Figure 1 shows unstructured data when plotted on the co-ordinate axis

Size: px
Start display at page:

Download "Figure 1 shows unstructured data when plotted on the co-ordinate axis"

Transcription

1 7th International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN) Key Frame Extraction and Foreground Modelling Using K-Means Clustering Azra Nasreen Kaushik Roy Kunal Roy Global Academy of Technology, Shobha G Abstract - In this paper, we have proposed and implemented a novel robust key frame extraction and foreground isolation method using k-means clustering and mean squared error method for variable frame rate videos. We also isolated foreground objects in the video whilst eliminating the noise generated in the recording. The flickering of the frames caused as a result of variable frame rate in a recorded video is reduced by a considerable degree using this method. Also, the k-means clustering is performed on Apache s hadoop infrastructure to make the results of the computation faster. We have implemented this method and obtained results to be clear enough to extract meaningful detail from the frames. The results of the method have been compared to similar results obtained using well- known techniques such as the Gaussian Mixture Model and have been shown to be better. Keywords Background Subtraction; Key Frame Extraction; Foreground modeling ; Hadoop; Distributed Computing I. INTRODUCTION In today s world, image processing concepts such as foreground extraction and key frame extraction are used extensively to reduce computational burden on post processing of the video. Post processing of the video can mean to extract features of objects of interest, for example face recognition or perhaps, for surveillance in cameras or perhaps, for analysis in detection of traffic violations, to name a few. In any case one problem that many image processing techniques face today is variable frame rates and large amounts of background noise that is created during recording of the video being analyzed. The variable frame rate and noise hinders key frame extraction by resulting in frames that have no discernible foreground movement. Therefore, in this paper we propose a method to extract key frames from a variable frame rate video and also isolate foreground objects using a combination of k- means clustering and mean squared error method, k- means clustering being performed on Apache s hadoop configuration [1][2][3]. In this method, first the background is modeled using a running average of all the frames. Statistically, the rate of averaging to decide the rate at which a workable model of the background in the video scene is obtained is determined [4]. Second, foreground objects contained in the video are obtained by using background subtraction. Next, the obtained foreground objects frame are color quantized using k- means clustering of the frames. It was found that frames that don t possess any significant motion and can be of no value in the post processing phase are complete blackened out after clustering. Such frames are filtered and sorted by a measure of black in the frame and obtain the most black frame. Finally, we do a mean squared error comparison of all the frames with the most black frame and extract the corresponding colored frame if the value returned is greater than a threshold [5]. A value of 0.0 means that the frames are similar. Thus only frames with significant foreground movement are extracted resulting in a method of key frame extraction which is computationally simple and highly time efficient. This paper contains seven sections. The first section introduces the topic and the proposed method. The second section provides some background that can aid with the understanding of the proposed method. The third section explains about how the background is modeled for background subtraction. The fourth section explains how the background subtraction phase is carried out and also how the clustering on a MapReduce setup is accomplished. The fifth section describes how finally the blank frames or black frames are filtered out using the mean squared error similarity checker. The sixth section illustrates the results obtained and compares them to similar results obtained using the well-known Gaussian Mixture Model. The seventh section presents the conclusion of the paper along with some insight into how we plan to further our research. Finally, references that have greatly helped us carry out the research have been listed. II. BACKGROUND A. Background modeling It refers to modeling of the background contained in the video scene without all the foreground objects. This background can later be used for extracting foreground objects of interest using techniques such as background /15 $ IEEE DOI /CICSyN

2 subtraction. Background modeling can be carried out using various methods. Some of the more popular methods include the running average method where frames are averaged to obtain a background of the scene dynamically, the fuzzy running average method, Morphological background modeling, etc. [6][7] B.K-means clustering K-means clustering refers to the clustering or grouping of dataset of point s representative of some data into the defined number of clusters. The grouping, as the name suggests is done by calculating the measure of the average of all the points representing the data when mapped into a co-ordinate system. The dataset is collected using statistical methods and once the desired clusters are obtained, the characteristics that define a particular cluster can be used to further process the meaning of the clustered data and also, draw logical co-relation between the data-points contained in the dataset. Figure 2: Clustered Data. Figure 2 shows the results of clustering. After grouping into clusters in this manner meaningful common characteristics can be identified among data points and processed. C. Mean squared error method Mean squared error is used to measure the average of the squares of the errors of an estimator or in simple terms, the difference between the entity that is estimating and what is estimated. The square root of the mean squared error is equivalent to what is known as the standard deviation in statistics. Figure 1: Unstructered data. Figure 1 shows unstructured data when plotted on the co-ordinate axis The above equation (1) represents the mean square error of a set of points. mn are the total number of points and the bracket represents the squares of the difference of the data points to the mean. All these differences are added to get the mean squared error. D. Key frame extraction When a video is recorded and frames are extracted. Upon careful analysis it is revealed that many of these frames are redundant frames in that, they contain no significant movement of objects in the scene. During the post processing phase of these frames for further analysis depending on the application, processing of the same type of frame repetitively introduces a sizeable amount of overhead that can be avoided by filtering out such frames. E. Foreground isolation Foreground objects in a scene are those objects that move against a background modeled in the scene. This background can be modeled using techniques already

3 discussed. To obtain foreground objects as defined, each frame of a video needs to be subtracted from the modeled background thus, leaving only objects that are in motion against that background and blacking out the rest of the frame. III. MODELING THE BACKGROUND USING RUNNING AVERAGE METHOD In this paper, this method has been used to model the background of the recorded video. First, the frames of the video are extracted and averaged as they are extracted. The above equation (2) represents the running average method. F n is the new or destination frame. F 0 is the old frame or source frame and, r is a regulator value which regulates the rate at which the foreground objects are deleted from the background in the scene. Figure 3: Foreground objects. Figure 3 shows the foreground image of objects moving in the background. In the above figure the foreground is that of a vehicle and people on two wheelers at a cross roads. F. MapReduce on the Hadoop Distributed File System MapReduce is a software paradigm that operates on the data that is stored on the Hadoop distributed cluster framework, basically targeted at making the processing of large amounts of data easier. Hadoop provides distributed storage which does away with much of the complexities of storing huge amounts of data. But since it is so scattered, we need an effective tool to navigate the data, process the data and aggregate the results. The distributions are commonly referred to as nodes. MapReduce provides this mechanism of collating node results. A master node holds a copy of all tasks (distributed across the framework) and the resources needed to perform these tasks. The other nodes, or the agent nodes of the master node (called the name node) have multiple copies of the data (relating to tasks and resources) to allow easy recovery from a malfunction or failure. The name node, however, is the single point of failure of the framework. There is no recovery mechanism if the name node fails. The unstructured data is read (typically from a file) by the mapper and is reshuffled to form <key,value> pairs of data points. The mapper then proceeds to assort these data points in some order of significance or by imposing some other such structure of meaning to make it easy for the reducer to process. The Reduce function aggregates the data points along the single line for the repeated occurrences, resulting in an output. Therefore by using a high value of r, non-static background objects are also considered when modeling the background. Thus only foreground objects that move for longer periods of time are averaged out of the modeled background. Figure 4: Foreground object being averaged out. Figure 4 shows the foreground object being deleted from the background using the running average method

4 for the reducer to concurrently re-calculate the centroids upon clustering. Cluster1 and Cluster2 is grouped as per the Euclidean distance between the centroids and the pixel points as shown in equation (3) and (4). The new centroids after grouping the pixel point is calculated by averaging the intensities of all pixel points belonging to or grouped under that cluster. Figure 5: Modeled background. Figure 5 shows the background modeled after sustained averaging for prolonged periods of time. IV. BACKGROUND SUBSTRACTION AND CLUSTERING USING MAP REDUCE After modeling the background, the frames of the video are subtracted from the background to isolate the foreground objects. However, there is noise present in the resulting foreground noise. To eliminate this noise to some extent, a bilateral filter is applied to the frame. This helps blur the noise and thus make the foreground objects more clear. After obtaining and de-noising the foreground mask, color quantization using k-means clustering is performed. This process reduces the number of distinct colors in the image and thus completely eliminates background noise. First, the width and height of the foreground mask image is obtained. Second, the image is converted from the RGB color space to the LAB color space to make use of the Euclidean distance between colors for easier implementation of the k-means clustering algorithm. Next, we reshape the frame of M x N pixels and 3 channels into a feature vector to convert the image into a two-dimensional array representation for clustering. Finally, we cluster using 2 clusters, and predict which quantized color the original color in the foreground mask is going to be. This is done by determining which centroid out of the two clusters, the input pixel is closest to. The clustering of all these pixels is carried out using the MapReduce implementation of k-means. The Mapper first chooses two initial colors as centroids to get started. Next, by comparing the Euclidean distance from each of the remaining colors to the two initial colors in consideration and in doing so, choosing the color that is closer, it proceeds to align the newly chosen color with the closest cluster. This data is replicated in the HDFS nodes to allow V. MEAN SQUARED ERROR SIMILARITY CHECK AND KEYFRAME EXTRACTION After clustering of the foreground masks, the frames that cause flicker as a result of the frame rate appear as completely black frames. All such frames are sorted according to the number of black pixels in them and a mean squared error comparison of the foreground mask frames and the black frames is done. If dissimilar it is considered a key frame. To carry out the mean squared error comparison, we begin by converting the frames or images from 8-bit unsigned integers to floating point. Next the pixel intensities of the two images are subtracted and squared. This difference is summed for all pairs of images to calculate the mean squared error. If the value returned by the mean squared error comparison is close to 0.0 the images are considered to be similar. Thus when the foreground masks are found dissimilar to the black frame, the value returned by the mean square error function was significantly greater than zero. VI. RESULTS This experiment was carried out with a MPEG-4 format and an AVI format video with 3 channel images. The frame rate of the video was 10 frames per second. Also, the same was carried out with the same video running at a frame rate of 25 frames per second. Figure 6: Foreground frames extracted using GMM

5 Figure 6 above shows foreground frames extracted using the Gaussian Mixture model. As is evident, the frame rate introduces a blank frame in between two frames of recorded movement. Also, the noise is not completely filtered out and there is still exists a small amount of background noise in the frames extracted.. VII. CONCLUSION AND FUTURE WORK In this paper, a novel approach to key frame extraction and foreground isolation, making use of MapReduce, has been shown to effectively and accurately model foreground objects and record actual foreground movement for further processing of the video. Furthermore, the proposed method also performs the required task in a timely manner with the trade off in time as compared to traditional methods being compensated by the higher accuracy and clarity achieved. The proposed technique is slower by only 5 seconds but filters out all blank frames and eliminates noise at a higher degree of efficiency compared to the Gaussian Mixture Model. We are also trying to obtain faster execution of the entire model by exploiting GPU architecture or CUDA architecture. REFERENCES Figure 7: Foreground Mask frames extracted using the proposed method. As Figure 7 shows, the frame extracted using the proposed method filters out the blank frames, eliminates noise and records only actual foreground movement. Also the proposed method only takes 30 seconds more to complete the frame extraction when compared to the frames extracted using the Gaussian Mixture Model. However, this deficiency is overcome using the MapReduce implementation of the k-means Clustering algorithm to only 5 seconds. Therefore for a trade-off of only 5 seconds, considerably more accuracy and clarity is achieved. [1] Apache Hadoop. apache. org/ [2] T.White, Hadoop: The Definitive Guide. O'Reilly Media, Yahoo! Press, June 5, 2009 [3] J. Dean and S. Ghemawat. Mapreduce: Simplied data processing on large clusters. Communications of the ACM, 51(1): , 2008 [4] M. Piccardi, "Background subtraction techniques: a review," IEEEInternational Conference on Systems, Man and Cybernetics, 2004: [5] L. Bruzzone and D. Prieto, "Automatic analysis of the difference image for unsupervised change detection," IEEE Trans. Geosci.Remote Sens.,vol. 38, no. 3, pp , May 2000 [6] M.HoseynSigari N Mozayani H Reza Rpurrerza Fuzzy Running Average and Fuzzy Background Subtraction:Concepts and Application, International Journal of Computer Science andnetwork Security, 2005 [7] Sen-Ching S. Cheung and Chandrika Kamath, "Robust Techniques for Background Subtraction in Urban Traffic Video," EURASIP Journal on Applied Signal Processing, vol.2005, pp , Jan

Improved MapReduce k-means Clustering Algorithm with Combiner

Improved MapReduce k-means Clustering Algorithm with Combiner 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation Improved MapReduce k-means Clustering Algorithm with Combiner Prajesh P Anchalia Department Of Computer Science and Engineering

More information

Real-time Detection of Illegally Parked Vehicles Using 1-D Transformation

Real-time Detection of Illegally Parked Vehicles Using 1-D Transformation Real-time Detection of Illegally Parked Vehicles Using 1-D Transformation Jong Taek Lee, M. S. Ryoo, Matthew Riley, and J. K. Aggarwal Computer & Vision Research Center Dept. of Electrical & Computer Engineering,

More information

A Comparative study of Clustering Algorithms using MapReduce in Hadoop

A Comparative study of Clustering Algorithms using MapReduce in Hadoop A Comparative study of Clustering Algorithms using MapReduce in Hadoop Dweepna Garg 1, Khushboo Trivedi 2, B.B.Panchal 3 1 Department of Computer Science and Engineering, Parul Institute of Engineering

More information

CATEGORIZATION OF THE DOCUMENTS BY USING MACHINE LEARNING

CATEGORIZATION OF THE DOCUMENTS BY USING MACHINE LEARNING CATEGORIZATION OF THE DOCUMENTS BY USING MACHINE LEARNING Amol Jagtap ME Computer Engineering, AISSMS COE Pune, India Email: 1 amol.jagtap55@gmail.com Abstract Machine learning is a scientific discipline

More information

Comparative Analysis of K means Clustering Sequentially And Parallely

Comparative Analysis of K means Clustering Sequentially And Parallely Comparative Analysis of K means Clustering Sequentially And Parallely Kavya D S 1, Chaitra D Desai 2 1 M.tech, Computer Science and Engineering, REVA ITM, Bangalore, India 2 REVA ITM, Bangalore, India

More information

SIMULINK based Moving Object Detection and Blob Counting Algorithm for Traffic Surveillance

SIMULINK based Moving Object Detection and Blob Counting Algorithm for Traffic Surveillance SIMULINK based Moving Object Detection and Blob Counting Algorithm for Traffic Surveillance Mayur Salve Dinesh Repale Sanket Shingate Divya Shah Asst. Professor ABSTRACT The main objective of this paper

More information

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications International Journal of Current Engineering and Technology E-ISSN 2277 4106, P-ISSN 2347 5161 2015INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Research Article Evaluation

More information

MAPREDUCE FOR BIG DATA PROCESSING BASED ON NETWORK TRAFFIC PERFORMANCE Rajeshwari Adrakatti

MAPREDUCE FOR BIG DATA PROCESSING BASED ON NETWORK TRAFFIC PERFORMANCE Rajeshwari Adrakatti International Journal of Computer Engineering and Applications, ICCSTAR-2016, Special Issue, May.16 MAPREDUCE FOR BIG DATA PROCESSING BASED ON NETWORK TRAFFIC PERFORMANCE Rajeshwari Adrakatti 1 Department

More information

Uday Kumar Sr 1, Naveen D Chandavarkar 2 1 PG Scholar, Assistant professor, Dept. of CSE, NMAMIT, Nitte, India. IJRASET 2015: All Rights are Reserved

Uday Kumar Sr 1, Naveen D Chandavarkar 2 1 PG Scholar, Assistant professor, Dept. of CSE, NMAMIT, Nitte, India. IJRASET 2015: All Rights are Reserved Implementation of K-Means Clustering Algorithm in Hadoop Framework Uday Kumar Sr 1, Naveen D Chandavarkar 2 1 PG Scholar, Assistant professor, Dept. of CSE, NMAMIT, Nitte, India Abstract Drastic growth

More information

Idle Object Detection in Video for Banking ATM Applications

Idle Object Detection in Video for Banking ATM Applications Research Journal of Applied Sciences, Engineering and Technology 4(24): 5350-5356, 2012 ISSN: 2040-7467 Maxwell Scientific Organization, 2012 Submitted: March 18, 2012 Accepted: April 06, 2012 Published:

More information

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY A PATH FOR HORIZING YOUR INNOVATIVE WORK DISTRIBUTED FRAMEWORK FOR DATA MINING AS A SERVICE ON PRIVATE CLOUD RUCHA V. JAMNEKAR

More information

MOVING OBJECT DETECTION USING BACKGROUND SUBTRACTION ALGORITHM USING SIMULINK

MOVING OBJECT DETECTION USING BACKGROUND SUBTRACTION ALGORITHM USING SIMULINK MOVING OBJECT DETECTION USING BACKGROUND SUBTRACTION ALGORITHM USING SIMULINK Mahamuni P. D 1, R. P. Patil 2, H.S. Thakar 3 1 PG Student, E & TC Department, SKNCOE, Vadgaon Bk, Pune, India 2 Asst. Professor,

More information

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 16, Issue 6, Ver. VI (Nov Dec. 2014), PP 29-33 Analysis of Image and Video Using Color, Texture and Shape Features

More information

BSFD: BACKGROUND SUBTRACTION FRAME DIFFERENCE ALGORITHM FOR MOVING OBJECT DETECTION AND EXTRACTION

BSFD: BACKGROUND SUBTRACTION FRAME DIFFERENCE ALGORITHM FOR MOVING OBJECT DETECTION AND EXTRACTION BSFD: BACKGROUND SUBTRACTION FRAME DIFFERENCE ALGORITHM FOR MOVING OBJECT DETECTION AND EXTRACTION 1 D STALIN ALEX, 2 Dr. AMITABH WAHI 1 Research Scholer, Department of Computer Science and Engineering,Anna

More information

Supervised vs. Unsupervised Learning

Supervised vs. Unsupervised Learning Clustering Supervised vs. Unsupervised Learning So far we have assumed that the training samples used to design the classifier were labeled by their class membership (supervised learning) We assume now

More information

REAL TIME ESTIMATION OF VEHICULAR SPEED USING NORMALIZED CORRELATION

REAL TIME ESTIMATION OF VEHICULAR SPEED USING NORMALIZED CORRELATION International Journal of Mechanical Engineering and Technology (IJMET) Volume 8, Issue 12, December 2017, pp. 628 633, Article ID: IJMET_08_12_065 Available online at http://www.iaeme.com/ijmet/issues.asp?jtype=ijmet&vtype=8&itype=12

More information

Fast Fuzzy Clustering of Infrared Images. 2. brfcm

Fast Fuzzy Clustering of Infrared Images. 2. brfcm Fast Fuzzy Clustering of Infrared Images Steven Eschrich, Jingwei Ke, Lawrence O. Hall and Dmitry B. Goldgof Department of Computer Science and Engineering, ENB 118 University of South Florida 4202 E.

More information

AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S

AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S Radha Krishna Rambola, Associate Professor, NMIMS University, India Akash Agrawal, Student at NMIMS University, India ABSTRACT Due to the

More information

Clustering. Supervised vs. Unsupervised Learning

Clustering. Supervised vs. Unsupervised Learning Clustering Supervised vs. Unsupervised Learning So far we have assumed that the training samples used to design the classifier were labeled by their class membership (supervised learning) We assume now

More information

AN EFFECTIVE DETECTION OF SATELLITE IMAGES VIA K-MEANS CLUSTERING ON HADOOP SYSTEM. Mengzhao Yang, Haibin Mei and Dongmei Huang

AN EFFECTIVE DETECTION OF SATELLITE IMAGES VIA K-MEANS CLUSTERING ON HADOOP SYSTEM. Mengzhao Yang, Haibin Mei and Dongmei Huang International Journal of Innovative Computing, Information and Control ICIC International c 2017 ISSN 1349-4198 Volume 13, Number 3, June 2017 pp. 1037 1046 AN EFFECTIVE DETECTION OF SATELLITE IMAGES VIA

More information

Detection and Classification of Vehicles

Detection and Classification of Vehicles Detection and Classification of Vehicles Gupte et al. 2002 Zeeshan Mohammad ECG 782 Dr. Brendan Morris. Introduction Previously, magnetic loop detectors were used to count vehicles passing over them. Advantages

More information

Fast and Effective System for Name Entity Recognition on Big Data

Fast and Effective System for Name Entity Recognition on Big Data International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-3, Issue-2 E-ISSN: 2347-2693 Fast and Effective System for Name Entity Recognition on Big Data Jigyasa Nigam

More information

Adaptive Background Mixture Models for Real-Time Tracking

Adaptive Background Mixture Models for Real-Time Tracking Adaptive Background Mixture Models for Real-Time Tracking Chris Stauffer and W.E.L Grimson CVPR 1998 Brendan Morris http://www.ee.unlv.edu/~b1morris/ecg782/ 2 Motivation Video monitoring and surveillance

More information

Connected Component Analysis and Change Detection for Images

Connected Component Analysis and Change Detection for Images Connected Component Analysis and Change Detection for Images Prasad S.Halgaonkar Department of Computer Engg, MITCOE Pune University, India Abstract Detection of the region of change in images of a particular

More information

The MapReduce Framework

The MapReduce Framework The MapReduce Framework In Partial fulfilment of the requirements for course CMPT 816 Presented by: Ahmed Abdel Moamen Agents Lab Overview MapReduce was firstly introduced by Google on 2004. MapReduce

More information

Cluster Analysis. Prof. Thomas B. Fomby Department of Economics Southern Methodist University Dallas, TX April 2008 April 2010

Cluster Analysis. Prof. Thomas B. Fomby Department of Economics Southern Methodist University Dallas, TX April 2008 April 2010 Cluster Analysis Prof. Thomas B. Fomby Department of Economics Southern Methodist University Dallas, TX 7575 April 008 April 010 Cluster Analysis, sometimes called data segmentation or customer segmentation,

More information

Survey on Wireless Intelligent Video Surveillance System Using Moving Object Recognition Technology

Survey on Wireless Intelligent Video Surveillance System Using Moving Object Recognition Technology Survey on Wireless Intelligent Video Surveillance System Using Moving Object Recognition Technology Durgesh Patil Phone: +919766654777; E-mail: patildurgesh95@yahoo.com Sachin Joshi Phone: +919767845334;

More information

Automatic Tracking of Moving Objects in Video for Surveillance Applications

Automatic Tracking of Moving Objects in Video for Surveillance Applications Automatic Tracking of Moving Objects in Video for Surveillance Applications Manjunath Narayana Committee: Dr. Donna Haverkamp (Chair) Dr. Arvin Agah Dr. James Miller Department of Electrical Engineering

More information

Introduction to MapReduce

Introduction to MapReduce Basics of Cloud Computing Lecture 4 Introduction to MapReduce Satish Srirama Some material adapted from slides by Jimmy Lin, Christophe Bisciglia, Aaron Kimball, & Sierra Michels-Slettvet, Google Distributed

More information

Detection and Classification of a Moving Object in a Video Stream

Detection and Classification of a Moving Object in a Video Stream Detection and Classification of a Moving Object in a Video Stream Asim R. Aldhaheri and Eran A. Edirisinghe Abstract In this paper we present a new method for detecting and classifying moving objects into

More information

Semantic-Based Surveillance Video Retrieval

Semantic-Based Surveillance Video Retrieval Semantic-Based Surveillance Video Retrieval Weiming Hu, Dan Xie, Zhouyu Fu, Wenrong Zeng, and Steve Maybank, Senior Member, IEEE IEEE Transactions on Image Processing, Vol. 16, No. 4, April 2007 Present

More information

Department of Computer Science San Marcos, TX Report Number TXSTATE-CS-TR Clustering in the Cloud. Xuan Wang

Department of Computer Science San Marcos, TX Report Number TXSTATE-CS-TR Clustering in the Cloud. Xuan Wang Department of Computer Science San Marcos, TX 78666 Report Number TXSTATE-CS-TR-2010-24 Clustering in the Cloud Xuan Wang 2010-05-05 !"#$%&'()*+()+%,&+!"-#. + /+!"#$%&'()*+0"*-'(%,1$+0.23%(-)+%-+42.--3+52367&.#8&+9'21&:-';

More information

A Moving Object Segmentation Method for Low Illumination Night Videos Soumya. T

A Moving Object Segmentation Method for Low Illumination Night Videos Soumya. T Proceedings of the World Congress on Engineering and Computer Science 28 WCECS 28, October 22-24, 28, San Francisco, USA A Moving Object Segmentation Method for Low Illumination Night Videos Soumya. T

More information

PSON: A Parallelized SON Algorithm with MapReduce for Mining Frequent Sets

PSON: A Parallelized SON Algorithm with MapReduce for Mining Frequent Sets 2011 Fourth International Symposium on Parallel Architectures, Algorithms and Programming PSON: A Parallelized SON Algorithm with MapReduce for Mining Frequent Sets Tao Xiao Chunfeng Yuan Yihua Huang Department

More information

Chapter 3 Image Registration. Chapter 3 Image Registration

Chapter 3 Image Registration. Chapter 3 Image Registration Chapter 3 Image Registration Distributed Algorithms for Introduction (1) Definition: Image Registration Input: 2 images of the same scene but taken from different perspectives Goal: Identify transformation

More information

CHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION

CHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION CHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION 6.1 INTRODUCTION Fuzzy logic based computational techniques are becoming increasingly important in the medical image analysis arena. The significant

More information

Defining a Better Vehicle Trajectory With GMM

Defining a Better Vehicle Trajectory With GMM Santa Clara University Department of Computer Engineering COEN 281 Data Mining Professor Ming- Hwa Wang, Ph.D Winter 2016 Defining a Better Vehicle Trajectory With GMM Christiane Gregory Abe Millan Contents

More information

Unsupervised Learning and Clustering

Unsupervised Learning and Clustering Unsupervised Learning and Clustering Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Spring 2008 CS 551, Spring 2008 c 2008, Selim Aksoy (Bilkent University)

More information

An Empirical Study of Block Matching Techniques for the Detection of Moving Objects. Abstract

An Empirical Study of Block Matching Techniques for the Detection of Moving Objects. Abstract An Empirical Study of Block Matching Techniques for the Detection of Moving Objects Nicole S. Love and Chandrika Kamath {love1, kamath}@llnl.gov Center for Applied Scientific Computing Lawrence Livermore

More information

Mounica B, Aditya Srivastava, Md. Faisal Alam

Mounica B, Aditya Srivastava, Md. Faisal Alam International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2017 IJSRCSEIT Volume 2 Issue 3 ISSN : 2456-3307 Clustering of large datasets using Hadoop Ecosystem

More information

Implementation of the Gaussian Mixture Model Algorithm for Real-Time Segmentation of High Definition video: A review 1

Implementation of the Gaussian Mixture Model Algorithm for Real-Time Segmentation of High Definition video: A review 1 Implementation of the Gaussian Mixture Model Algorithm for Real-Time Segmentation of High Definition video: A review 1 Mr. Sateesh Kumar, 2 Mr. Rupesh Mahamune 1, M. Tech. Scholar (Digital Electronics),

More information

/13/$ IEEE

/13/$ IEEE Proceedings of the 013 International Conference on Pattern Recognition, Informatics and Mobile Engineering, February 1- Background Subtraction Based on Threshold detection using Modified K-Means Algorithm

More information

Detecting motion by means of 2D and 3D information

Detecting motion by means of 2D and 3D information Detecting motion by means of 2D and 3D information Federico Tombari Stefano Mattoccia Luigi Di Stefano Fabio Tonelli Department of Electronics Computer Science and Systems (DEIS) Viale Risorgimento 2,

More information

Background subtraction in people detection framework for RGB-D cameras

Background subtraction in people detection framework for RGB-D cameras Background subtraction in people detection framework for RGB-D cameras Anh-Tuan Nghiem, Francois Bremond INRIA-Sophia Antipolis 2004 Route des Lucioles, 06902 Valbonne, France nghiemtuan@gmail.com, Francois.Bremond@inria.fr

More information

PLATFORM AND SOFTWARE AS A SERVICE THE MAPREDUCE PROGRAMMING MODEL AND IMPLEMENTATIONS

PLATFORM AND SOFTWARE AS A SERVICE THE MAPREDUCE PROGRAMMING MODEL AND IMPLEMENTATIONS PLATFORM AND SOFTWARE AS A SERVICE THE MAPREDUCE PROGRAMMING MODEL AND IMPLEMENTATIONS By HAI JIN, SHADI IBRAHIM, LI QI, HAIJUN CAO, SONG WU and XUANHUA SHI Prepared by: Dr. Faramarz Safi Islamic Azad

More information

OTCYMIST: Otsu-Canny Minimal Spanning Tree for Born-Digital Images

OTCYMIST: Otsu-Canny Minimal Spanning Tree for Born-Digital Images OTCYMIST: Otsu-Canny Minimal Spanning Tree for Born-Digital Images Deepak Kumar and A G Ramakrishnan Medical Intelligence and Language Engineering Laboratory Department of Electrical Engineering, Indian

More information

International Journal of Innovative Research in Computer and Communication Engineering

International Journal of Innovative Research in Computer and Communication Engineering Moving Object Detection By Background Subtraction V.AISWARYA LAKSHMI, E.ANITHA, S.SELVAKUMARI. Final year M.E, Department of Computer Science and Engineering Abstract : Intelligent video surveillance systems

More information

Data Clustering on the Parallel Hadoop MapReduce Model. Dimitrios Verraros

Data Clustering on the Parallel Hadoop MapReduce Model. Dimitrios Verraros Data Clustering on the Parallel Hadoop MapReduce Model Dimitrios Verraros Overview The purpose of this thesis is to implement and benchmark the performance of a parallel K- means clustering algorithm on

More information

Unsupervised Learning and Clustering

Unsupervised Learning and Clustering Unsupervised Learning and Clustering Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Spring 2009 CS 551, Spring 2009 c 2009, Selim Aksoy (Bilkent University)

More information

An Efficient Clustering for Crime Analysis

An Efficient Clustering for Crime Analysis An Efficient Clustering for Crime Analysis Malarvizhi S 1, Siddique Ibrahim 2 1 UG Scholar, Department of Computer Science and Engineering, Kumaraguru College Of Technology, Coimbatore, Tamilnadu, India

More information

Object Tracking using HOG and SVM

Object Tracking using HOG and SVM Object Tracking using HOG and SVM Siji Joseph #1, Arun Pradeep #2 Electronics and Communication Engineering Axis College of Engineering and Technology, Ambanoly, Thrissur, India Abstract Object detection

More information

Keywords Hadoop, Map Reduce, K-Means, Data Analysis, Storage, Clusters.

Keywords Hadoop, Map Reduce, K-Means, Data Analysis, Storage, Clusters. Volume 6, Issue 3, March 2016 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Special Issue

More information

Efficient Content Based Image Retrieval System with Metadata Processing

Efficient Content Based Image Retrieval System with Metadata Processing IJIRST International Journal for Innovative Research in Science & Technology Volume 1 Issue 10 March 2015 ISSN (online): 2349-6010 Efficient Content Based Image Retrieval System with Metadata Processing

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

Image Filtering with MapReduce in Pseudo-Distribution Mode

Image Filtering with MapReduce in Pseudo-Distribution Mode Image Filtering with MapReduce in Pseudo-Distribution Mode Tharindu D. Gamage, Jayathu G. Samarawickrama, Ranga Rodrigo and Ajith A. Pasqual Department of Electronic & Telecommunication Engineering, University

More information

Automatic Shadow Removal by Illuminance in HSV Color Space

Automatic Shadow Removal by Illuminance in HSV Color Space Computer Science and Information Technology 3(3): 70-75, 2015 DOI: 10.13189/csit.2015.030303 http://www.hrpub.org Automatic Shadow Removal by Illuminance in HSV Color Space Wenbo Huang 1, KyoungYeon Kim

More information

University of Ghana Department of Computer Engineering School of Engineering Sciences College of Basic and Applied Sciences

University of Ghana Department of Computer Engineering School of Engineering Sciences College of Basic and Applied Sciences University of Ghana Department of Computer Engineering School of Engineering Sciences College of Basic and Applied Sciences CPEN 405: Artificial Intelligence Lab 7 November 15, 2017 Unsupervised Learning

More information

Region-based Segmentation

Region-based Segmentation Region-based Segmentation Image Segmentation Group similar components (such as, pixels in an image, image frames in a video) to obtain a compact representation. Applications: Finding tumors, veins, etc.

More information

University of Cambridge Engineering Part IIB Module 4F12 - Computer Vision and Robotics Mobile Computer Vision

University of Cambridge Engineering Part IIB Module 4F12 - Computer Vision and Robotics Mobile Computer Vision report University of Cambridge Engineering Part IIB Module 4F12 - Computer Vision and Robotics Mobile Computer Vision Web Server master database User Interface Images + labels image feature algorithm Extract

More information

Object Detection in a Fixed Frame

Object Detection in a Fixed Frame Object Detection in a Fixed Frame Debjyoti Bagchi 1, Dipaneeta Roy Chowdhury 2 and Satarupa Das 2 1 Assistant Professor, Calcutta Institute Of Engineering And Management Kolkata, India, 2 Calcutta Institute

More information

Object Detection in Video Streams

Object Detection in Video Streams Object Detection in Video Streams Sandhya S Deore* *Assistant Professor Dept. of Computer Engg., SRES COE Kopargaon *sandhya.deore@gmail.com ABSTRACT Object Detection is the most challenging area in video

More information

Improving License Plate Recognition Rate using Hybrid Algorithms

Improving License Plate Recognition Rate using Hybrid Algorithms Improving License Plate Recognition Rate using Hybrid Algorithms 1 Anjli Varghese, 2 R Srikantaswamy 1,2 Dept. of Electronics and Communication Engineering, Siddaganga Institute of Technology, Tumakuru,

More information

Pedestrian Detection Using Correlated Lidar and Image Data EECS442 Final Project Fall 2016

Pedestrian Detection Using Correlated Lidar and Image Data EECS442 Final Project Fall 2016 edestrian Detection Using Correlated Lidar and Image Data EECS442 Final roject Fall 2016 Samuel Rohrer University of Michigan rohrer@umich.edu Ian Lin University of Michigan tiannis@umich.edu Abstract

More information

Unsupervised Learning Partitioning Methods

Unsupervised Learning Partitioning Methods Unsupervised Learning Partitioning Methods Road Map 1. Basic Concepts 2. K-Means 3. K-Medoids 4. CLARA & CLARANS Cluster Analysis Unsupervised learning (i.e., Class label is unknown) Group data to form

More information

Estimating Speed, Velocity, Acceleration and Angle Using Image Addition Method

Estimating Speed, Velocity, Acceleration and Angle Using Image Addition Method Estimating Speed, Velocity, Acceleration and Angle Using Image Addition Method Sawan Singh Third Year Student, Dept. of ECE, UIET, CSJM University, Kanpur, India ABSTRACT: This paper leads us to a new

More information

Multi prototype fuzzy pattern matching for handwritten character recognition

Multi prototype fuzzy pattern matching for handwritten character recognition Multi prototype fuzzy pattern matching for handwritten character recognition MILIND E. RANE, DHABE P. S AND J. B. PATIL Dept. of Electronics and Computer, R.C. Patel Institute of Technology, Shirpur, Dist.

More information

A Parallel Algorithm for Finding Sub-graph Isomorphism

A Parallel Algorithm for Finding Sub-graph Isomorphism CS420: Parallel Programming, Fall 2008 Final Project A Parallel Algorithm for Finding Sub-graph Isomorphism Ashish Sharma, Santosh Bahir, Sushant Narsale, Unmil Tambe Department of Computer Science, Johns

More information

Enhancing K-means Clustering Algorithm with Improved Initial Center

Enhancing K-means Clustering Algorithm with Improved Initial Center Enhancing K-means Clustering Algorithm with Improved Initial Center Madhu Yedla #1, Srinivasa Rao Pathakota #2, T M Srinivasa #3 # Department of Computer Science and Engineering, National Institute of

More information

Module 7 VIDEO CODING AND MOTION ESTIMATION

Module 7 VIDEO CODING AND MOTION ESTIMATION Module 7 VIDEO CODING AND MOTION ESTIMATION Lesson 20 Basic Building Blocks & Temporal Redundancy Instructional Objectives At the end of this lesson, the students should be able to: 1. Name at least five

More information

Programming Exercise 7: K-means Clustering and Principal Component Analysis

Programming Exercise 7: K-means Clustering and Principal Component Analysis Programming Exercise 7: K-means Clustering and Principal Component Analysis Machine Learning May 13, 2012 Introduction In this exercise, you will implement the K-means clustering algorithm and apply it

More information

Graph-based High Level Motion Segmentation using Normalized Cuts

Graph-based High Level Motion Segmentation using Normalized Cuts Graph-based High Level Motion Segmentation using Normalized Cuts Sungju Yun, Anjin Park and Keechul Jung Abstract Motion capture devices have been utilized in producing several contents, such as movies

More information

Pairwise Threshold for Gaussian Mixture Classification and its Application on Human Tracking Enhancement

Pairwise Threshold for Gaussian Mixture Classification and its Application on Human Tracking Enhancement Pairwise Threshold for Gaussian Mixture Classification and its Application on Human Tracking Enhancement Daegeon Kim Sung Chun Lee Institute for Robotics and Intelligent Systems University of Southern

More information

Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation

Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation ÖGAI Journal 24/1 11 Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation Michael Bleyer, Margrit Gelautz, Christoph Rhemann Vienna University of Technology

More information

Robust color segmentation algorithms in illumination variation conditions

Robust color segmentation algorithms in illumination variation conditions 286 CHINESE OPTICS LETTERS / Vol. 8, No. / March 10, 2010 Robust color segmentation algorithms in illumination variation conditions Jinhui Lan ( ) and Kai Shen ( Department of Measurement and Control Technologies,

More information

A Texture-based Method for Detecting Moving Objects

A Texture-based Method for Detecting Moving Objects A Texture-based Method for Detecting Moving Objects Marko Heikkilä University of Oulu Machine Vision Group FINLAND Introduction The moving object detection, also called as background subtraction, is one

More information

Parallelizing Multi-featured Content Based Search and Retrieval of Videos through High Performance Computing

Parallelizing Multi-featured Content Based Search and Retrieval of Videos through High Performance Computing Indonesian Journal of Electrical Engineering and Computer Science Vol. 5, No. 1, January 2017, pp. 214 ~ 219 DOI: 10.11591/ijeecs.v5.i1.pp 214-219 214 Parallelizing Multi-featured Content Based Search

More information

A New HadoopBased Network Management System with Policy Approach

A New HadoopBased Network Management System with Policy Approach Computer Engineering and Applications Vol. 3, No. 3, September 2014 A New HadoopBased Network Management System with Policy Approach Department of Computer Engineering and IT, Shiraz University of Technology,

More information

The Application of Image Processing to Solve Occlusion Issue in Object Tracking

The Application of Image Processing to Solve Occlusion Issue in Object Tracking The Application of Image Processing to Solve Occlusion Issue in Object Tracking Yun Zhe Cheong 1 and Wei Jen Chew 1* 1 School of Engineering, Taylor s University, 47500 Subang Jaya, Selangor, Malaysia.

More information

Learning the Three Factors of a Non-overlapping Multi-camera Network Topology

Learning the Three Factors of a Non-overlapping Multi-camera Network Topology Learning the Three Factors of a Non-overlapping Multi-camera Network Topology Xiaotang Chen, Kaiqi Huang, and Tieniu Tan National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy

More information

Unsupervised Learning : Clustering

Unsupervised Learning : Clustering Unsupervised Learning : Clustering Things to be Addressed Traditional Learning Models. Cluster Analysis K-means Clustering Algorithm Drawbacks of traditional clustering algorithms. Clustering as a complex

More information

Image Inpainting by Hyperbolic Selection of Pixels for Two Dimensional Bicubic Interpolations

Image Inpainting by Hyperbolic Selection of Pixels for Two Dimensional Bicubic Interpolations Image Inpainting by Hyperbolic Selection of Pixels for Two Dimensional Bicubic Interpolations Mehran Motmaen motmaen73@gmail.com Majid Mohrekesh mmohrekesh@yahoo.com Mojtaba Akbari mojtaba.akbari@ec.iut.ac.ir

More information

Spatial Enhancement Definition

Spatial Enhancement Definition Spatial Enhancement Nickolas Faust The Electro- Optics, Environment, and Materials Laboratory Georgia Tech Research Institute Georgia Institute of Technology Definition Spectral enhancement relies on changing

More information

V Conclusions. V.1 Related work

V Conclusions. V.1 Related work V Conclusions V.1 Related work Even though MapReduce appears to be constructed specifically for performing group-by aggregations, there are also many interesting research work being done on studying critical

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

Vehicle Detection & Tracking

Vehicle Detection & Tracking Vehicle Detection & Tracking Gagan Bansal Johns Hopkins University gagan@cis.jhu.edu Sandeep Mullur Johns Hopkins University sandeepmullur@gmail.com Abstract Object tracking is a field of intense research

More information

COMPUTER VISION. Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai

COMPUTER VISION. Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai COMPUTER VISION Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai 600036. Email: sdas@iitm.ac.in URL: //www.cs.iitm.ernet.in/~sdas 1 INTRODUCTION 2 Human Vision System (HVS) Vs.

More information

Global Journal of Engineering Science and Research Management

Global Journal of Engineering Science and Research Management A FUNDAMENTAL CONCEPT OF MAPREDUCE WITH MASSIVE FILES DATASET IN BIG DATA USING HADOOP PSEUDO-DISTRIBUTION MODE K. Srikanth*, P. Venkateswarlu, Ashok Suragala * Department of Information Technology, JNTUK-UCEV

More information

ABSTRACT I. INTRODUCTION

ABSTRACT I. INTRODUCTION International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2018 IJSRCSEIT Volume 3 Issue 3 ISS: 2456-3307 Hadoop Periodic Jobs Using Data Blocks to Achieve

More information

Map Reduce.

Map Reduce. Map Reduce dacosta@irit.fr Divide and conquer at PaaS Second Third Fourth 100 % // Fifth Sixth Seventh Cliquez pour 2 Typical problem Second Extract something of interest from each MAP Third Shuffle and

More information

CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR)

CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR) 63 CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR) 4.1 INTRODUCTION The Semantic Region Based Image Retrieval (SRBIR) system automatically segments the dominant foreground region and retrieves

More information

In the recent past, the World Wide Web has been witnessing an. explosive growth. All the leading web search engines, namely, Google,

In the recent past, the World Wide Web has been witnessing an. explosive growth. All the leading web search engines, namely, Google, 1 1.1 Introduction In the recent past, the World Wide Web has been witnessing an explosive growth. All the leading web search engines, namely, Google, Yahoo, Askjeeves, etc. are vying with each other to

More information

OFFLINE SIGNATURE VERIFICATION

OFFLINE SIGNATURE VERIFICATION International Journal of Electronics and Communication Engineering and Technology (IJECET) Volume 8, Issue 2, March - April 2017, pp. 120 128, Article ID: IJECET_08_02_016 Available online at http://www.iaeme.com/ijecet/issues.asp?jtype=ijecet&vtype=8&itype=2

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 11 140311 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Motion Analysis Motivation Differential Motion Optical

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

K-Means Clustering. Sargur Srihari

K-Means Clustering. Sargur Srihari K-Means Clustering Sargur srihari@cedar.buffalo.edu 1 Topics in Mixture Models and EM Mixture models K-means Clustering Mixtures of Gaussians Maximum Likelihood EM for Gaussian mistures EM Algorithm Gaussian

More information

A physically motivated pixel-based model for background subtraction in 3D images

A physically motivated pixel-based model for background subtraction in 3D images A physically motivated pixel-based model for background subtraction in 3D images M. Braham, A. Lejeune and M. Van Droogenbroeck INTELSIG, Montefiore Institute, University of Liège, Belgium IC3D - December

More information

Introduction to Medical Imaging (5XSA0) Module 5

Introduction to Medical Imaging (5XSA0) Module 5 Introduction to Medical Imaging (5XSA0) Module 5 Segmentation Jungong Han, Dirk Farin, Sveta Zinger ( s.zinger@tue.nl ) 1 Outline Introduction Color Segmentation region-growing region-merging watershed

More information

[2006] IEEE. Reprinted, with permission, from [Wenjing Jia, Huaifeng Zhang, Xiangjian He, and Qiang Wu, A Comparison on Histogram Based Image

[2006] IEEE. Reprinted, with permission, from [Wenjing Jia, Huaifeng Zhang, Xiangjian He, and Qiang Wu, A Comparison on Histogram Based Image [6] IEEE. Reprinted, with permission, from [Wenjing Jia, Huaifeng Zhang, Xiangjian He, and Qiang Wu, A Comparison on Histogram Based Image Matching Methods, Video and Signal Based Surveillance, 6. AVSS

More information

Unsupervised Learning

Unsupervised Learning Outline Unsupervised Learning Basic concepts K-means algorithm Representation of clusters Hierarchical clustering Distance functions Which clustering algorithm to use? NN Supervised learning vs. unsupervised

More information

Open Access Surveillance Video Synopsis Based on Moving Object Matting Using Noninteractive

Open Access Surveillance Video Synopsis Based on Moving Object Matting Using Noninteractive Send Orders for Reprints to reprints@benthamscience.net The Open Automation and Control Systems Journal, 2013, 5, 113-118 113 Open Access Surveillance Video Synopsis Based on Moving Object Matting Using

More information