimensional Digital Signal Processing Literature Survey Nathaniel Walker The University of Texas at Austin nathaniel.walker@baesystems.com

More information

SAR change detection based on Generalized Gamma distribution. divergence and auto-threshold segmentation

SAR change detection based on Generalized Gamma distribution. divergence and auto-threshold segmentation SAR change detection based on Generalized Gamma distribution divergence and auto-threshold segmentation GAO Cong-shan 1 2, ZHANG Hong 1*, WANG Chao 1 1.Center for Earth Observation and Digital Earth, CAS,

More information

Image Classification Using Wavelet Coefficients in Low-pass Bands

Image Classification Using Wavelet Coefficients in Low-pass Bands Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August -7, 007 Image Classification Using Wavelet Coefficients in Low-pass Bands Weibao Zou, Member, IEEE, and Yan

More information

SiftingGAN: Generating and Sifting Labeled Samples to Improve the Remote Sensing Image Scene Classification Baseline in vitro

SiftingGAN: Generating and Sifting Labeled Samples to Improve the Remote Sensing Image Scene Classification Baseline in vitro 1 SiftingGAN: Generating and Sifting Labeled Samples to Improve the Remote Sensing Image Scene Classification Baseline in vitro Dongao Ma, Ping Tang, and Lijun Zhao arxiv:1809.04985v4 [cs.cv] 30 Nov 2018

More information

(Refer Slide Time: 0:51)

(Refer Slide Time: 0:51) Introduction to Remote Sensing Dr. Arun K Saraf Department of Earth Sciences Indian Institute of Technology Roorkee Lecture 16 Image Classification Techniques Hello everyone welcome to 16th lecture in

More information

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin

More information

Stripe Noise Removal from Remote Sensing Images Based on Stationary Wavelet Transform

Stripe Noise Removal from Remote Sensing Images Based on Stationary Wavelet Transform Sensors & Transducers, Vol. 78, Issue 9, September 204, pp. 76-8 Sensors & Transducers 204 by IFSA Publishing, S. L. http://www.sensorsportal.com Stripe Noise Removal from Remote Sensing Images Based on

More information

CAP 6412 Advanced Computer Vision

CAP 6412 Advanced Computer Vision CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha

More information

IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING

IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING Jianzhou Feng Li Song Xiaog Huo Xiaokang Yang Wenjun Zhang Shanghai Digital Media Processing Transmission Key Lab, Shanghai Jiaotong University

More information

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images Karthik Ram K.V & Mahantesh K Department of Electronics and Communication Engineering, SJB Institute of Technology, Bangalore,

More information

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK 1 Po-Jen Lai ( 賴柏任 ), 2 Chiou-Shann Fuh ( 傅楸善 ) 1 Dept. of Electrical Engineering, National Taiwan University, Taiwan 2 Dept.

More information

Co-Saliency Detection Based on Hierarchical Segmentation

Co-Saliency Detection Based on Hierarchical Segmentation 88 IEEE SIGNAL PROCESSING LETTERS, VOL. 21, NO. 1, JANUARY 2014 Co-Saliency Detection Based on Hierarchical Segmentation Zhi Liu, Member, IEEE, Wenbin Zou, Lina Li, Liquan Shen, and Olivier Le Meur Abstract

More information

Mobile Human Detection Systems based on Sliding Windows Approach-A Review

Mobile Human Detection Systems based on Sliding Windows Approach-A Review Mobile Human Detection Systems based on Sliding Windows Approach-A Review Seminar: Mobile Human detection systems Njieutcheu Tassi cedrique Rovile Department of Computer Engineering University of Heidelberg

More information

An Angle Estimation to Landmarks for Autonomous Satellite Navigation

An Angle Estimation to Landmarks for Autonomous Satellite Navigation 5th International Conference on Environment, Materials, Chemistry and Power Electronics (EMCPE 2016) An Angle Estimation to Landmarks for Autonomous Satellite Navigation Qing XUE a, Hongwen YANG, Jian

More information

Understanding Clustering Supervising the unsupervised

Understanding Clustering Supervising the unsupervised Understanding Clustering Supervising the unsupervised Janu Verma IBM T.J. Watson Research Center, New York http://jverma.github.io/ jverma@us.ibm.com @januverma Clustering Grouping together similar data

More information

International Journal of Electrical, Electronics ISSN No. (Online): and Computer Engineering 3(2): 85-90(2014)

International Journal of Electrical, Electronics ISSN No. (Online): and Computer Engineering 3(2): 85-90(2014) I J E E E C International Journal of Electrical, Electronics ISSN No. (Online): 2277-2626 Computer Engineering 3(2): 85-90(2014) Robust Approach to Recognize Localize Text from Natural Scene Images Khushbu

More information

Last week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints

Last week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints Last week Multi-Frame Structure from Motion: Multi-View Stereo Unknown camera viewpoints Last week PCA Today Recognition Today Recognition Recognition problems What is it? Object detection Who is it? Recognizing

More information

Human Motion Detection and Tracking for Video Surveillance

Human Motion Detection and Tracking for Video Surveillance Human Motion Detection and Tracking for Video Surveillance Prithviraj Banerjee and Somnath Sengupta Department of Electronics and Electrical Communication Engineering Indian Institute of Technology, Kharagpur,

More information

An Approach for Reduction of Rain Streaks from a Single Image

An Approach for Reduction of Rain Streaks from a Single Image An Approach for Reduction of Rain Streaks from a Single Image Vijayakumar Majjagi 1, Netravati U M 2 1 4 th Semester, M. Tech, Digital Electronics, Department of Electronics and Communication G M Institute

More information

A Novel Approach to Saliency Detection Model and Its Applications in Image Compression

A Novel Approach to Saliency Detection Model and Its Applications in Image Compression RESEARCH ARTICLE OPEN ACCESS A Novel Approach to Saliency Detection Model and Its Applications in Image Compression Miss. Radhika P. Fuke 1, Mr. N. V. Raut 2 1 Assistant Professor, Sipna s College of Engineering

More information

Semi-supervised Data Representation via Affinity Graph Learning

Semi-supervised Data Representation via Affinity Graph Learning 1 Semi-supervised Data Representation via Affinity Graph Learning Weiya Ren 1 1 College of Information System and Management, National University of Defense Technology, Changsha, Hunan, P.R China, 410073

More information

Using the Deformable Part Model with Autoencoded Feature Descriptors for Object Detection

Using the Deformable Part Model with Autoencoded Feature Descriptors for Object Detection Using the Deformable Part Model with Autoencoded Feature Descriptors for Object Detection Hyunghoon Cho and David Wu December 10, 2010 1 Introduction Given its performance in recent years' PASCAL Visual

More information

Discriminative classifiers for image recognition

Discriminative classifiers for image recognition Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study

More information

Object Detection Design challenges

Object Detection Design challenges Object Detection Design challenges How to efficiently search for likely objects Even simple models require searching hundreds of thousands of positions and scales Feature design and scoring How should

More information

https://en.wikipedia.org/wiki/the_dress Recap: Viola-Jones sliding window detector Fast detection through two mechanisms Quickly eliminate unlikely windows Use features that are fast to compute Viola

More information

Robotics Programming Laboratory

Robotics Programming Laboratory Chair of Software Engineering Robotics Programming Laboratory Bertrand Meyer Jiwon Shin Lecture 8: Robot Perception Perception http://pascallin.ecs.soton.ac.uk/challenges/voc/databases.html#caltech car

More information

Spatio-Temporal LBP based Moving Object Segmentation in Compressed Domain

Spatio-Temporal LBP based Moving Object Segmentation in Compressed Domain 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance Spatio-Temporal LBP based Moving Object Segmentation in Compressed Domain Jianwei Yang 1, Shizheng Wang 2, Zhen

More information

Region Based Image Fusion Using SVM

Region Based Image Fusion Using SVM Region Based Image Fusion Using SVM Yang Liu, Jian Cheng, Hanqing Lu National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences ABSTRACT This paper presents a novel

More information

ECG782: Multidimensional Digital Signal Processing

ECG782: Multidimensional Digital Signal Processing Professor Brendan Morris, SEB 3216, brendan.morris@unlv.edu ECG782: Multidimensional Digital Signal Processing Spring 2014 TTh 14:30-15:45 CBC C313 Lecture 10 Segmentation 14/02/27 http://www.ee.unlv.edu/~b1morris/ecg782/

More information

Quasi-thematic Features Detection & Tracking. Future Rover Long-Distance Autonomous Navigation

Quasi-thematic Features Detection & Tracking. Future Rover Long-Distance Autonomous Navigation Quasi-thematic Feature Detection And Tracking For Future Rover Long-Distance Autonomous Navigation Authors: Affan Shaukat, Conrad Spiteri, Yang Gao, Said Al-Milli, and Abhinav Bajpai Surrey Space Centre,

More information

Face Detection using Hierarchical SVM

Face Detection using Hierarchical SVM Face Detection using Hierarchical SVM ECE 795 Pattern Recognition Christos Kyrkou Fall Semester 2010 1. Introduction Face detection in video is the process of detecting and classifying small images extracted

More information

Adaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision

Adaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision Adaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision Zhiyan Zhang 1, Wei Qian 1, Lei Pan 1 & Yanjun Li 1 1 University of Shanghai for Science and Technology, China

More information

Multi-DSP Parallel Processing Platform for Hyperspectral Anomaly Detection

Multi-DSP Parallel Processing Platform for Hyperspectral Anomaly Detection Multi-DSP Parallel Processing Platform for Hyperspectral Anomaly Detection GUO Wenji, MING Xing, ZENG Xiaoru, ZHANG Guifeng, LV Qunbo, ZHAO Baowei, and HUANG Min Key Laboratory of Computational Optical

More information

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Tomoyuki Nagahashi 1, Hironobu Fujiyoshi 1, and Takeo Kanade 2 1 Dept. of Computer Science, Chubu University. Matsumoto 1200,

More information

Image Resizing Based on Gradient Vector Flow Analysis

Image Resizing Based on Gradient Vector Flow Analysis Image Resizing Based on Gradient Vector Flow Analysis Sebastiano Battiato battiato@dmi.unict.it Giovanni Puglisi puglisi@dmi.unict.it Giovanni Maria Farinella gfarinellao@dmi.unict.it Daniele Ravì rav@dmi.unict.it

More information

FACULTY OF ENGINEERING AND INFORMATION TECHNOLOGY DEPARTMENT OF COMPUTER SCIENCE. Project Plan

FACULTY OF ENGINEERING AND INFORMATION TECHNOLOGY DEPARTMENT OF COMPUTER SCIENCE. Project Plan FACULTY OF ENGINEERING AND INFORMATION TECHNOLOGY DEPARTMENT OF COMPUTER SCIENCE Project Plan Structured Object Recognition for Content Based Image Retrieval Supervisors: Dr. Antonio Robles Kelly Dr. Jun

More information