Class 9 Action Recognition
|
|
- Alexis McDowell
- 5 years ago
- Views:
Transcription
1 Class 9 Action Recognition Liangliang Cao, April 4, 2013 EECS 6890 Topics in Information Processing Spring 2013, Columbia University Visual Recognition And Search 1
2 A Historical Overview Few internet videos Few surveillance cameras Visual Recognition And Search 2
3 A Historical Overview TRECVID videos - 11 hours - mainly TV news Few internet videos Few surveillance cameras Visual Recognition And Search 3
4 A Historical Overview KTH Dataset, ICPR 04 (1100+ cite) TRECVID videos - 11 hours - mainly TV news Few internet videos Few surveillance cameras Visual Recognition And Search 4
5 A Historical Overview KTH Dataset, ICPR 04 (1100+ cite) TRECVID videos - 11 hours - mainly TV news YouTube launched! Few internet videos Few surveillance cameras Visual Recognition And Search 5
6 A Historical Overview KTH Dataset, ICPR 04 (1100+ cite) TRECVID videos - 11 hours - mainly TV news YouTube launched! bought by Google $1.65 Billion Few internet videos Few surveillance cameras Visual Recognition And Search 6
7 A Historical Overview Hollywood2 dataset STIP new version CVPR 08 (700+ cite) KTH Dataset, ICPR 04 (1100+ cite) Topic model for actions IJCV 08 (500+ cite) TRECVID videos - 11 hours - mainly TV news YouTube launched! bought by Google $1.65 Billion Few internet videos Few surveillance cameras Visual Recognition And Search 7
8 A Historical Overview Hollywood2 dataset STIP new version CVPR 08 (700+ cite) More datasets UCF50, 2008 KTH Dataset, ICPR 04 (1100+ cite) Topic model for actions IJCV 08 (500+ cite) TRECVID videos - 11 hours - mainly TV news YouTube launched! bought by Google $1.65 Billion YouTube ad revenue raise Few internet videos Few surveillance cameras Visual Recognition And Search 8
9 A Historical Overview Hollywood2 dataset STIP new version CVPR 08 (700+ cite) More datasets UCF50, 2008 MSR 2009 KTH Dataset, ICPR 04 (1100+ cite) Topic model for actions IJCV 08 (500+ cite) TRECVID videos - 11 hours - mainly TV news YouTube launched! bought by Google $1.65 Billion YouTube ad revenue raise Few internet videos Few surveillance cameras Visual Recognition And Search 9
10 A Historical Overview KTH Dataset, ICPR 04 (1100+ cite) Hollywood2 dataset STIP new version CVPR 08 (700+ cite) Topic model for actions IJCV 08 (500+ cite) More datasets UCF50, 2008 MSR 2009 HMDB TRECVID videos - 11 hours - mainly TV news YouTube launched! bought by Google $1.65 Billion YouTube ad revenue raise Few internet videos Few surveillance cameras Visual Recognition And Search 10
11 A Historical Overview KTH Dataset, ICPR 04 (1100+ cite) Hollywood2 dataset STIP new version CVPR 08 (700+ cite) Topic model for actions IJCV 08 (500+ cite) More datasets UCF50, 2008 MSR 2009 HMDB TRECVID videos - 11 hours - mainly TV news YouTube launched! bought by Google $1.65 Billion Few internet videos Few surveillance cameras YouTube ad revenue raise Example: 48 video-hours uploaded per min. 4M security cameras at UK. VIRAT 2011 (29 hours) TRECVID SED (100 hours) TRECVID MED (100K clips) Visual Recognition And Search 11
12 A Historical Overview KTH Dataset, ICPR 04 (1100+ cite) Hollywood2 dataset STIP new version CVPR 08 (700+ cite) Topic model for actions IJCV 08 (500+ cite) More datasets UCF50, 2008 MSR 2009 HMDB TRECVID videos - 11 hours - mainly TV news YouTube launched! bought by Google $1.65 Billion Few internet videos Few surveillance cameras YouTube ad revenue raise Example: 48 video-hours uploaded per min. 4M security cameras at UK. VIRAT 2011 (29 hours) TRECVID SED (100 hours) TRECVID MED (100K clips) Flooding internet videos. Surveillance cam everywhere. Visual Recognition And Search 12
13 What Am I Going To Talk Patch-feature based video recognition KTH Dataset, ICPR 04 (1100+ cite) Hollywood2 dataset STIP new version CVPR 08 (700+ cite) Topic model for actions IJCV 08 (500+ cite) More datasets UCF50, 2008 MSR 2009 HMDB 2011 Big gap TRECVID videos - 11 hours - mainly TV news YouTube launched! bought by Google $1.65 Billion Few internet videos Few surveillance cameras Non-patch based surveillance tech YouTube ad revenue raise Example: 48 video-hours uploaded per min. 4M security cameras at UK. VIRAT 2011 (29 hours) TRECVID SED (100 hours) TRECVID MED (100K clips) Flooding internet videos. Surveillance cam everywhere. Visual Recognition And Search 13
14 Classical Surveillance Techniques Many Techniques Background subtraction Object detection Tracking People counting Trajectory analysis Visual Recognition And Search 14
15 Classical Surveillance Techniques Background Mixture Model Chris Stauer& Eric L. Grimson Adaptive Background Mixture Models for Real-Time Tracking CVPR citations Visual Recognition And Search 15
16 GMM For Background Subtraction Idea Case = + Assumption: Background is fixed There is not much noise Example courtesy to Michael Knowles Visual Recognition And Search 16
17 GMM For Background Subtraction Background Image Background Subtraction: Construct a background image B as average of few images For each actual frame I, classify individual pixels as foreground if B-I > T (threshold) Real Case Current Image Example courtesy to Latecki et al Visual Recognition And Search 17
18 GMM For Background Subtraction Why Difficult Illumination Changes Gradual Sudden Repetitive background changes Long term scene changes Low resolution Figure from Stauffer and Grimson 98 Subject stayed and then left Scatter plots of red and green values of a single pixel overtime Visual Recognition And Search 18
19 GMM For Background Subtraction Gaussian Mixture Model Mixture model to capture multiple components in each location Visual Recognition And Search 19
20 GMM For Background Subtraction Adaptive GMM Recall that GMM adaptation is used in coding and pooling (lecture 3) Now we use adaptiation to capture the lighting changes is used to limit the influence of old data Visual Recognition And Search 20
21 GMM For Background Subtraction Background and Foreground The Gaussians are ordered via (high support & less variance) Then simply the first distributions are chosen as the background model. Visual Recognition And Search 21
22 GMM For Background Subtraction Background and Foreground -- foreground -- background Visual Recognition And Search 22
23 GMM For Background Subtraction Background Updating Pixels that do not match with the background Gaussians are classified as foreground. If the new pixel do not match to any of the K existing Gaussians, the least probably distribution is replaced with a new one. New distribution has a high variance and a low prior weight. Visual Recognition And Search 23
24 GMM For Background Subtraction Pixel-wise threshold Judging New Pixels You may use eigenanalysis or neighboring blocks to strengthen the analysis (see Seki et al s work) Visual Recognition And Search 24
25 Local Features for Images Semantics, attributes Detection BOW model Local detector/descriptor Local Features for Video Analysis Visual Recognition And Search 25
26 Local Features Based Video Analysis Space-Time Interest Point Following the local detector + descriptor paradigm Similar to (or even worse than) image domain, the detectors are of good mathematic motivation but unsatisfying performance. Dense sampling is still a good option Laptev swidely used descriptors: HOG (histof oriented gradients) and HOF (histof optical flow) Visual Recognition And Search 26
27 Local Features Based Video Analysis Space-Time Interest Point Following the local detector + descriptor paradigm Similar to (or even worse than) image domain, the detectors are of good mathematic motivation but unsatisfying performance. Dense sampling is still a good option Laptev swidely used descriptors: HOG(histof oriented gradients) and HOF(histof optical flow) Ivan Laptev et al, CVPR 08 Visual Recognition And Search 27
28 Local Features Based Video Analysis Hierarchically Filtered Motion Motion history is informative but often very noisy Using Hierarchical filter + HOG descriptor Implementation faster than STIP (60+ frame/ second) Tian et al, Hierarchical Filtered Motion for Action in Crowded Videos, TSMC 2011 Visual Recognition And Search 28
29 Local Features Based Video Analysis Dense Trajectory Do not use feature detector but dense sampling. Tracking densely-sampled points for Lframes by median filtering in a dense optical flow field. Wang et al, CVPR 2011, IJCV 2012 Visual Recognition And Search 29
30 Local Features Based Video Analysis Bag of Words Model Niebles, Wang, Fei-Fei, IJCV 2008 (559 citations) Visual Recognition And Search 30
31 Local Features Based Video Analysis Action Detection Object detection in image (Branch and bound in 2D) Action detection in videos Branch and bound in 3D (xyt) Lampert, Blaschko, and Hofmann, Beyond sliding windows: Object localization by efficient subwindow search, CVPR 08 Yuan, Liu and Wu, Discriminative Subvolume Search for Efficient Action Detection, CVPR 09 Visual Recognition And Search 31
32 Semantics Based Video Analysis From Object Bank To Action Bank Li et al, Object Bank: A High-Level Image Representation for Scene Classification and Semantic Feature Sparsification, NIPS 2010 Visual Recognition And Search 32
33 Semantics Based Video Analysis From Object Bank To Action Bank Sadanand and Corso, Action Bank: A High-Level Representation of Activity in Video, CVPR 2010 Visual Recognition And Search 33
34 Semantics Based Video Analysis Action Attributes Liu, Kuipers, and Savarese, Recognizing Human Actioins by Attributes, CVPR 2011 Visual Recognition And Search 34
35 Local Features Based Video Analysis Pros Easily borrow techniques from image analysis No need for tracking or detecting of human body (which sometimes can be frustrating) Cons Pros and Cons of Local Video Feature Most of them are slow (for real time processing) Expensive (the number of local features can be as large as several millions) Not good enough for low-resolution, crowded scenes Visual Recognition And Search 35
36 state-of-the-art action recognition Gap large scale action/event recognition Visual Recognition And Search 36
37 VIRAT Dataset Real-world surveillance: - Low resolution of subjects - Both spatial and temporal detection - Multiple objects, different movement, occlusions - Majority of the videos are of nonevent, only a small amount of event sequences Figures are courtesy to Oh and Perera Oh et al, A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video, CVPR 11 Visual Recognition And Search 37
38 TRECVID SED Challenges of SED: - Majority of the videos are of non-event, only a small amount of event sequences - Heavy occlusion, significantly different viewing directions Results from CMU-IBM team (best performer at TRECVID SED 12) Note: you will get a score of 1.0 with an emptysubmission. Visual Recognition And Search 38
39 Why Event/Action Recognition Are Difficult Features are not good enough How to design or learn efficient, accurate features? How to make feature reliable accross different views/scenes? Training labels are not enough How much improvement can we expect from more data? How to learn from heavily imbalanced data? Visual Recognition And Search 39
Adaptive Action Detection
Adaptive Action Detection Illinois Vision Workshop Dec. 1, 2009 Liangliang Cao Dept. ECE, UIUC Zicheng Liu Microsoft Research Thomas Huang Dept. ECE, UIUC Motivation Action recognition is important in
More informationAction recognition in videos
Action recognition in videos Cordelia Schmid INRIA Grenoble Joint work with V. Ferrari, A. Gaidon, Z. Harchaoui, A. Klaeser, A. Prest, H. Wang Action recognition - goal Short actions, i.e. drinking, sit
More informationAdaptive 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 informationLecture 18: Human Motion Recognition
Lecture 18: Human Motion Recognition Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Introduction Motion classification using template matching Motion classification i using spatio
More informationEVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION. Ing. Lorenzo Seidenari
EVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION Ing. Lorenzo Seidenari e-mail: seidenari@dsi.unifi.it What is an Event? Dictionary.com definition: something that occurs in a certain place during a particular
More informationPerson Action Recognition/Detection
Person Action Recognition/Detection Fabrício Ceschin Visão Computacional Prof. David Menotti Departamento de Informática - Universidade Federal do Paraná 1 In object recognition: is there a chair in the
More informationRecognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213)
Recognition of Animal Skin Texture Attributes in the Wild Amey Dharwadker (aap2174) Kai Zhang (kz2213) Motivation Patterns and textures are have an important role in object description and understanding
More informationLeveraging Textural Features for Recognizing Actions in Low Quality Videos
Leveraging Textural Features for Recognizing Actions in Low Quality Videos Saimunur Rahman, John See, Chiung Ching Ho Centre of Visual Computing, Faculty of Computing and Informatics Multimedia University,
More informationEE795: 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 informationDeep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon
Deep Learning For Video Classification Presented by Natalie Carlebach & Gil Sharon Overview Of Presentation Motivation Challenges of video classification Common datasets 4 different methods presented in
More informationEvaluation 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 informationLarge-scale Video Classification with Convolutional Neural Networks
Large-scale Video Classification with Convolutional Neural Networks Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, Li Fei-Fei Note: Slide content mostly from : Bay Area
More informationLearning Realistic Human Actions from Movies
Learning Realistic Human Actions from Movies Ivan Laptev*, Marcin Marszałek**, Cordelia Schmid**, Benjamin Rozenfeld*** INRIA Rennes, France ** INRIA Grenoble, France *** Bar-Ilan University, Israel Presented
More informationExtracting Spatio-temporal Local Features Considering Consecutiveness of Motions
Extracting Spatio-temporal Local Features Considering Consecutiveness of Motions Akitsugu Noguchi and Keiji Yanai Department of Computer Science, The University of Electro-Communications, 1-5-1 Chofugaoka,
More informationLearning Visual Semantics: Models, Massive Computation, and Innovative Applications
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Part II: Visual Features and Representations Liangliang Cao, IBM Watson Research Center Evolvement of Visual Features
More informationMotion Interchange Patterns for Action Recognition in Unconstrained Videos
Motion Interchange Patterns for Action Recognition in Unconstrained Videos Orit Kliper-Gross, Yaron Gurovich, Tal Hassner, Lior Wolf Weizmann Institute of Science The Open University of Israel Tel Aviv
More informationPairwise 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 informationCS231N Section. Video Understanding 6/1/2018
CS231N Section Video Understanding 6/1/2018 Outline Background / Motivation / History Video Datasets Models Pre-deep learning CNN + RNN 3D convolution Two-stream What we ve seen in class so far... Image
More informationAction Recognition & Categories via Spatial-Temporal Features
Action Recognition & Categories via Spatial-Temporal Features 华俊豪, 11331007 huajh7@gmail.com 2014/4/9 Talk at Image & Video Analysis taught by Huimin Yu. Outline Introduction Frameworks Feature extraction
More informationAction Recognition with HOG-OF Features
Action Recognition with HOG-OF Features Florian Baumann Institut für Informationsverarbeitung, Leibniz Universität Hannover, {last name}@tnt.uni-hannover.de Abstract. In this paper a simple and efficient
More informationTemporal Poselets for Collective Activity Detection and Recognition
Temporal Poselets for Collective Activity Detection and Recognition Moin Nabi Alessio Del Bue Vittorio Murino Pattern Analysis and Computer Vision (PAVIS) Istituto Italiano di Tecnologia (IIT) Via Morego
More informationBackground 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 informationLeveraging Textural Features for Recognizing Actions in Low Quality Videos
Leveraging Textural Features for Recognizing Actions in Low Quality Videos Saimunur Rahman 1, John See 2, and Chiung Ching Ho 3 Centre of Visual Computing, Faculty of Computing and Informatics Multimedia
More informationIMPROVING SPATIO-TEMPORAL FEATURE EXTRACTION TECHNIQUES AND THEIR APPLICATIONS IN ACTION CLASSIFICATION. Maral Mesmakhosroshahi, Joohee Kim
IMPROVING SPATIO-TEMPORAL FEATURE EXTRACTION TECHNIQUES AND THEIR APPLICATIONS IN ACTION CLASSIFICATION Maral Mesmakhosroshahi, Joohee Kim Department of Electrical and Computer Engineering Illinois Institute
More informationClassification of objects from Video Data (Group 30)
Classification of objects from Video Data (Group 30) Sheallika Singh 12665 Vibhuti Mahajan 12792 Aahitagni Mukherjee 12001 M Arvind 12385 1 Motivation Video surveillance has been employed for a long time
More informationAction Recognition in Video by Sparse Representation on Covariance Manifolds of Silhouette Tunnels
Action Recognition in Video by Sparse Representation on Covariance Manifolds of Silhouette Tunnels Kai Guo, Prakash Ishwar, and Janusz Konrad Department of Electrical & Computer Engineering Motivation
More informationTemplates and Background Subtraction. Prof. D. Stricker Doz. G. Bleser
Templates and Background Subtraction Prof. D. Stricker Doz. G. Bleser 1 Surveillance Video: Example of multiple people tracking http://www.youtube.com/watch?v=inqv34bchem&feature=player_embedded As for
More informationPeople Detection and Video Understanding
1 People Detection and Video Understanding Francois BREMOND INRIA Sophia Antipolis STARS team Institut National Recherche Informatique et Automatisme Francois.Bremond@inria.fr http://www-sop.inria.fr/members/francois.bremond/
More informationBus Detection and recognition for visually impaired people
Bus Detection and recognition for visually impaired people Hangrong Pan, Chucai Yi, and Yingli Tian The City College of New York The Graduate Center The City University of New York MAP4VIP Outline Motivation
More informationCS 231A Computer Vision (Fall 2011) Problem Set 4
CS 231A Computer Vision (Fall 2011) Problem Set 4 Due: Nov. 30 th, 2011 (9:30am) 1 Part-based models for Object Recognition (50 points) One approach to object recognition is to use a deformable part-based
More informationMoving Object Detection for Video Surveillance
International OPEN ACCESS Journal Of Modern Engineering Research (IJMER) Moving Object Detection for Video Surveillance Abhilash K.Sonara 1, Pinky J. Brahmbhatt 2 1 Student (ME-CSE), Electronics and Communication,
More informationSCENE TEXT RECOGNITION IN MULTIPLE FRAMES BASED ON TEXT TRACKING
SCENE TEXT RECOGNITION IN MULTIPLE FRAMES BASED ON TEXT TRACKING Xuejian Rong 1, Chucai Yi 2, Xiaodong Yang 1 and Yingli Tian 1,2 1 The City College, 2 The Graduate Center, City University of New York
More informationObject Classification for Video Surveillance
Object Classification for Video Surveillance Rogerio Feris IBM TJ Watson Research Center rsferis@us.ibm.com http://rogerioferis.com 1 Outline Part I: Object Classification in Far-field Video Part II: Large
More informationSampling Strategies for Real-time Action Recognition
2013 IEEE Conference on Computer Vision and Pattern Recognition Sampling Strategies for Real-time Action Recognition Feng Shi, Emil Petriu and Robert Laganière School of Electrical Engineering and Computer
More informationMultiple Kernel Learning for Emotion Recognition in the Wild
Multiple Kernel Learning for Emotion Recognition in the Wild Karan Sikka, Karmen Dykstra, Suchitra Sathyanarayana, Gwen Littlewort and Marian S. Bartlett Machine Perception Laboratory UCSD EmotiW Challenge,
More informationClass 5: Attributes and Semantic Features
Class 5: Attributes and Semantic Features Rogerio Feris, Feb 21, 2013 EECS 6890 Topics in Information Processing Spring 2013, Columbia University http://rogerioferis.com/visualrecognitionandsearch Project
More informationCategory-level localization
Category-level localization Cordelia Schmid Recognition Classification Object present/absent in an image Often presence of a significant amount of background clutter Localization / Detection Localize object
More informationHuman-Robot Interaction
Human-Robot Interaction Elective in Artificial Intelligence Lecture 6 Visual Perception Luca Iocchi DIAG, Sapienza University of Rome, Italy With contributions from D. D. Bloisi and A. Youssef Visual Perception
More informationHuman 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 informationBACKGROUND MODELS FOR TRACKING OBJECTS UNDER WATER
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IMPACT FACTOR: 5.258 IJCSMC,
More informationBeyond Sliding Windows: Object Localization by Efficient Subwindow Search
Beyond Sliding Windows: Object Localization by Efficient Subwindow Search Christoph H. Lampert, Matthew B. Blaschko, & Thomas Hofmann Max Planck Institute for Biological Cybernetics Tübingen, Germany Google,
More informationPart-Based Models for Object Class Recognition Part 3
High Level Computer Vision! Part-Based Models for Object Class Recognition Part 3 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de! http://www.d2.mpi-inf.mpg.de/cv ! State-of-the-Art
More informationLocal Features and Bag of Words Models
10/14/11 Local Features and Bag of Words Models Computer Vision CS 143, Brown James Hays Slides from Svetlana Lazebnik, Derek Hoiem, Antonio Torralba, David Lowe, Fei Fei Li and others Computer Engineering
More informationA 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 informationSpatial Latent Dirichlet Allocation
Spatial Latent Dirichlet Allocation Xiaogang Wang and Eric Grimson Computer Science and Computer Science and Artificial Intelligence Lab Massachusetts Tnstitute of Technology, Cambridge, MA, 02139, USA
More informationMoSIFT: Recognizing Human Actions in Surveillance Videos
MoSIFT: Recognizing Human Actions in Surveillance Videos CMU-CS-09-161 Ming-yu Chen and Alex Hauptmann School of Computer Science Carnegie Mellon University Pittsburgh PA 15213 September 24, 2009 Copyright
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 17 130402 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Background Subtraction Stauffer and Grimson
More informationMultilayer and Multimodal Fusion of Deep Neural Networks for Video Classification
Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Xiaodong Yang, Pavlo Molchanov, Jan Kautz INTELLIGENT VIDEO ANALYTICS Surveillance event detection Human-computer interaction
More informationCAP 6412 Advanced Computer Vision
CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha
More informationObject detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation
Object detection using Region Proposals (RCNN) Ernest Cheung COMP790-125 Presentation 1 2 Problem to solve Object detection Input: Image Output: Bounding box of the object 3 Object detection using CNN
More informationTri-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 informationPreviously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011
Previously Part-based and local feature models for generic object recognition Wed, April 20 UT-Austin Discriminative classifiers Boosting Nearest neighbors Support vector machines Useful for object recognition
More informationPEOPLE IN SEATS COUNTING VIA SEAT DETECTION FOR MEETING SURVEILLANCE
PEOPLE IN SEATS COUNTING VIA SEAT DETECTION FOR MEETING SURVEILLANCE Hongyu Liang, Jinchen Wu, and Kaiqi Huang National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science
More informationHistogram of Flow and Pyramid Histogram of Visual Words for Action Recognition
Histogram of Flow and Pyramid Histogram of Visual Words for Action Recognition Ethem F. Can and R. Manmatha Department of Computer Science, UMass Amherst Amherst, MA, 01002, USA [efcan, manmatha]@cs.umass.edu
More informationContent-based image and video analysis. Event Recognition
Content-based image and video analysis Event Recognition 21.06.2010 What is an event? a thing that happens or takes place, Oxford Dictionary Examples: Human gestures Human actions (running, drinking, etc.)
More informationDeep 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 informationClass 3: Advanced Moving Object Detection and Alert Detection Feb. 18, 2008
Class 3: Advanced Moving Object Detection and Alert Detection Feb. 18, 2008 Instructor: YingLi Tian Video Surveillance E6998-007 Senior/Feris/Tian 1 Outlines Moving Object Detection with Distraction Motions
More informationA Background Modeling Approach Based on Visual Background Extractor Taotao Liu1, a, Lin Qi2, b and Guichi Liu2, c
4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2015) A Background Modeling Approach Based on Visual Background Extractor Taotao Liu1, a, Lin Qi2, b
More informationMinimizing hallucination in Histogram of Oriented Gradients
Minimizing hallucination in Histogram of Oriented Gradients Javier Ortiz Sławomir Bąk Michał Koperski François Brémond INRIA Sophia Antipolis, STARS group 2004, route des Lucioles, BP93 06902 Sophia Antipolis
More informationDefinition, Detection, and Evaluation of Meeting Events in Airport Surveillance Videos
Definition, Detection, and Evaluation of Meeting Events in Airport Surveillance Videos Sung Chun Lee, Chang Huang, and Ram Nevatia University of Southern California, Los Angeles, CA 90089, USA sungchun@usc.edu,
More informationTracking. Hao Guan( 管皓 ) School of Computer Science Fudan University
Tracking Hao Guan( 管皓 ) School of Computer Science Fudan University 2014-09-29 Multimedia Video Audio Use your eyes Video Tracking Use your ears Audio Tracking Tracking Video Tracking Definition Given
More informationMotion in 2D image sequences
Motion in 2D image sequences Definitely used in human vision Object detection and tracking Navigation and obstacle avoidance Analysis of actions or activities Segmentation and understanding of video sequences
More informationOptical flow and tracking
EECS 442 Computer vision Optical flow and tracking Intro Optical flow and feature tracking Lucas-Kanade algorithm Motion segmentation Segments of this lectures are courtesy of Profs S. Lazebnik S. Seitz,
More informationClassification and Detection in Images. D.A. Forsyth
Classification and Detection in Images D.A. Forsyth Classifying Images Motivating problems detecting explicit images classifying materials classifying scenes Strategy build appropriate image features train
More informationResearch on Recognition and Classification of Moving Objects in Mixed Traffic Based on Video Detection
Hu, Qu, Li and Wang 1 Research on Recognition and Classification of Moving Objects in Mixed Traffic Based on Video Detection Hongyu Hu (corresponding author) College of Transportation, Jilin University,
More informationSearching Video Collections:Part I
Searching Video Collections:Part I Introduction to Multimedia Information Retrieval Multimedia Representation Visual Features (Still Images and Image Sequences) Color Texture Shape Edges Objects, Motion
More informationAction Recognition in Low Quality Videos by Jointly Using Shape, Motion and Texture Features
Action Recognition in Low Quality Videos by Jointly Using Shape, Motion and Texture Features Saimunur Rahman, John See, Chiung Ching Ho Centre of Visual Computing, Faculty of Computing and Informatics
More informationEXMOVES: Mid-level Features for Efficient Action Recognition and Video Analysis
Int J Comput Vis (2016) 119:239 253 DOI 10.1007/s11263-016-0905-6 EXMOVES: Mid-level Features for Efficient Action Recognition and Video Analysis Du Tran 1 Lorenzo Torresani 1 Received: 15 May 2014 / Accepted:
More informationIntroduction 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 informationDYNAMIC BACKGROUND SUBTRACTION BASED ON SPATIAL EXTENDED CENTER-SYMMETRIC LOCAL BINARY PATTERN. Gengjian Xue, Jun Sun, Li Song
DYNAMIC BACKGROUND SUBTRACTION BASED ON SPATIAL EXTENDED CENTER-SYMMETRIC LOCAL BINARY PATTERN Gengjian Xue, Jun Sun, Li Song Institute of Image Communication and Information Processing, Shanghai Jiao
More informationFish species recognition from video using SVM classifier
Fish species recognition from video using SVM classifier Katy Blanc, Diane Lingrand, Frédéric Precioso Univ. Nice Sophia Antipolis, I3S, UMR 7271, 06900 Sophia Antipolis, France CNRS, I3S, UMR 7271, 06900
More informationCS 231A Computer Vision (Fall 2012) Problem Set 3
CS 231A Computer Vision (Fall 2012) Problem Set 3 Due: Nov. 13 th, 2012 (2:15pm) 1 Probabilistic Recursion for Tracking (20 points) In this problem you will derive a method for tracking a point of interest
More informationBeyond Bags of Features
: for Recognizing Natural Scene Categories Matching and Modeling Seminar Instructed by Prof. Haim J. Wolfson School of Computer Science Tel Aviv University December 9 th, 2015
More informationSegmentation by Clustering. Segmentation by Clustering Reading: Chapter 14 (skip 14.5) General ideas
Reading: Chapter 14 (skip 14.5) Data reduction - obtain a compact representation for interesting image data in terms of a set of components Find components that belong together (form clusters) Frame differencing
More informationSegmentation by Clustering Reading: Chapter 14 (skip 14.5)
Segmentation by Clustering Reading: Chapter 14 (skip 14.5) Data reduction - obtain a compact representation for interesting image data in terms of a set of components Find components that belong together
More informationEvaluation of Local Space-time Descriptors based on Cuboid Detector in Human Action Recognition
International Journal of Innovation and Applied Studies ISSN 2028-9324 Vol. 9 No. 4 Dec. 2014, pp. 1708-1717 2014 Innovative Space of Scientific Research Journals http://www.ijias.issr-journals.org/ Evaluation
More informationThe 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 informationA Fast Moving Object Detection Technique In Video Surveillance System
A Fast Moving Object Detection Technique In Video Surveillance System Paresh M. Tank, Darshak G. Thakore, Computer Engineering Department, BVM Engineering College, VV Nagar-388120, India. Abstract Nowadays
More informationEECS150 - 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 informationHuman detection solution for a retail store environment
FACULDADE DE ENGENHARIA DA UNIVERSIDADE DO PORTO Human detection solution for a retail store environment Vítor Araújo PREPARATION OF THE MSC DISSERTATION Mestrado Integrado em Engenharia Eletrotécnica
More informationA Feature Point Matching Based Approach for Video Objects Segmentation
A Feature Point Matching Based Approach for Video Objects Segmentation Yan Zhang, Zhong Zhou, Wei Wu State Key Laboratory of Virtual Reality Technology and Systems, Beijing, P.R. China School of Computer
More informationSpatio-temporal Feature Classifier
Spatio-temporal Feature Classifier Send Orders for Reprints to reprints@benthamscience.ae The Open Automation and Control Systems Journal, 2015, 7, 1-7 1 Open Access Yun Wang 1,* and Suxing Liu 2 1 School
More informationSURVEY 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 informationP-CNN: Pose-based CNN Features for Action Recognition. Iman Rezazadeh
P-CNN: Pose-based CNN Features for Action Recognition Iman Rezazadeh Introduction automatic understanding of dynamic scenes strong variations of people and scenes in motion and appearance Fine-grained
More informationEfficient and effective human action recognition in video through motion boundary description with a compact set of trajectories
biblio.ugent.be The UGent Institutional Repository is the electronic archiving and dissemination platform for all UGent research publications. Ghent University has implemented a mandate stipulating that
More informationAutomatic 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 informationVisual Action Recognition
Visual Action Recognition Ying Wu Electrical Engineering and Computer Science Northwestern University, Evanston, IL 60208 yingwu@northwestern.edu http://www.eecs.northwestern.edu/~yingwu 1 / 57 Outline
More informationTwo-Stream Convolutional Networks for Action Recognition in Videos
Two-Stream Convolutional Networks for Action Recognition in Videos Karen Simonyan Andrew Zisserman Cemil Zalluhoğlu Introduction Aim Extend deep Convolution Networks to action recognition in video. Motivation
More informationAction Recognition Using Super Sparse Coding Vector with Spatio-Temporal Awareness
Action Recognition Using Super Sparse Coding Vector with Spatio-Temporal Awareness Xiaodong Yang and YingLi Tian Department of Electrical Engineering City College, City University of New York Abstract.
More informationThe Stanford/Technicolor/Fraunhofer HHI Video Semantic Indexing System
The Stanford/Technicolor/Fraunhofer HHI Video Semantic Indexing System Our first participation on the TRECVID workshop A. F. de Araujo 1, F. Silveira 2, H. Lakshman 3, J. Zepeda 2, A. Sheth 2, P. Perez
More informationMultiple-Person Tracking by Detection
http://excel.fit.vutbr.cz Multiple-Person Tracking by Detection Jakub Vojvoda* Abstract Detection and tracking of multiple person is challenging problem mainly due to complexity of scene and large intra-class
More informationDet De e t cting abnormal event n s Jaechul Kim
Detecting abnormal events Jaechul Kim Purpose Introduce general methodologies used in abnormality detection Deal with technical details of selected papers Abnormal events Easy to verify, but hard to describe
More informationTOWARDS DETECTING PEOPLE CARRYING OBJECTS A Periodicity Dependency Pattern Approach
TOWARDS DETECTING PEOPLE CARRYING OBJECTS A Periodicity Dependency Pattern Approach Tobias Senst, Rubén Heras Evangelio, Volker Eiselein, Michael Pätzold and Thomas Sikora Communication Systems Group,
More informationFeature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking
Feature descriptors Alain Pagani Prof. Didier Stricker Computer Vision: Object and People Tracking 1 Overview Previous lectures: Feature extraction Today: Gradiant/edge Points (Kanade-Tomasi + Harris)
More informationEfficient Object Localization with Gaussianized Vector Representation
Efficient Object Localization with Gaussianized Vector Representation ABSTRACT Xiaodan Zhuang xzhuang2@uiuc.edu Mark A. Hasegawa-Johnson jhasegaw@uiuc.edu Recently, the Gaussianized vector representation
More informationSpring semester 2008 June 24 th 2009
Spring semester 2008 June 24 th 2009 Introduction Suggested Algorithm Outline Implementation Summary Live Demo 2 Project Motivation and Domain High quality pedestrian detection and tracking system. Fixed
More informationCS 223B Computer Vision Problem Set 3
CS 223B Computer Vision Problem Set 3 Due: Feb. 22 nd, 2011 1 Probabilistic Recursion for Tracking In this problem you will derive a method for tracking a point of interest through a sequence of images.
More informationColorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.
Professor William Hoff Dept of Electrical Engineering &Computer Science http://inside.mines.edu/~whoff/ 1 Object Recognition in Large Databases Some material for these slides comes from www.cs.utexas.edu/~grauman/courses/spring2011/slides/lecture18_index.pptx
More informationCS 231A Computer Vision (Fall 2012) Problem Set 4
CS 231A Computer Vision (Fall 2012) Problem Set 4 Master Set Due: Nov. 29 th, 2012 (23:59pm) 1 Part-based models for Object Recognition (50 points) One approach to object recognition is to use a deformable
More informationOn the Effects of Low Video Quality in Human Action Recognition
On the Effects of Low Video Quality in Human Action Recognition John See Faculty of Computing and Informatics Multimedia University Cyberjaya, Selangor, Malaysia Email: johnsee@mmu.edu.my Saimunur Rahman
More information