MVL (Machine Vision Lab) UIC HUMAN MOTION VIDEO DATABASE Jezekiel Ben-Arie ECE Department University Of Illinois at Chicago Scripts, Queries, Recognition.

Slides:



Advertisements
Similar presentations
Animation in Video Games presented by Jason Gregory
Advertisements

Presented by Xinyu Chang
Kien A. Hua Division of Computer Science University of Central Florida.
Content-Based Image Retrieval
Víctor Ponce Miguel Reyes Xavier Baró Mario Gorga Sergio Escalera Two-level GMM Clustering of Human Poses for Automatic Human Behavior Analysis Departament.
Vision Based Control Motion Matt Baker Kevin VanDyke.
Real-Time Human Pose Recognition in Parts from Single Depth Images Presented by: Mohammad A. Gowayyed.
Silhouette Lookup for Automatic Pose Tracking N ICK H OWE.
Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots Chao-Yeh Chen and Kristen Grauman University of Texas at Austin.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
A Novel Scheme for Video Similarity Detection Chu-Hong Hoi, Steven March 5, 2003.
Haojie Li Jinhui Tang Si Wu Yongdong Zhang Shouxun Lin Automatic Detection and Analysis of Player Action in Moving Background Sports Video Sequences IEEE.
Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.
Motion Editing and Retargetting Jinxiang Chai. Outline Motion editing [video, click here]here Motion retargeting [video, click here]here.
KAIST CS780 Topics in Interactive Computer Graphics : Crowd Simulation A Task Definition Language for Virtual Agents WSCG’03 Spyros Vosinakis, Themis Panayiotopoulos.
A Study of Approaches for Object Recognition
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman ICCV 2003 Presented by: Indriyati Atmosukarto.
Motion Map: Image-based Retrieval and Segmentation of Motion Data EG SCA ’ 04 學生 : 林家如
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE.
Dynamic Response for Motion Capture Animation Victor B. Zordan Anna Majkowska Bill Chiu Matthew Fast Riverside Graphics Lab University of California, Riverside.
Tracking Video Objects in Cluttered Background
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
A Vision-Based System that Detects the Act of Smoking a Cigarette Xiaoran Zheng, University of Nevada-Reno, Dept. of Computer Science Dr. Mubarak Shah,
Learning and Recognizing Activities in Streams of Video Dinesh Govindaraju.
Computer-Based Animation. ● To animate something – to bring it to life ● Animation covers all changes that have visual effects – Positon (motion dynamic)
Jan SedmidubskySeptember 23, 2014Motion Retrieval for Security Applications Jan Sedmidubsky Jakub Valcik Pavel Zezula Motion Retrieval for Security Applications.
Human Emotion Synthesis David Oziem, Lisa Gralewski, Neill Campbell, Colin Dalton, David Gibson, Barry Thomas University of Bristol, Motion Ripper, 3CR.
Keypoint-based Recognition Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 03/04/10.
Flow Based Action Recognition Papers to discuss: The Representation and Recognition of Action Using Temporal Templates (Bobbick & Davis 2001) Recognizing.
Introduction Tracking the corners Camera model and collision detection Keyframes Path Correction Controlling the entire path of a virtual camera In computer.
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
Probabilistic Context Free Grammars for Representing Action Song Mao November 14, 2000.
Miguel Reyes 1,2, Gabriel Dominguez 2, Sergio Escalera 1,2 Computer Vision Center (CVC) 1, University of Barcelona (UB) 2
A Method for Hand Gesture Recognition Jaya Shukla Department of Computer Science Shiv Nadar University Gautam Budh Nagar, India Ashutosh Dwivedi.
Zhejiang University Wavelet-based 3D mesh model watermarking Shi Jiao-Ying State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou
HOUGH TRANSFORM Presentation by Sumit Tandon
Recognition, Analysis and Synthesis of Gesture Expressivity George Caridakis IVML-ICCS.
3D polygonal meshes watermarking using normal vector distributions Suk-Hawn Lee, Tae-su Kim, Byung-Ju Kim, Seong-Geun Kwon.
Recognizing Action at a Distance Alexei A. Efros, Alexander C. Berg, Greg Mori, Jitendra Malik Computer Science Division, UC Berkeley Presented by Pundik.
A Face processing system Based on Committee Machine: The Approach and Experimental Results Presented by: Harvest Jang 29 Jan 2003.
Mingyang Zhu, Huaijiang Sun, Zhigang Deng Quaternion Space Sparse Decomposition for Motion Compression and Retrieval SCA 2012.
Dynamic Captioning: Video Accessibility Enhancement for Hearing Impairment Richang Hong, Meng Wang, Mengdi Xuy Shuicheng Yany and Tat-Seng Chua School.
CAMEO: Year 1 Progress and Year 2 Goals Manuela Veloso, Takeo Kanade, Fernando de la Torre, Paul Rybski, Brett Browning, Raju Patil, Carlos Vallespi, Betsy.
Human pose recognition from depth image MS Research Cambridge.
Ai-Mei Huang, Student Member, IEEE, and Truong Nguyen, Fellow, IEEE.
Chapter 5 Multi-Cue 3D Model- Based Object Tracking Geoffrey Taylor Lindsay Kleeman Intelligent Robotics Research Centre (IRRC) Department of Electrical.
Sparse Bayesian Learning for Efficient Visual Tracking O. Williams, A. Blake & R. Cipolloa PAMI, Aug Presented by Yuting Qi Machine Learning Reading.
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
Bachelor of Engineering In Image Processing Techniques For Video Content Extraction Submitted to the faculty of Engineering North Maharashtra University,
Human Activity Recognition at Mid and Near Range Ram Nevatia University of Southern California Based on work of several collaborators: F. Lv, P. Natarajan,
Semantic Extraction and Semantics-Based Annotation and Retrieval for Video Databases Authors: Yan Liu & Fei Li Department of Computer Science Columbia.
Team Members Ming-Chun Chang Lungisa Matshoba Steven Preston Supervisors Dr James Gain Dr Patrick Marais.
Chapter 8. Learning of Gestures by Imitation in a Humanoid Robot in Imitation and Social Learning in Robots, Calinon and Billard. Course: Robots Learning.
Multimedia Systems and Communication Research Multimedia Systems and Communication Research Department of Electrical and Computer Engineering Multimedia.
Human Activity Recognition, Biometrics and Cybersecurity Mohamed Abdel-Mottaleb, Ph.D. Image Processing and Computer Vision Department of Electrical and.
VISUAL INFORMATION RETRIEVAL Presented by Dipti Vaidya.
Frank Bergschneider February 21, 2014 Presented to National Instruments.
3D Motion Classification Partial Image Retrieval and Download Multimedia Project Multimedia and Network Lab, Department of Computer Science.
ENTERFACE 08 Project 9 “ Tracking-dependent and interactive video projection ” Mid-term presentation August 19th, 2008.
Over the recent years, computer vision has started to play a significant role in the Human Computer Interaction (HCI). With efficient object tracking.
Computer Graphics.
Visual Information Retrieval
Date of download: 10/17/2017 Copyright © ASME. All rights reserved.
3D Motion Classification Partial Image Retrieval and Download
Gait Recognition Gökhan ŞENGÜL.
Nearest-neighbor matching to feature database
Video-based human motion recognition using 3D mocap data
Nearest-neighbor matching to feature database
Kan Liu, Bingpeng Ma, Wei Zhang, Rui Huang
Presentation transcript:

MVL (Machine Vision Lab) UIC HUMAN MOTION VIDEO DATABASE Jezekiel Ben-Arie ECE Department University Of Illinois at Chicago Scripts, Queries, Recognition

MVL (Machine Vision Lab) UIC  Composition of interactive motion queries.  Analysis and Recognition of human activities.  Human body parts labeling.  Human detection.

MVL (Machine Vision Lab) UIC HUMAN ACTIVITY CAPTURE AND REGONITION

MVL (Machine Vision Lab) UIC Motion Query Video Retrieval Retrieved videos Video Database Videos Video Analysis and Recognition User Visual Feedback

MVL (Machine Vision Lab) UIC HUMAN BODY PART LABELING  Objective: Identify the roles of parts that appear as bars.  Labeling : Using the spatial locations and orientations.  Method : Finding maximum conjunction of partial hypotheses.

MVL (Machine Vision Lab) UIC Theoretical Foundations HUMAN BODY PART LABELING

MVL (Machine Vision Lab) UIC HUMAN BODY PART LABELING Illustration of Theoretical Foundations (a) (b) Overlap of Spatial distribution for (a) Correct Labeling (b) Incorrect Labeling

MVL (Machine Vision Lab) UIC HUMAN BODY PART LABELING (a) (b) Mesh diagram of Overlap of Spatial distribution for (a) Correct Labeling (b) Incorrect Labeling

MVL (Machine Vision Lab) UIC HUMAN BODY PART LABELING Experimental Results / Silhouette Extraction / Bar detection Using Gabor signatures. Parsing silhouettes / 90 different human poses / 98.7% correct labeling.

MVL (Machine Vision Lab) UIC HUMAN BODY PART LABELING Experimental Results

MVL (Machine Vision Lab) UIC HUMAN BODY PART LABELING Experimental Results

MVL (Machine Vision Lab) UIC HUMAN BODY PART LABELING Silhouette Extraction

MVL (Machine Vision Lab) UIC HUMAN BODY PART LABELING Silhouette Extraction Illustration of variation of chromaticity and brightness distortion

MVL (Machine Vision Lab) UIC HUMAN ACTIVITY RECOGNITION Introduction / Poses indicative of actions taking place Poses involved in walking / Indexing based recognition using sparse frames / Extends this technique with optimal constrained sequencing based voting

MVL (Machine Vision Lab) UIC HUMAN ACTIVITY RECOGNITION Introduction / Temporal sequence of pose vectors / Multidimensional hash tables for model activities / Individual hash tables for each body part / Identifying input pose vectors as samples of densely sampled model activity and create vote vectors / Vote vectors are temporal depiction of the log- likelihood that indexed pose belongs to a model / Dynamic programming based constrained sequencing to recognize activities

MVL (Machine Vision Lab) UIC HUMAN ACTIVITY RECOGNITION Creating Vote Vectors Illustration of the entire voting process

MVL (Machine Vision Lab) UIC HUMAN ACTIVITY RECOGNITION Experimental Results Videos of sitting action overlaid with skeleton superposed with the help of tracking information Sparse samples of jump activity adequate for robust recognition

MVL (Machine Vision Lab) UIC HUMAN ACTIVITY RECOGNITION Experimental Results Average votes for 5 test videos of each activity along with the votes for other activities. Rows – Test Activity Columns – Model Activity Recognition rate under various conditions of occlusion

MVL (Machine Vision Lab) UIC HUMAN ACTIVITY RECOGNITION Experimental Results Performance of the approach under conditions of view point variance

MVL (Machine Vision Lab) UIC FACE DETECTION Original ImageSkin detectionRegions passing the ellipse area criterion Detection by the GaborsDetected Faces

MVL (Machine Vision Lab) UIC FACE DETECTION Original Image Detected faces with medium threshold (0.7) Detected faces with maximum threshold (0.8)

MVL (Machine Vision Lab) UIC GUI for Queries Composition " Motion query is composed by using model motion data clips. " An example of a model motion data clip is a walk cycle consisting of a sequence of poses in one basic cycle of left-right steps. " Model motion data clip can also be non-cyclic such as sitting. " Model motion data clip is obtained from a motion capture library or can be interactively composed by the user.

MVL (Machine Vision Lab) UIC Specify Trajectory Key-points Interpolate by Splines Specify Activities Calculate Segments Calculate Position and Orientations Generate Motion Sequences(Scripts) Display INTERACTIVE GUI

MVL (Machine Vision Lab) UIC Theoretical Foundations Parameterization of 3-D rotations (Euler Quaternions) Splines (Catmull Rom) Interpolation (SLERP, Quaternions) Human body model Motion composition techniques (Inverse Kinematics, Mocap)

MVL (Machine Vision Lab) UIC Limb Pose Vocabulary

MVL (Machine Vision Lab) UIC Example of complete body poses

MVL (Machine Vision Lab) UIC Inverse kinematics based key framing tool

MVL (Machine Vision Lab) UIC Implementation