Single-Frame Image Processing Techniques for Low-SNR Infrared Imagery

Size: px
Start display at page:

Download "Single-Frame Image Processing Techniques for Low-SNR Infrared Imagery"

Transcription

1 Single-Frame Image Processing Techniques for Low-SNR Infrared Imagery Richard Edmondson, Michael Rodgers, Michele Banish, Michelle Johnson Sensor Technologies Huntsville, AL Heggere Ranganath University of Alabama in Huntsville Huntsville, AL Sensor Technologies is a small, woman-owned business with expertise in the following areas: Custom Optical Sensor Prototypes Advanced Signal Processing Algorithms 3D Visualization Technology Field Test support and Data Analysis Diverse Expertise and Customer Base DoD and DHS Small Business Innovation Research Collaborating with Large and Small Businesses Multiple contract vehicles for Engineering Services (CIMTIC, AMCOM, SETAC, etc.) Founded in 2003 and located in Huntsville, Alabama Meet us in booth # 28! is marketing our Sensors, Tracker, and 3D Visualization System.

2 Problem Being Addressed Detect a signal of small spatial extent in infrared imagery at low Signal to Noise Ratio (SNR ~2 ) SNR defined as peak signal intensity divided by spatial standard deviation of background Initial Approach Detect target in uncorrected infrared imagery (no NUC) Pulse Coupled Neural Network (PCNN) Signal eliminates is blurred due to mechanical motion - DC data of no interest Unfortunately, there was no way to devise a set of optimal control parameters An acceptable solution was achieved with training IR HWIL Data: Difficult data set to process artifacts, low S/N PCNN offers a solution with significant improvements over thresholding Best performance to date offers >7000 fewer False Target Pixels Approach Segment signal pixels from background pixels as near the focal plane as possible Explore ways to optimize and automate PCNN solutions that were identified in prior research as candidates for signal segmentation Evaluate simple spatial filter techniques that exploit sensor and readout circuit properties to segment signal Compare and report the results of all viable approaches Sample input imagery at 2 contrast settings (SNR = 2.5), and sample PCNN binary output Fixed pattern noise reduced by background subtraction; readout noise still apparent 2

3 Pulse Coupled Neural Network A pixel feeds a neuron with feed-forward and feed-back input from a local neighborhood and the network is inspired by vision biology The neuron state is compared to a threshold that decays until the neuron fires, at which point the threshold is increased (pulse) Linking and Feeding kernels are used to weight the neighborhood around the neuron when evaluating its state S is input signal, U is neuron state, Y is activation state, Θ is the threshold " Variables are the a values, b, and V values, as well as the size and weighting of the Linking and Feeding kernels, W and M F ( n) = e L ( n) = e U ( n) = F ( n Q ( n) = e F ( n -) + S + V n L ( n -) + VL )[ + bl ( n) ] M ì, if U( n) > Q ( n -) Y ( n) -a F Dn -a LD -a QDn Q( n -) + V Y ( n) Q F W Y ( n -) Y ( n -) Equations are evaluated iteratively Each iteration is called a pulse PCNN For Image Processing Research has shown there is value in using PCNN for image processing Segmentation (Ranganath, Banish, Lindblad, Kinser) Edge detection (Lindblad, Kinser) Target recognition (Lindblad) Each input pixel feeds a single neuron in the PCNN Problems using PCNN for image processing Heuristics for selecting coefficients require human intervention Not previously possible to determine on which pulse the feature of interest will be identified, meaning that human evaluation of output after each pulse is necessary Ranganath and Banish explored method of using image statistical properties to set coefficients, and evaluated using only one pulse Single pulse does not fully allow power of decaying threshold to segment image Our solution is use of Genetic Algorithm (GA) to select coefficients which segment image on the pulse of our choosing Typical scene and signal used for algorithm development 3

4 Genetic Algorithm for PCNN Genetic Algorithm (GA) allows use of large data set to search for a solution to a nonlinear problem. It is an intelligent exploitation of a random search that finds acceptably good solutions. The values for each variables in the PCNN are encoded into bit fields in a chromosome that represent a vector of PCNN coefficients Each input vector of PCNN coefficients, called an individual is scored for fitness as a solution Individuals are selected for mating within and between populations and sub-populations The GA used Rank order selection Demes (sub-populations) Uniform crossover Scoring was based on Successfully identifying the signal Failure to identify the signal Identifying pixels not on signal in the output (false alarms) The PCNN was always scored after a specific pulse in our case pulse 4 but the pulse number could have been encoded as another variable in the chromosome Typical Results Point signal blurred across several pixels (jitter) SNR defined as peak signal counts divided by the spatial sigma of the background Input Image Indicates Program Goals Truth Image Output Image 4

5 Spatial Filtering Approach Evaluate methods that reject readout and other noise sources, but return signal pixels Perform statistical analysis of background imagery Devise methods to segment small signals from background using a variety of kernels Convolution kernels can be implemented using a shift register scheme in an FPGA Requires only multiply/accumulate operations and comparison to a threshold InSb and HgCdTe IR FPA imagery have distinct properties such as focal plane non-uniformity and column readout noise that make segmentation of point signals difficult. Kernels for Spatial Filtering Local Mean versus Global Threshold Local Mean versus Border Threshold, aka Box Filter Intensity versus Local Shaped Threshold, aka Cross Average Filter Intensity versus Local Shaped Threshold, aka Line Average Filter 5

6 Simple Thresholding Kernels Local Mean m = S 9 ì if m > mspatial + 2 s Y î0 spatial Local Mean Filtering simply compares the mean of a region against the global mean of the image plus two times the standard deviation Mean and standard deviation can be computed on previous image if background image properties change slowly Requires relatively uniform background Filtering with the Box Filter compares the mean of a region against mean of a border region plus two times the standard deviation Mean and standard deviation can be computed on previous image if background image properties change slowly Requires relatively uniform background m = 9 b = 24 mn mn ì if m > b + 2 s Y S S, where m and n specify the 24 border pixels in a 7x7 neighborhood about the pixel of interest spatial Box Filter Kernels with Shaped Thresholds Cross Average Filter m = 20 ì, if S > m + 3 s T ì, if T > 5 Y S, where k and l specify th e 20 pixels that form a cross pattern in a 9x9 neighborho od ± 4 pixels from the pixel of interest spatial where k and l specify a 5x5 kernel about the pixel of interest Line Average Filter m = 0 ì, if S > m + 3 s T ì, if T > 5 Y S, where k and l specify th e 0 pixels that reside in a 9 pixel line spatial ± 4 where k and l specify a 5x5 kernel about the pixel of interest pixels from the pixel of interest These two techniques work to identify signal in backgrounds which exhibit linear fixed pattern noise properties, such as column readout noise Both filters compute a temporary state indicating whether the signal intensity exceeds the mean of the linear regions in the kernel by three global standard deviations Algorithm output values are computed using a median filter; i.e. counting the number of on pixels in a region 6

7 Comparison of Algorithms Probability of Detection (Pd) PCNN provides best detection at very low SNR Shown are PCNNs trained with 50 and 250 false alarm pixels per frame allowed Using the GA, PCNN solutions can achieve Pd approaching 90% at SNR of 2 if the application can tolerate 500 to 000 false alarm pixels per frame GA scoring can be adjusted to create solutions that favor either Pd or low false alarms Single Frame Probability of Detection Results Signal to Noise Ratio (SNR) PCNN trained with 50 allowable False Alarms Local Mean Box Filter Cross Average Line Average Vertical Line Average PCNN trained with 250 allowable False Alarms Comparison of Algorithms Spatial filters provide the simplest implementation to low SNR detection, but are not effective below SNR of 3 Spatial filters excel at rejecting background, but do so at the expense of signal detection at low SNR More highly dependent on spatial extent than PCNN Single Frame Probability of Detection Results Probability of Detection (Pd) Signal to Noise Ratio (SNR) PCNN trained with 50 allowable False Alarms Local Mean Box Filter Cross Average Line Average Vertical Line Average PCNN trained with 250 allowable False Alarms 7

8 Comparison of Results at Low SNR for Simulated IR Backgrounds and Single Point Signals Input Truth Local Mean Box Filter Image Image SNR of 2.5 is below the performance ability of spatial filters PCNN identifies pixels on all signal patches Cross Line Matched PCNN Average Average Filter Input is Background Subtracted. Readout noise is apparent, but non-uniformity of background is reduced All non-zero signal pixels are shown Green pixels are on signal, red pixels are missed signals, and yellow are false alarms All non-zero pixels for each signal patch are shown, but only 2-3 pixels per patch are more than a few counts DSP/FPGA Processing Solutions Boards to host these and other image processing algorithms in DSP and FPGA nearing completion Applications include UAV, UGV, and remote sensing for homeland security and vision based guidance and control Flexible Programming Environment High Speed Operation Memory Onboard High Speed Bus Real Time Processing Digital and analog inputs and outputs Gen : one TI DSP and Gen 2: two TI DSPs. Both with an aggregate computational rate of 4.8 billion fixed point instructions per second or 3.6 billion floating point instructions per second. Gen : Lattice FPGA and Gen 2: Two Lattice FPGAs. Each DSP has access to 28 Mbytes of zero wait state synchronous dynamic RAM Zero wait state Dual Port RAM. Bi-directional communications FIFOs. Gen : implements one Gen 2: implements two 00 MHz external memory interface (EMIF) buses each capable of sustaining 400 MByte/second data transfers. Command/Status registers and interrupt logic provide for inter-processor data sharing and handshaking. 52 x 52 imagery at 400 frames/second. This estimate assumes 50 fixed point operations/pixel. EMIF interface port is attached to each bus to allow the use of custom or 3rd party daughter cards. 8

Foveation by a Pulse-Coupled Neural Network

Foveation by a Pulse-Coupled Neural Network Foveation by a Pulse-Coupled Neural Network Jason M. Kinser Center for Applied Optical Sciences Dept. of Physics, PO Box 1268 Alabama A & M Univ. Normal, AL 35762 jaker@mycroft.caos.aamu.edu Keywords Foveation,

More information

SECTION 5 IMAGE PROCESSING 2

SECTION 5 IMAGE PROCESSING 2 SECTION 5 IMAGE PROCESSING 2 5.1 Resampling 3 5.1.1 Image Interpolation Comparison 3 5.2 Convolution 3 5.3 Smoothing Filters 3 5.3.1 Mean Filter 3 5.3.2 Median Filter 4 5.3.3 Pseudomedian Filter 6 5.3.4

More information

Pulse Image Processing Using Centripetal Autowaves

Pulse Image Processing Using Centripetal Autowaves Pulse Image Processing Using Centripetal Autowaves Jason M. Kinser and Chau Nguyen The Institute for Biosciences, Bioinformatics, and Biotechnology George Mason University, MSN 4E3 Email: jkinser@gmu.edu

More information

Outline 7/2/201011/6/

Outline 7/2/201011/6/ Outline Pattern recognition in computer vision Background on the development of SIFT SIFT algorithm and some of its variations Computational considerations (SURF) Potential improvement Summary 01 2 Pattern

More information

Survey on Multi-Focus Image Fusion Algorithms

Survey on Multi-Focus Image Fusion Algorithms Proceedings of 2014 RAECS UIET Panjab University Chandigarh, 06 08 March, 2014 Survey on Multi-Focus Image Fusion Algorithms Rishu Garg University Inst of Engg & Tech. Panjab University Chandigarh, India

More information

CHAPTER 3 IMAGE ENHANCEMENT IN THE SPATIAL DOMAIN

CHAPTER 3 IMAGE ENHANCEMENT IN THE SPATIAL DOMAIN CHAPTER 3 IMAGE ENHANCEMENT IN THE SPATIAL DOMAIN CHAPTER 3: IMAGE ENHANCEMENT IN THE SPATIAL DOMAIN Principal objective: to process an image so that the result is more suitable than the original image

More information

Detection of Sub-resolution Dots in Microscopy Images

Detection of Sub-resolution Dots in Microscopy Images Detection of Sub-resolution Dots in Microscopy Images Karel Štěpka, 2012 Centre for Biomedical Image Analysis, FI MU supervisor: prof. RNDr. Michal Kozubek, Ph.D. Outline Introduction Existing approaches

More information

Digital Image Processing COSC 6380/4393

Digital Image Processing COSC 6380/4393 Digital Image Processing COSC 6380/4393 Lecture 21 Nov 16 th, 2017 Pranav Mantini Ack: Shah. M Image Processing Geometric Transformation Point Operations Filtering (spatial, Frequency) Input Restoration/

More information

EECS150 - Digital Design Lecture 14 FIFO 2 and SIFT. Recap and Outline

EECS150 - Digital Design Lecture 14 FIFO 2 and SIFT. Recap and Outline EECS150 - Digital Design Lecture 14 FIFO 2 and SIFT Oct. 15, 2013 Prof. Ronald Fearing Electrical Engineering and Computer Sciences University of California, Berkeley (slides courtesy of Prof. John Wawrzynek)

More information

EECS 556 Image Processing W 09. Image enhancement. Smoothing and noise removal Sharpening filters

EECS 556 Image Processing W 09. Image enhancement. Smoothing and noise removal Sharpening filters EECS 556 Image Processing W 09 Image enhancement Smoothing and noise removal Sharpening filters What is image processing? Image processing is the application of 2D signal processing methods to images Image

More information

Digital Image Processing

Digital Image Processing Digital Image Processing Lecture # 6 Image Enhancement in Spatial Domain- II ALI JAVED Lecturer SOFTWARE ENGINEERING DEPARTMENT U.E.T TAXILA Email:: ali.javed@uettaxila.edu.pk Office Room #:: 7 Local/

More information

NI Vision Platform. Radim ŠTEFAN. ni.com

NI Vision Platform. Radim ŠTEFAN.  ni.com NI Vision Platform Radim ŠTEFAN www./vision National Instruments Our Stability Revenue: $1.15B in 2012 Innovation: 18% re-invested to R&D Global Operations: Approximately 7,100 employees; operations in

More information

Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation

Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation Obviously, this is a very slow process and not suitable for dynamic scenes. To speed things up, we can use a laser that projects a vertical line of light onto the scene. This laser rotates around its vertical

More information

Filtering Images. Contents

Filtering Images. Contents Image Processing and Data Visualization with MATLAB Filtering Images Hansrudi Noser June 8-9, 010 UZH, Multimedia and Robotics Summer School Noise Smoothing Filters Sigmoid Filters Gradient Filters Contents

More information

CSE 252B: Computer Vision II

CSE 252B: Computer Vision II CSE 252B: Computer Vision II Lecturer: Serge Belongie Scribes: Jeremy Pollock and Neil Alldrin LECTURE 14 Robust Feature Matching 14.1. Introduction Last lecture we learned how to find interest points

More information

Hardware Neuronale Netzwerke - Lernen durch künstliche Evolution (?)

Hardware Neuronale Netzwerke - Lernen durch künstliche Evolution (?) SKIP - May 2004 Hardware Neuronale Netzwerke - Lernen durch künstliche Evolution (?) S. G. Hohmann, Electronic Vision(s), Kirchhoff Institut für Physik, Universität Heidelberg Hardware Neuronale Netzwerke

More information

Lecture 4: Spatial Domain Transformations

Lecture 4: Spatial Domain Transformations # Lecture 4: Spatial Domain Transformations Saad J Bedros sbedros@umn.edu Reminder 2 nd Quiz on the manipulator Part is this Fri, April 7 205, :5 AM to :0 PM Open Book, Open Notes, Focus on the material

More information

A Paper presentation on REAL TIME IMAGE PROCESSING APPLIED TO TRAFFIC QUEUE DETECTION ALGORITHM

A Paper presentation on REAL TIME IMAGE PROCESSING APPLIED TO TRAFFIC QUEUE DETECTION ALGORITHM A Paper presentation on REAL TIME IMAGE PROCESSING APPLIED TO TRAFFIC QUEUE DETECTION ALGORITHM ABSTRACT This paper primarily aims at the new technique of video image processing used to solve problems

More information

Super-Resolution on Moving Objects and Background

Super-Resolution on Moving Objects and Background Super-Resolution on Moving Objects and Background A. van Eekeren K. Schutte J. Dijk D.J.J. de Lange L.J. van Vliet TNO Defence, Security and Safety, P.O. Box 96864, 2509 JG, The Hague, The Netherlands

More information

Genetic Algorithm Based Template Optimization for a Vision System: Obstacle Detection

Genetic Algorithm Based Template Optimization for a Vision System: Obstacle Detection ISTET'09 Umair Ali Khan, Alireza Fasih, Kyandoghere Kyamakya, Jean Chamberlain Chedjou Transportation Informatics Group, Alpen Adria University, Klagenfurt, Austria. Genetic Algorithm Based Template Optimization

More information

3D-OBJECT DETECTION METHOD BASED ON THE STEREO IMAGE TRANSFORMATION TO THE COMMON OBSERVATION POINT

3D-OBJECT DETECTION METHOD BASED ON THE STEREO IMAGE TRANSFORMATION TO THE COMMON OBSERVATION POINT 3D-OBJECT DETECTION METHOD BASED ON THE STEREO IMAGE TRANSFORMATION TO THE COMMON OBSERVATION POINT V. M. Lisitsyn *, S. V. Tikhonova ** State Research Institute of Aviation Systems, Moscow, Russia * lvm@gosniias.msk.ru

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

Chapter 3: Intensity Transformations and Spatial Filtering

Chapter 3: Intensity Transformations and Spatial Filtering Chapter 3: Intensity Transformations and Spatial Filtering 3.1 Background 3.2 Some basic intensity transformation functions 3.3 Histogram processing 3.4 Fundamentals of spatial filtering 3.5 Smoothing

More information

Practice Exam Sample Solutions

Practice Exam Sample Solutions CS 675 Computer Vision Instructor: Marc Pomplun Practice Exam Sample Solutions Note that in the actual exam, no calculators, no books, and no notes allowed. Question 1: out of points Question 2: out of

More information

CS4442/9542b Artificial Intelligence II prof. Olga Veksler

CS4442/9542b Artificial Intelligence II prof. Olga Veksler CS4442/9542b Artificial Intelligence II prof. Olga Veksler Lecture 2 Computer Vision Introduction, Filtering Some slides from: D. Jacobs, D. Lowe, S. Seitz, A.Efros, X. Li, R. Fergus, J. Hayes, S. Lazebnik,

More information

A Real-time Algorithm for Atmospheric Turbulence Correction

A Real-time Algorithm for Atmospheric Turbulence Correction Logic Fruit Technologies White Paper 806, 8 th Floor, BPTP Park Centra, Sector 30, Gurgaon. Pin: 122001 T: +91-124-4117336 W: http://www.logic-fruit.com A Real-time Algorithm for Atmospheric Turbulence

More information

Simple and Robust Tracking of Hands and Objects for Video-based Multimedia Production

Simple and Robust Tracking of Hands and Objects for Video-based Multimedia Production Simple and Robust Tracking of Hands and Objects for Video-based Multimedia Production Masatsugu ITOH Motoyuki OZEKI Yuichi NAKAMURA Yuichi OHTA Institute of Engineering Mechanics and Systems University

More information

The SIFT (Scale Invariant Feature

The SIFT (Scale Invariant Feature The SIFT (Scale Invariant Feature Transform) Detector and Descriptor developed by David Lowe University of British Columbia Initial paper ICCV 1999 Newer journal paper IJCV 2004 Review: Matt Brown s Canonical

More information

CAP 5415 Computer Vision Fall 2012

CAP 5415 Computer Vision Fall 2012 CAP 5415 Computer Vision Fall 01 Dr. Mubarak Shah Univ. of Central Florida Office 47-F HEC Lecture-5 SIFT: David Lowe, UBC SIFT - Key Point Extraction Stands for scale invariant feature transform Patented

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

The Continuous Genetic Algorithm. Universidad de los Andes-CODENSA

The Continuous Genetic Algorithm. Universidad de los Andes-CODENSA The Continuous Genetic Algorithm Universidad de los Andes-CODENSA 1. Components of a Continuous Genetic Algorithm The flowchart in figure1 provides a big picture overview of a continuous GA.. Figure 1.

More information

Bio-inspired Binocular Disparity with Position-Shift Receptive Field

Bio-inspired Binocular Disparity with Position-Shift Receptive Field Bio-inspired Binocular Disparity with Position-Shift Receptive Field Fernanda da C. e C. Faria, Jorge Batista and Helder Araújo Institute of Systems and Robotics, Department of Electrical Engineering and

More information

Information Fusion Dr. B. K. Panigrahi

Information Fusion Dr. B. K. Panigrahi Information Fusion By Dr. B. K. Panigrahi Asst. Professor Department of Electrical Engineering IIT Delhi, New Delhi-110016 01/12/2007 1 Introduction Classification OUTLINE K-fold cross Validation Feature

More information

Other Linear Filters CS 211A

Other Linear Filters CS 211A Other Linear Filters CS 211A Slides from Cornelia Fermüller and Marc Pollefeys Edge detection Convert a 2D image into a set of curves Extracts salient features of the scene More compact than pixels Origin

More information

PROCESS > SPATIAL FILTERS

PROCESS > SPATIAL FILTERS 83 Spatial Filters There are 19 different spatial filters that can be applied to a data set. These are described in the table below. A filter can be applied to the entire volume or to selected objects

More information

Logical Templates for Feature Extraction in Fingerprint Images

Logical Templates for Feature Extraction in Fingerprint Images Logical Templates for Feature Extraction in Fingerprint Images Bir Bhanu, Michael Boshra and Xuejun Tan Center for Research in Intelligent Systems University of Califomia, Riverside, CA 9252 1, USA Email:

More information

Edge and local feature detection - 2. Importance of edge detection in computer vision

Edge and local feature detection - 2. Importance of edge detection in computer vision Edge and local feature detection Gradient based edge detection Edge detection by function fitting Second derivative edge detectors Edge linking and the construction of the chain graph Edge and local feature

More information

Random Search Report An objective look at random search performance for 4 problem sets

Random Search Report An objective look at random search performance for 4 problem sets Random Search Report An objective look at random search performance for 4 problem sets Dudon Wai Georgia Institute of Technology CS 7641: Machine Learning Atlanta, GA dwai3@gatech.edu Abstract: This report

More information

INFRARED AUTONOMOUS ACQUISITION AND TRACKING

INFRARED AUTONOMOUS ACQUISITION AND TRACKING INFRARED AUTONOMOUS ACQUISITION AND TRACKING Teresa L.P. Olson and Harry C. Lee Teresa.Lolson@lmco.com (407) 356-7109 Harrv.c.lee@lmco.com (407) 356-6997 Lockheed Martin Missiles and Fire Control - Orlando

More information

CS4442/9542b Artificial Intelligence II prof. Olga Veksler

CS4442/9542b Artificial Intelligence II prof. Olga Veksler CS4442/9542b Artificial Intelligence II prof. Olga Veksler Lecture 8 Computer Vision Introduction, Filtering Some slides from: D. Jacobs, D. Lowe, S. Seitz, A.Efros, X. Li, R. Fergus, J. Hayes, S. Lazebnik,

More information

Comparative Analysis in Medical Imaging

Comparative Analysis in Medical Imaging 1 International Journal of Computer Applications (975 8887) Comparative Analysis in Medical Imaging Ashish Verma DCS, Punjabi University 1, Patiala, India Bharti Sharma DCS, Punjabi University 1, Patiala,

More information

The Content-Based Image Retrieval using the Pulse Coupled Neural Network

The Content-Based Image Retrieval using the Pulse Coupled Neural Network WCCI 22 IEEE World Congress on Computational Intelligence June, -5, 22 - Brisbane, Australia IJCNN The Content-Based Image Retrieval using the Pulse Coupled Neural Network Masato Yonekawa and Hiroaki Kurokawa

More information

Local Features: Detection, Description & Matching

Local Features: Detection, Description & Matching Local Features: Detection, Description & Matching Lecture 08 Computer Vision Material Citations Dr George Stockman Professor Emeritus, Michigan State University Dr David Lowe Professor, University of British

More information

Design and Performance Analysis of and Gate using Synaptic Inputs for Neural Network Application

Design and Performance Analysis of and Gate using Synaptic Inputs for Neural Network Application IJIRST International Journal for Innovative Research in Science & Technology Volume 1 Issue 12 May 2015 ISSN (online): 2349-6010 Design and Performance Analysis of and Gate using Synaptic Inputs for Neural

More information

MRO CRISM TRR3 Hyperspectral Data Filtering

MRO CRISM TRR3 Hyperspectral Data Filtering MRO CRISM TRR3 Hyperspectral Data Filtering CRISM Data User's Workshop 03/18/12 F. Seelos, CRISM SOC CRISM PDS-Delivered VNIR TRR3 I/F 3-Panel Plot False Color RGB Composite Composite band distribution

More information

USING A CLUSTERING TECHNIQUE FOR DETECTION OF MOVING TARGETS IN CLUTTER-CANCELLED QUICKSAR IMAGES

USING A CLUSTERING TECHNIQUE FOR DETECTION OF MOVING TARGETS IN CLUTTER-CANCELLED QUICKSAR IMAGES USING A CLUSTERING TECHNIQUE FOR DETECTION OF MOVING TARGETS IN CLUTTER-CANCELLED QUICKSAR IMAGES Mr. D. P. McGarry, Dr. D. M. Zasada, Dr. P. K. Sanyal, Mr. R. P. Perry The MITRE Corporation, 26 Electronic

More information

What will we learn? Neighborhood processing. Convolution and correlation. Neighborhood processing. Chapter 10 Neighborhood Processing

What will we learn? Neighborhood processing. Convolution and correlation. Neighborhood processing. Chapter 10 Neighborhood Processing What will we learn? Lecture Slides ME 4060 Machine Vision and Vision-based Control Chapter 10 Neighborhood Processing By Dr. Debao Zhou 1 What is neighborhood processing and how does it differ from point

More information

Suppose you have a problem You don t know how to solve it What can you do? Can you use a computer to somehow find a solution for you?

Suppose you have a problem You don t know how to solve it What can you do? Can you use a computer to somehow find a solution for you? Gurjit Randhawa Suppose you have a problem You don t know how to solve it What can you do? Can you use a computer to somehow find a solution for you? This would be nice! Can it be done? A blind generate

More information

Part 3: Image Processing

Part 3: Image Processing Part 3: Image Processing Image Filtering and Segmentation Georgy Gimel farb COMPSCI 373 Computer Graphics and Image Processing 1 / 60 1 Image filtering 2 Median filtering 3 Mean filtering 4 Image segmentation

More information

SIMULATIVE ANALYSIS OF EDGE DETECTION OPERATORS AS APPLIED FOR ROAD IMAGES

SIMULATIVE ANALYSIS OF EDGE DETECTION OPERATORS AS APPLIED FOR ROAD IMAGES SIMULATIVE ANALYSIS OF EDGE DETECTION OPERATORS AS APPLIED FOR ROAD IMAGES Sukhpreet Kaur¹, Jyoti Saxena² and Sukhjinder Singh³ ¹Research scholar, ²Professsor and ³Assistant Professor ¹ ² ³ Department

More information

EXAM SOLUTIONS. Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006,

EXAM SOLUTIONS. Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006, School of Computer Science and Communication, KTH Danica Kragic EXAM SOLUTIONS Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006, 14.00 19.00 Grade table 0-25 U 26-35 3 36-45

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 WRI C225 Lecture 04 130131 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Histogram Equalization Image Filtering Linear

More information

Basic Algorithms for Digital Image Analysis: a course

Basic Algorithms for Digital Image Analysis: a course Institute of Informatics Eötvös Loránd University Budapest, Hungary Basic Algorithms for Digital Image Analysis: a course Dmitrij Csetverikov with help of Attila Lerch, Judit Verestóy, Zoltán Megyesi,

More information

An Efficient Multi-Focus Image Fusion Scheme Based On PCNN

An Efficient Multi-Focus Image Fusion Scheme Based On PCNN An Efficient Multi-Focus Fusion Scheme Based On PCNN Shruti D. Athawale 1, Sagar S. Badnerkar 2 1 ME Student, Department of Electronics & Telecommunication, GHRCEM, Amravati, India 2 Asst.Professor, Department

More information

DIGITAL SYSTEM. Technology Overview Nordco. All rights reserved. Rev C

DIGITAL SYSTEM. Technology Overview Nordco. All rights reserved. Rev C DIGITAL SYSTEM Technology Overview Rev C 01-05-2016 Insert Full Frame Product Picture Here 2015 KEY FEATURES DIGITAL PROCESSING SYSTEM FOR INDUSTRIAL & TONNE UE SYSTEM DIGITAL PROCESSING SYSTEM FOR MICRO

More information

OPERATIONAL SHIP DETECTION & RAPID URBAN MAPPING : EXPLORING DIVERSE METHODOLOGICAL APPROACHES IN OBJECT RECOGNTION AND SATELLITE IMAGE CLASSIFICATION

OPERATIONAL SHIP DETECTION & RAPID URBAN MAPPING : EXPLORING DIVERSE METHODOLOGICAL APPROACHES IN OBJECT RECOGNTION AND SATELLITE IMAGE CLASSIFICATION Journées ORFEO Méthodo 10-11 Janvier 2008 OPERATIONAL SHIP DETECTION & RAPID URBAN MAPPING : EXPLORING DIVERSE METHODOLOGICAL APPROACHES IN OBJECT RECOGNTION AND SATELLITE IMAGE CLASSIFICATION Michel Petit,

More information

Classification of image operations. Image enhancement (GW-Ch. 3) Point operations. Neighbourhood operation

Classification of image operations. Image enhancement (GW-Ch. 3) Point operations. Neighbourhood operation Image enhancement (GW-Ch. 3) Classification of image operations Process of improving image quality so that the result is more suitable for a specific application. contrast stretching histogram processing

More information

Traffic Sign Localization and Classification Methods: An Overview

Traffic Sign Localization and Classification Methods: An Overview Traffic Sign Localization and Classification Methods: An Overview Ivan Filković University of Zagreb Faculty of Electrical Engineering and Computing Department of Electronics, Microelectronics, Computer

More information

SURVEY PAPER ON REAL TIME MOTION DETECTION TECHNIQUES

SURVEY PAPER ON REAL TIME MOTION DETECTION TECHNIQUES SURVEY PAPER ON REAL TIME MOTION DETECTION TECHNIQUES 1 R. AROKIA PRIYA, 2 POONAM GUJRATHI Assistant Professor, Department of Electronics and Telecommunication, D.Y.Patil College of Engineering, Akrudi,

More information

Using temporal seeding to constrain the disparity search range in stereo matching

Using temporal seeding to constrain the disparity search range in stereo matching Using temporal seeding to constrain the disparity search range in stereo matching Thulani Ndhlovu Mobile Intelligent Autonomous Systems CSIR South Africa Email: tndhlovu@csir.co.za Fred Nicolls Department

More information

C E N T E R A T H O U S T O N S C H O O L of H E A L T H I N F O R M A T I O N S C I E N C E S. Image Operations I

C E N T E R A T H O U S T O N S C H O O L of H E A L T H I N F O R M A T I O N S C I E N C E S. Image Operations I T H E U N I V E R S I T Y of T E X A S H E A L T H S C I E N C E C E N T E R A T H O U S T O N S C H O O L of H E A L T H I N F O R M A T I O N S C I E N C E S Image Operations I For students of HI 5323

More information

Multiple target detection in video using quadratic multi-frame correlation filtering

Multiple target detection in video using quadratic multi-frame correlation filtering Multiple target detection in video using quadratic multi-frame correlation filtering Ryan Kerekes Oak Ridge National Laboratory B. V. K. Vijaya Kumar Carnegie Mellon University March 17, 2008 1 Outline

More information

Image Compression: An Artificial Neural Network Approach

Image Compression: An Artificial Neural Network Approach Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and

More information

CS 664 Segmentation. Daniel Huttenlocher

CS 664 Segmentation. Daniel Huttenlocher CS 664 Segmentation Daniel Huttenlocher Grouping Perceptual Organization Structural relationships between tokens Parallelism, symmetry, alignment Similarity of token properties Often strong psychophysical

More information

The Evolution of Thermal Imaging Cameras

The Evolution of Thermal Imaging Cameras 170 Years of Continued Innovation The Evolution of Thermal Imaging Cameras The World s Finest Manufacturers of Temperature, Pressure & Humidity, Test and Calibration Instruments t May, 2007 What is a Thermal

More information

Adaptive Scene-Based Non-Uniformity Correction Method for Infrared-Focal Plane Arrays

Adaptive Scene-Based Non-Uniformity Correction Method for Infrared-Focal Plane Arrays Adaptive Scene-Based Non-Uniformity Correction Method for Infrared-Focal Plane Arrays Sergio N. Torres, Esteban M. Vera, Rodrigo A. Reeves, Sergio K. Sobarzo Department of Electrical Engineering University

More information

Image Processing Fundamentals. Nicolas Vazquez Principal Software Engineer National Instruments

Image Processing Fundamentals. Nicolas Vazquez Principal Software Engineer National Instruments Image Processing Fundamentals Nicolas Vazquez Principal Software Engineer National Instruments Agenda Objectives and Motivations Enhancing Images Checking for Presence Locating Parts Measuring Features

More information

Active contour: a parallel genetic algorithm approach

Active contour: a parallel genetic algorithm approach id-1 Active contour: a parallel genetic algorithm approach Florence Kussener 1 1 MathWorks, 2 rue de Paris 92196 Meudon Cedex, France Florence.Kussener@mathworks.fr Abstract This paper presents an algorithm

More information

International Journal of Scientific & Engineering Research, Volume 8, Issue 1, January ISSN

International Journal of Scientific & Engineering Research, Volume 8, Issue 1, January ISSN International Journal of Scientific & Engineering Research, Volume 8, Issue 1, January-2017 550 Using Neuro Fuzzy and Genetic Algorithm for Image Denoising Shaymaa Rashid Saleh Raidah S. Khaudeyer Abstract

More information

Hom o om o or o phi p c Processing

Hom o om o or o phi p c Processing Homomorphic o o Processing Motivation: Image with a large dynamic range, e.g. natural scene on a bright sunny day, recorded on a medium with a small dynamic range, e.g. a film image contrast significantly

More information

Time-of-flight basics

Time-of-flight basics Contents 1. Introduction... 2 2. Glossary of Terms... 3 3. Recovering phase from cross-correlation... 4 4. Time-of-flight operating principle: the lock-in amplifier... 6 5. The time-of-flight sensor pixel...

More information

doi: /

doi: / Yiting Xie ; Anthony P. Reeves; Single 3D cell segmentation from optical CT microscope images. Proc. SPIE 934, Medical Imaging 214: Image Processing, 9343B (March 21, 214); doi:1.1117/12.243852. (214)

More information

INTENSITY TRANSFORMATION AND SPATIAL FILTERING

INTENSITY TRANSFORMATION AND SPATIAL FILTERING 1 INTENSITY TRANSFORMATION AND SPATIAL FILTERING Lecture 3 Image Domains 2 Spatial domain Refers to the image plane itself Image processing methods are based and directly applied to image pixels Transform

More information

Light Field Occlusion Removal

Light Field Occlusion Removal Light Field Occlusion Removal Shannon Kao Stanford University kaos@stanford.edu Figure 1: Occlusion removal pipeline. The input image (left) is part of a focal stack representing a light field. Each image

More information

Image restoration. Restoration: Enhancement:

Image restoration. Restoration: Enhancement: Image restoration Most images obtained by optical, electronic, or electro-optic means is likely to be degraded. The degradation can be due to camera misfocus, relative motion between camera and object,

More information

Grid-Based Genetic Algorithm Approach to Colour Image Segmentation

Grid-Based Genetic Algorithm Approach to Colour Image Segmentation Grid-Based Genetic Algorithm Approach to Colour Image Segmentation Marco Gallotta Keri Woods Supervised by Audrey Mbogho Image Segmentation Identifying and extracting distinct, homogeneous regions from

More information

Stereo Vision. MAN-522 Computer Vision

Stereo Vision. MAN-522 Computer Vision Stereo Vision MAN-522 Computer Vision What is the goal of stereo vision? The recovery of the 3D structure of a scene using two or more images of the 3D scene, each acquired from a different viewpoint in

More information

GEOG 4110/5100 Advanced Remote Sensing Lecture 2

GEOG 4110/5100 Advanced Remote Sensing Lecture 2 GEOG 4110/5100 Advanced Remote Sensing Lecture 2 Data Quality Radiometric Distortion Radiometric Error Correction Relevant reading: Richards, sections 2.1 2.8; 2.10.1 2.10.3 Data Quality/Resolution Spatial

More information

Evolutionary On-line Synthesis of Hardware Accelerators for Software Modules in Reconfigurable Embedded Systems

Evolutionary On-line Synthesis of Hardware Accelerators for Software Modules in Reconfigurable Embedded Systems Evolutionary On-line Synthesis of Hardware Accelerators for Software Modules in Reconfigurable Embedded Systems Roland Dobai Faculty of Information Technology Brno University of Technology Brno, Czech

More information

Genetic Algorithms Variations and Implementation Issues

Genetic Algorithms Variations and Implementation Issues Genetic Algorithms Variations and Implementation Issues CS 431 Advanced Topics in AI Classic Genetic Algorithms GAs as proposed by Holland had the following properties: Randomly generated population Binary

More information

Minimizing Noise and Bias in 3D DIC. Correlated Solutions, Inc.

Minimizing Noise and Bias in 3D DIC. Correlated Solutions, Inc. Minimizing Noise and Bias in 3D DIC Correlated Solutions, Inc. Overview Overview of Noise and Bias Digital Image Correlation Background/Tracking Function Minimizing Noise Focus Contrast/Lighting Glare

More information

A Hybrid Approach to Non-Uniformity Correction of Large Format Emitter Arrays

A Hybrid Approach to Non-Uniformity Correction of Large Format Emitter Arrays A Hybrid Approach to Non-Uniformity Correction of Large Format Emitter Arrays Joe LaVeigne a, Marcus Prewarski a, Greg Franks a, Steve McHugh a a Santa Barbara Infrared, 30 S Calle Cesar Chavez, Suite

More information

Experiments with Edge Detection using One-dimensional Surface Fitting

Experiments with Edge Detection using One-dimensional Surface Fitting Experiments with Edge Detection using One-dimensional Surface Fitting Gabor Terei, Jorge Luis Nunes e Silva Brito The Ohio State University, Department of Geodetic Science and Surveying 1958 Neil Avenue,

More information

Human Detection. A state-of-the-art survey. Mohammad Dorgham. University of Hamburg

Human Detection. A state-of-the-art survey. Mohammad Dorgham. University of Hamburg Human Detection A state-of-the-art survey Mohammad Dorgham University of Hamburg Presentation outline Motivation Applications Overview of approaches (categorized) Approaches details References Motivation

More information

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS Cognitive Robotics Original: David G. Lowe, 004 Summary: Coen van Leeuwen, s1460919 Abstract: This article presents a method to extract

More information

CS201: Computer Vision Introduction to Tracking

CS201: Computer Vision Introduction to Tracking CS201: Computer Vision Introduction to Tracking John Magee 18 November 2014 Slides courtesy of: Diane H. Theriault Question of the Day How can we represent and use motion in images? 1 What is Motion? Change

More information

Advances in Neural Networks ISNN 2007

Advances in Neural Networks ISNN 2007 Derong Liu Shumin Fei Zengguang Hou Huaguang Zhang Changyin Sun (Eds.) Advances in Neural Networks ISNN 2007 4th International Symposium on Neural Networks, ISNN 2007 Nanjing, China, June 3-7, 2007 Proceedings,

More information

Multimedia Systems Video II (Video Coding) Mahdi Amiri April 2012 Sharif University of Technology

Multimedia Systems Video II (Video Coding) Mahdi Amiri April 2012 Sharif University of Technology Course Presentation Multimedia Systems Video II (Video Coding) Mahdi Amiri April 2012 Sharif University of Technology Video Coding Correlation in Video Sequence Spatial correlation Similar pixels seem

More information

Medical images, segmentation and analysis

Medical images, segmentation and analysis Medical images, segmentation and analysis ImageLab group http://imagelab.ing.unimo.it Università degli Studi di Modena e Reggio Emilia Medical Images Macroscopic Dermoscopic ELM enhance the features of

More information

DESIGN OF A NOVEL IMAGE FUSION ALGORITHM FOR IMPULSE NOISE REMOVAL IN REMOTE SENSING IMAGES BY USING THE QUALITY ASSESSMENT

DESIGN OF A NOVEL IMAGE FUSION ALGORITHM FOR IMPULSE NOISE REMOVAL IN REMOTE SENSING IMAGES BY USING THE QUALITY ASSESSMENT DESIGN OF A NOVEL IMAGE FUSION ALGORITHM FOR IMPULSE NOISE REMOVAL IN REMOTE SENSING IMAGES BY USING THE QUALITY ASSESSMENT P.PAVANI, M.V.H.BHASKARA MURTHY Department of Electronics and Communication Engineering,Aditya

More information

DESIGNER S NOTEBOOK Proximity Calibration and Test by Kerry Glover August 2011

DESIGNER S NOTEBOOK Proximity Calibration and Test by Kerry Glover August 2011 INTELLIGENT OPTO SENSOR Number 37 DESIGNER S NOTEBOOK Proximity Calibration and Test by Kerry Glover August 2011 Overview TAOS proximity sensors are very flexible and are used in many applications from

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

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

DT-Binarize: A Hybrid Binarization Method using Decision Tree for Protein Crystallization Images

DT-Binarize: A Hybrid Binarization Method using Decision Tree for Protein Crystallization Images DT-Binarize: A Hybrid Binarization Method using Decision Tree for Protein Crystallization Images İmren Dinç 1, Semih Dinç 1, Madhav Sigdel 1, Madhu S. Sigdel 1, Marc L. Pusey 2, Ramazan S. Aygün 1 1 DataMedia

More information

C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT Chennai

C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT Chennai Traffic Sign Detection Via Graph-Based Ranking and Segmentation Algorithm C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT

More information

Filters. Advanced and Special Topics: Filters. Filters

Filters. Advanced and Special Topics: Filters. Filters Filters Advanced and Special Topics: Filters Dr. Edmund Lam Department of Electrical and Electronic Engineering The University of Hong Kong ELEC4245: Digital Image Processing (Second Semester, 2016 17)

More information

PROBLEM FORMULATION AND RESEARCH METHODOLOGY

PROBLEM FORMULATION AND RESEARCH METHODOLOGY PROBLEM FORMULATION AND RESEARCH METHODOLOGY ON THE SOFT COMPUTING BASED APPROACHES FOR OBJECT DETECTION AND TRACKING IN VIDEOS CHAPTER 3 PROBLEM FORMULATION AND RESEARCH METHODOLOGY The foregoing chapter

More information

MEDICAL IMAGE ANALYSIS

MEDICAL IMAGE ANALYSIS SECOND EDITION MEDICAL IMAGE ANALYSIS ATAM P. DHAWAN g, A B IEEE Engineering in Medicine and Biology Society, Sponsor IEEE Press Series in Biomedical Engineering Metin Akay, Series Editor +IEEE IEEE PRESS

More information

Massively Parallel Computing on Silicon: SIMD Implementations. V.M.. Brea Univ. of Santiago de Compostela Spain

Massively Parallel Computing on Silicon: SIMD Implementations. V.M.. Brea Univ. of Santiago de Compostela Spain Massively Parallel Computing on Silicon: SIMD Implementations V.M.. Brea Univ. of Santiago de Compostela Spain GOAL Give an overview on the state-of of-the- art of Digital on-chip CMOS SIMD Solutions,

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