Particle Dynamics and Multi- Channel Feature Dictionaries for Robust Visual Tracking Srikrishna Karanam, Yang Li, Rich Radke Dept. of Electrical, Computer,

Slides:



Advertisements
Similar presentations
Dynamic Spatial Mixture Modelling and its Application in Cell Tracking - Work in Progress - Chunlin Ji & Mike West Department of Statistical Sciences,
Advertisements

Probabilistic Tracking and Recognition of Non-rigid Hand Motion
Jose-Luis Blanco, Javier González, Juan-Antonio Fernández-Madrigal University of Málaga (Spain) Dpt. of System Engineering and Automation May Pasadena,
Automatic Image Annotation Using Group Sparsity
ETISEO, Nice, May PETS International Workshops on Performance Evaluation of Tracking and Surveillance James Ferryman Computational Vision Group.
Fast Algorithms For Hierarchical Range Histogram Constructions
Analysis of Contour Motions Ce Liu William T. Freeman Edward H. Adelson Computer Science and Artificial Intelligence Laboratory Massachusetts Institute.
Robust Visual Tracking – Algorithms, Evaluations and Problems Haibin Ling Department of Computer and Information Sciences Temple University Philadelphia,
Patch to the Future: Unsupervised Visual Prediction
Spatial Histograms for Head Tracking Sriram Rangarajan Department of Electrical and Computer Engineering, Clemson University, Clemson, SC
Computer Vision for Human-Computer InteractionResearch Group, Universität Karlsruhe (TH) cv:hci Dr. Edgar Seemann 1 Computer Vision: Histograms of Oriented.
Activity Recognition Aneeq Zia. Agenda What is activity recognition Typical methods used for action recognition “Evaluation of local spatio-temporal features.
Computer Vision – Image Representation (Histograms)
More MR Fingerprinting
Forward-Backward Correlation for Template-Based Tracking Xiao Wang ECE Dept. Clemson University.
Robust Object Tracking via Sparsity-based Collaborative Model
Enhancing Exemplar SVMs using Part Level Transfer Regularization 1.
Robust Moving Object Detection & Categorization using self- improving classifiers Omar Javed, Saad Ali & Mubarak Shah.
Recognition using Regions CVPR Outline Introduction Overview of the Approach Experimental Results Conclusion.
Detecting Prosody Improvement in Oral Rereading Minh Duong and Jack Mostow Project LISTEN Carnegie Mellon University The research.
Multi-Class Object Recognition Using Shared SIFT Features
Robust Lane Detection and Tracking
CVPR 2006 New York City Granularity and Elasticity Adaptation in Visual Tracking Ming Yang, Ying Wu NEC Laboratories America Cupertino, CA 95014
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
Real Time Abnormal Motion Detection in Surveillance Video Nahum Kiryati Tammy Riklin Raviv Yan Ivanchenko Shay Rochel Vision and Image Analysis Laboratory.
KinWrite: Handwriting-Based Authentication Using Kinect Proceedings of the 20th Annual Network & Distributed System Security Symposium, NDSS 2013 Jing.
Computer vision.
Computer Vision James Hays, Brown
Parameter selection in prostate IMRT Renzhi Lu, Richard J. Radke 1, Andrew Jackson 2 Rensselaer Polytechnic Institute 1,Memorial Sloan-Kettering Cancer.
This material is based upon work supported by the U.S. Department of Homeland Security, Science and Technology Directorate, Office of University Programs,
Technion - Israel Institute of Technology Department of Electrical Engineering Advanced Topics in Computer Vision Course Presentation By Stav Shapiro.
Tracking by Sampling Trackers Junseok Kwon* and Kyoung Mu lee Computer Vision Lab. Dept. of EECS Seoul National University, Korea Homepage:
Segmentation and classification of man-made maritime objects in TerraSAR-X images IEEE International Geoscience and Remote Sensing Symposium Vancouver,
Bag of Visual Words for Image Representation & Visual Search Jianping Fan Dept of Computer Science UNC-Charlotte.
A General Framework for Tracking Multiple People from a Moving Camera
A Local Adaptive Approach for Dense Stereo Matching in Architectural Scene Reconstruction C. Stentoumis 1, L. Grammatikopoulos 2, I. Kalisperakis 2, E.
Video Tracking Using Learned Hierarchical Features
Dynamic 3D Scene Analysis from a Moving Vehicle Young Ki Baik (CV Lab.) (Wed)
COLOR HISTOGRAM AND DISCRETE COSINE TRANSFORM FOR COLOR IMAGE RETRIEVAL Presented by 2006/8.
Deformable Part Model Presenter : Liu Changyu Advisor : Prof. Alex Hauptmann Interest : Multimedia Analysis April 11 st, 2013.
Structured Face Hallucination Chih-Yuan Yang Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science 1.
Epitomic Location Recognition A generative approach for location recognition K. Ni, A. Kannan, A. Criminisi and J. Winn In proc. CVPR Anchorage,
The 18th Meeting on Image Recognition and Understanding 2015/7/29 Depth Image Enhancement Using Local Tangent Plane Approximations Kiyoshi MatsuoYoshimitsu.
Students: Meera & Si Mentor: Afshin Dehghan WEEK 4: DEEP TRACKING.
Boosted Particle Filter: Multitarget Detection and Tracking Fayin Li.
An Effective & Interactive Approach to Particle Tracking for DNA Melting Curve Analysis 李穎忠 DEPARTMENT OF COMPUTER SCIENCE & INFORMATION ENGINEERING NATIONAL.
 Present by 陳群元.  Introduction  Previous work  Predicting motion patterns  Spatio-temporal transition distribution  Discerning pedestrians  Experimental.
A Dynamic Conditional Random Field Model for Object Segmentation in Image Sequences Duke University Machine Learning Group Presented by Qiuhua Liu March.
Skeleton Based Action Recognition with Convolutional Neural Network
Matching of Objects Moving Across Disjoint Cameras Eric D. Cheng and Massimo Piccardi IEEE International Conference on Image Processing
Quantitative Analysis of Mitochondrial Tubulation Using 3D Imaging Saritha Dwarakapuram*, Badrinath Roysam*, Gang Lin*, Kasturi Mitra§ Department of Electrical.
More sliding window detection: Discriminative part-based models
Video Google: Text Retrieval Approach to Object Matching in Videos Authors: Josef Sivic and Andrew Zisserman University of Oxford ICCV 2003.
1 Bilinear Classifiers for Visual Recognition Computational Vision Lab. University of California Irvine To be presented in NIPS 2009 Hamed Pirsiavash Deva.
Object detection with deformable part-based models
Introducing the M-metric Maurice R. Masliah and Paul Milgram
Application of 13 MHz SeaSonde Systems for Vessel Detection
Video Google: Text Retrieval Approach to Object Matching in Videos
Discussion and Conclusion
CSSE463: Image Recognition Day 25
A Tutorial on HOG Human Detection
Guest lecturer: Isabel K. Darcy
Convolutional Neural Networks for Visual Tracking
Vision Tracking System
KFC: Keypoints, Features and Correspondences
Part-based visual tracking with online latent structural learning -Rui Yao et al. ICCV 2013 Cvlab Jung ilchae.
Video Google: Text Retrieval Approach to Object Matching in Videos
Related Work in Camera Network Tracking
CVPR2019 Jiahe Li SiamRPN introduces the region proposal network after the Siamese network and performs joint classification and regression.
Presentation transcript:

Particle Dynamics and Multi- Channel Feature Dictionaries for Robust Visual Tracking Srikrishna Karanam, Yang Li, Rich Radke Dept. of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy NY

Compressive sensing tracking 2 Feature dictionary

Compressive sensing tracking 3 Curren t state Hypothese s

Compressive sensing tracking 4 Hypothesis Testing Sparse x, e

Contributions APPEARAN CE MODEL Multi-channel feature dictionaries Image intensity Image gradient magnitude Histograms of Oriented Gradients HYPOTHESI S GENERATIO N Particle filter Adaptive variance Gaussian State Transition Model 5

Appearance model 6 Intensity Normalized gradient magnitude Histograms of Oriented Gradients Norm. Gradien t HOG ∑ Intensit y ∑ ∑

Hypothesis generation – Transition model 7 Past state vecto rs Z. Hong et al., Tracking via robust multi-task multi-view joint sparse representation, ICCV 2013.

Hypothesis generation – Transition model 8 M. Ayazoglu et al., Dynamic subspace-based coordinated multicamera tracking, ICCV (1 ) (2 ) (3 ) (4 ) (5 ) (6 )

Hypothesis generation – Particle filtering 9 Related approaches – ( , fixed) Dynamic model + adaptive candidate filtering D. Fox, KLD-Sampling: Adaptive Particle Filters, NIPS 2001.

Hypothesis testing 10 FISTA Analytic

Data Publicly available standard test sequences 11 Focal Length Y. Wu et al., Online object tracking: a benchmark, CVPR 2013.

Evaluation metrics Success plot Robustness tests Temporal robustness test Spatial Robustness test 12 Principal PointFocal Length Overlap precision vs. Overlap threshold

Experimental Results – Overall Success Plot Ideally, close to 1 13 Principal PointFocal Length

Experimental Results – Robustness tests Temporal robustness evaluation Spatial robustness evaluation 14 Principal PointFocal Length

Experimental Results Validating key components. Choice of features. Choice of transition model. Adaptive candidate filtering 15 Principal PointFocal Length Distortion Coefficient

Speed 16 MethodSpeed (fps) Templat e size Average distance precisio n Average AUC Ours*2.564 x L1*8.212 x MTT*0.432 x ONDL*0.532 x SCM* x ASLA*0.732 x LSH LOT SPT MIL IVT * - based on sparse visual representation.

This material is based upon work supported by the U.S. Department of Homeland Security, Science and Technology Directorate, Office of University Programs, under Award 2013-ST-061-ED0001. The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the U.S. Department of Homeland Security. Conclusions Multi-Channel features Particle dynamical information Adaptive filtering Thank you! Questions?