Learning to Track: Online Multi- Object Tracking by Decision Making
|
|
- Charlotte Singleton
- 5 years ago
- Views:
Transcription
1 Learning to Track: Online Multi- Object Tracking by Decision Making Yu Xiang 1,2, Alexandre Alahi 1, and Silvio Savarese 1 1 Stanford University, 2 University of Michigan ICCV
2 Multi-Object Tracking Visual surveillance Robot navigation Sport Analysis Autonomous driving 2
3 Batch Mode vs. Online Mode Batch Mode t-2 t-1 t t+1 t+2 time axis Online Mode t-2 t-1 t t+1 t+2 time axis 3
4 Tracking by Detection 4
5 Data Association? Tracks at time t-1 Detections at time t time axis 5
6 Challenges Noisy detection: false alarms and missing detections 6
7 Challenges Occlusion 7
8 Similarity Function for Data Association Zhang et al., CVPR 08 Berclaz et al., TPAMI 11 Breitenstein et al., TPAMI 11 Pirsiavash et al., CVPR 11 Butt & Collins, CVPR 13 Milan et al., TPAMI 14 Etc. Tracks at time t-1 Detections at time t time axis Ours Simple similarity measure + Powerful optimization 8
9 Learning to Track Different features/cues between targets and detections Appearance Location Motion Etc. φ 1 (, ) Similarity = w w n φ n (, ) Weights to combine different cues (to be learned) 9
10 Offline-learning vs. Online-learning 10
11 Offline-learning vs. Online-learning Training time With supervision Before Tracking Offlinelearning Onlinelearning During Tracking Use history of the target Li et al., CVPR 09 Kim et al., ACCV 12 Etc. 11
12 Offline-learning vs. Online-learning Training time With supervision Before Tracking Offlinelearning Onlinelearning During Tracking Use history of the target Song et al., ECCV 08 Kuo et al., CVPR 10 Bae et al., CVPR 14 Etc. 12
13 Our Solution: Tracking by Decision Making The target is tracked The target is occluded The target is tracked again 13
14 Inverse Reinforcement Learning tracked lost tracked Ground truth trajectory Markov Decision Process (MDP) Supervision Tracked Lost Tracked 14
15 Comparison between Different Learning Strategies Offlinelearning Onlinelearning Ours Training time Before Tracking During Tracking Before Tracking With supervision Use history of the target 15
16 Comparison between Different Learning Strategies Offlinelearning Onlinelearning Ours Training time Before Tracking During Tracking Before Tracking With supervision Use history of the target 16
17 Outline Markov Decision Process (MDP) for a Single Target Online Multi-Object Tracking with MDPs Experiments Conclusion 17
18 Outline Markov Decision Process (MDP) for a Single Target Online Multi-Object Tracking with MDPs Experiments Conclusion 18
19 Markov Decision Process for a Single Target object detection Tracked Active Lost Inactive 19
20 Markov Decision Process for a Single Target object detection Tracked Active Lost Inactive 20
21 Markov Decision Process for a Single Target object detection Tracked Active Lost Inactive 21
22 Markov Decision Process for a Single Target object detection Tracked Active Inactive 22
23 Markov Decision Process for a Single Target object detection Tracked Single object tracking Active Lost Inactive TLD Tracker. Z. Kalal, K. Mikolajczyk, and J. Matas. Tracking-learning-detection. TPAMI, 34(7): ,
24 Template Tracking in Tracked States Frame 50 Frame 51 24
25 Template Tracking in Tracked States Frame 50 Frame 51 25
26 Template Tracking in Tracked States Frame 50 Frame 51 26
27 Template Tracking in Tracked States Frame 50 Frame 51 Tracked 27
28 Template Tracking in Tracked States Frame 50 Frame 57 28
29 Template Tracking in Tracked States Frame 50 Frame 57 29
30 Template Tracking in Tracked States Frame 50 Frame 57 30
31 Template Tracking in Tracked States Frame 50 Frame 57 Tracked Lost 31
32 Markov Decision Process for a Single Target object detection Tracked Active Lost Inactive If lost for more than T frames 32
33 Data Association in Lost States tracked lost? t-2 t-1 t time axis 33
34 Learning the Similarity Function φ 1 (, ) Similarity = w w n φ n (, ) + b Inverse reinforcement learning: tracking objects in training videos! (, 1 ) (, 2 ) (, M ) Hard positive examples (, 1 ) (, 2 ) (, N ) Hard negative examples 34
35 Inverse Reinforcement Learning Ground truth trajectory Supervision 1 tracked lost t-2 t-1 t time axis 35
36 Inverse Reinforcement Learning Ground truth trajectory Supervision 1 tracked lost t-2 t-1 t time axis 36
37 Inverse Reinforcement Learning Ground truth trajectory Supervision 1 Wrong decision! Update your weights! tracked lost 2 (, 1 ) 3 Negative example 4 t-2 t-1 t time axis 37
38 Inverse Reinforcement Learning Ground truth trajectory Try it again Supervision 1 tracked lost No association 2 Wrong decision! Association to this one! Update your weights! 3 (, 2 ) 4 Positive example time axis t-2 t-1 t 38
39 Inverse Reinforcement Learning Try it again Ground truth trajectory Supervision 1 tracked lost 2 Good job! Keep going! No update of the weights 3 4 t-2 t-1 t time axis 39
40 Markov Decision Process for a Single Target object detection Tracked Active Lost Inactive 40
41 Outline Markov Decision Process (MDP) for a Single Target Online Multi-Object Tracking with MDPs Experiments Conclusion 41
42 Ensemble MDPs for Online Multi-Object Tracking MDP1 MDP2 MDP3 t-2 t-1 t time axis 42
43 Step 1: Process tracked targets MDP1 MDP2 MDP3 t-2 t-1 t time axis 43
44 Step 2: Process lost targets MDP1 MDP2 MDP3 Hungarian algorithm for lost targets t-2 t-1 t time axis 44
45 Step 3: Initialize new targets MDP1 MDP2 Initialize new targets MDP3 Terminate detection t-2 t-1 t time axis 45
46 Online Multi-Object Tracking with MDPs MDP1 Tracked Lost Tracked MDP2 Tracked Lost Tracked MDP3 Tracked Tracked Tracked 46
47 Outline Markov Decision Process (MDP) for a Single Target Online Multi-Object Tracking with MDPs Experiments Conclusion 47
48 Experiments: Dataset Multiple Object Tracking Benchmark [1] 11 training sequences 11 test sequences Object detections from the ACF detector [2] [1] L. Leal-Taixé, A. Milan, I. Reid, S. Roth, and K. Schindler. MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking. arxiv: [cs], [2] P. Dollár, R. Appel, S. Belongie, and P. Perona. Fast feature pyramids for object detection. TPAMI, 36(8): ,
49 Experiments: Analysis on Validation Set Contribution of different components 49
50 Experiments: Analysis on Validation Set Contribution of different components object detection Tracked Active Lost Inactive MOTA: multiple object tracking accuracy 50
51 Experiments: Analysis on Validation Set Contribution of different components object detection Tracked Active Lost Inactive MOTA: multiple object tracking accuracy 51
52 Experiments: Analysis on Validation Set Contribution of different components object detection Tracked Active Lost Inactive MOTA: multiple object tracking accuracy 52
53 Experiments: Analysis on Validation Set Contribution of different components Similarity = w 1 φ 1 (, ) + + w n φ n (, ) + b MOTA: multiple object tracking accuracy 53
54 Experiments: Analysis on Validation Set Contribution of different components Similarity = w 1 φ 1 (, ) + + w n φ n (, ) + b MOTA: multiple object tracking accuracy 54
55 Training Sequences Experiments: Analysis on Validation Set Cross-domain tracking MOTA: multiple object tracking accuracy TUD-Stadtmitte ETH-Bahnhof ADL-Rundle-6 KITTI-13 PETS09-S2L1 Testing sequences 55
56 Training Sequences Experiments: Analysis on Validation Set Cross-domain tracking MOTA: multiple object tracking accuracy TUD-Stadtmitte ETH-Bahnhof ADL-Rundle-6 KITTI-13 PETS09-S2L1 Testing sequences 56
57 Training Sequences Experiments: Analysis on Validation Set Cross-domain tracking MOTA: multiple object tracking accuracy TUD-Stadtmitte ETH-Bahnhof ADL-Rundle-6 KITTI-13 PETS09-S2L1 Testing sequences 57
58 Experiments: Evaluation on Test Set Tracker Tracking Learning MOTA DP_NMS [1] Batch N/A 14.5 TC_ODAL [2] Online Online 15.1 TBD [3] Batch Offline 15.9 SMOT [4] Batch N/A 18.2 RMOT [5] Online N/A 18.6 CEM [6] Online N/A 19.3 SegTrack [7] Batch Offline 22.5 MotiCon [8] Batch Offline 23.1 MDP (Ours) Online Online 30.3 MOTA: multiple object tracking accuracy [1] Pirsiavash et al., CVPR 11 [2] Bae et al., CVPR 14 [3] Geiger et al., TPAMI 14 [4] Dicle et al., ICCV 13 [5] Yoon et al., WACV 15 [6] Milan et al., TPAMI 14 [7] Milan et al., CVPR 15 [8] Leal-Taixé et al., CVPR 14 58
59 Tracking Results 59
60 MDP [Ours] MotiCon [Leal-Taixé et al., CVPR 14] 60
61 MDP [Ours] MotiCon [Leal-Taixé et al., CVPR 14] 61
62 MDP [Ours] MotiCon [Leal-Taixé et al., CVPR 14] 62
63 Outline Markov Decision Process (MDP) for a Single Target Online Multi-Object Tracking with MDPs Experiments Conclusion 63
64 Conclusion Single Object Tracking Tracked Active Lost Object Detection Inactive Data Association Target Re-identification 64
65 Code 65
66 Single Object Tracking Tracked Active Lost Object Detection Inactive Data Association Target Re-identification Thank you! 66
Rewind to Track: Parallelized Apprenticeship Learning with Backward Tracklets
Rewind to Track: Parallelized Apprenticeship Learning with Backward Tracklets Jiang Liu 1,2, Jia Chen 2, De Cheng 2, Chenqiang Gao 1, Alexander G. Hauptmann 2 1 Chongqing University of Posts and Telecommunications
More informationSIMPLE ONLINE AND REALTIME TRACKING. Queensland University of Technology, University of Sydney
SIMPLE ONLINE AND REALTIME TRACKING Alex Bewley, Zongyuan Ge, Lionel Ott, Fabio Ramos, Ben Upcroft Queensland University of Technology, University of Sydney ABSTRACT This paper explores a pragmatic approach
More informationMulti-Target Tracking Using Hierarchical Convolutional Features and Motion Cues
Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues Heba Mahgoub, Khaled Mostafa, Khaled T. Wassif, Ibrahim Farag Faculty of Computers and Information Cairo University Cairo,
More informationarxiv: v1 [cs.cv] 28 Nov 2015
Sliding Window Optimization on an Ambiguity-Clearness Graph for Multi-object Tracking Qi Guo Le Dan Dong Yin Xiangyang Ji Tsinghua University, Beijing, 184, China arxiv:15118913v1 [cscv] 28 Nov 215 Abstract
More informationOnline Motion Agreement Tracking
WU,ZHANG,BETKE: ONLINE MOTION AGREEMENT TRACKING 1 Online Motion Agreement Tracking Zheng Wu wuzheng@bu.edu Jianming Zhang jmzhang@bu.edu Margrit Betke betke@bu.edu Computer Science Department Boston University
More informationMOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
MOTChallenge 5: Towards a Benchmark for Multi-Target Tracking Laura Leal-Taixé, Anton Milan, Ian Reid, Stefan Roth, and Konrad Schindler arxiv:54.94v [cs.cv] 8 Apr 5 Abstract In the recent past, the computer
More informationPerformance Measures and the DukeMTMC Benchmark for Multi-Target Multi-Camera Tracking. Ergys Ristani
Performance Measures and the DukeMTMC Benchmark for Multi-Target Multi-Camera Tracking Ergys Ristani In collaboration with: Francesco Solera Roger Zou Rita Cucchiara Carlo Tomasi Outline Problem Definition
More informationarxiv: v2 [cs.cv] 14 Aug 2017
Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism Qi Chu 1,3, Wanli Ouyang 2,3, Hongsheng Li 3, Xiaogang Wang 3, Bin Liu 1, Nenghai Yu 1, 1 University
More informationReal-Time* Multiple Object Tracking (MOT) for Autonomous Navigation
Real-Time* Multiple Object Tracking (MOT) for Autonomous Navigation Ankush Agarwal,1 Saurabh Suryavanshi,2 ankushag@stanford.edu saurabhv@stanford.edu Authors contributed equally for this project. 1 Google
More informationOnline Tracking Parameter Adaptation based on Evaluation
2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance Online Tracking Parameter Adaptation based on Evaluation Duc Phu Chau Julien Badie François Brémond Monique Thonnat
More informationJoint detection and online multi-object tracking
Joint detection and online multi-object tracking Hilke Kieritz, Wolfgang Hübner, and Michael Arens Fraunhofer IOSB, Germany {hilke.kieritz wolfgang.huebner michael.arens}@iosb.fraunhofer.de Abstract Most
More informationVisual Object Tracking. Jianan Wu Megvii (Face++) Researcher Dec 2017
Visual Object Tracking Jianan Wu Megvii (Face++) Researcher wjn@megvii.com Dec 2017 Applications From image to video: Augmented Reality Motion Capture Surveillance Sports Analysis Wait. What is visual
More informationarxiv: v1 [cs.cv] 10 Apr 2017 Abstract
Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking Laura Leal-Taixé 1, Anton Milan 2, Konrad Schindler 3 Daniel Cremers 1 Ian Reid 2 Stefan Roth 4 1 Technical University
More information3D Object Representations for Recognition. Yu Xiang Computational Vision and Geometry Lab Stanford University
3D Object Representations for Recognition Yu Xiang Computational Vision and Geometry Lab Stanford University 1 2D Object Recognition Ren et al. NIPS15 Ordonez et al. ICCV13 Image classification/tagging/annotation
More informationOnline Multi-Object Tracking based on Hierarchical Association Framework
Online Multi-Object Tracking based on Hierarchical Association Framework Jaeyong Ju, Daehun Kim, Bonhwa Ku, Hanseok Ko School of Electrical Engineering Korea University Anam-dong, Seongbuk-gu, Seoul, Korea
More informationObject Detection by 3D Aspectlets and Occlusion Reasoning
Object Detection by 3D Aspectlets and Occlusion Reasoning Yu Xiang University of Michigan Silvio Savarese Stanford University In the 4th International IEEE Workshop on 3D Representation and Recognition
More informationarxiv: v1 [cs.cv] 20 Jun 2018
Improving Online Multiple Object tracking with Deep Metric Learning arxiv:1806.07592v1 [cs.cv] 20 Jun 2018 Michael Thoreau, Navinda Kottege Abstract Tracking by detection is a common approach to solving
More informationTowards the evaluation of reproducible robustness in tracking-by-detection
Towards the evaluation of reproducible robustness in tracking-by-detection Francesco Solera Simone Calderara Rita Cucchiara Department of Engineering Enzo Ferrari University of Modena and Reggio Emilia
More informationMulti-Object Tracking of Pedestrian Driven by Context
Multi-Object Tracking of Pedestrian Driven by Context Nguyen Thi Lan Anh Francois Bremond INRIA Sophia Antipolis 2004 Route des Lucioles -BP93 Sophia Antipolis Cedex, 06902 - France {thi-lan-anh.nguyen
More informationarxiv: v1 [cs.cv] 15 May 2016
Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association Based on Large-Scale Datasets arxiv:1605.04502v1 [cs.cv] 15 May 2016 Bing Wang, Kap Luk Chan,
More informationMulti-person Tracking by Multicut and Deep Matching
Multi-person Tracking by Multicut and Deep Matching Siyu Tang (B), Bjoern Andres, Mykhaylo Andriluka, and Bernt Schiele Max Planck Institute for Informatics, Saarbrücken Informatics Campus, Saarbrücken,
More informationMULTI-OBJECT tracking in real scenes is an important. Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association
1 Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association Bing Wang, Student Member, IEEE, Li Wang, Member, IEEE, Bing Shuai, Student Member, IEEE, Zhen Zuo, Student
More informationTowards Semantic Understanding of Surrounding Vehicular Maneuvers: A Panoramic Vision-Based Framework for Real-World Highway Studies
Towards Semantic Understanding of Surrounding Vehicular Maneuvers: A Panoramic Vision-Based Framework for Real-World Highway Studies Miklas S. Kristoffersen 1,2, Jacob V. Dueholm 1,2, Ravi K. Satzoda 2,
More informationLearning Optimal Parameters For Multi-target Tracking
WANG, FOWLKES: LEARNING MULTI-TARGET TRACKING 1 Learning Optimal Parameters For Multi-target Tracking Shaofei Wang shaofeiw@uci.edu Charless Fowlkes fowlkes@ics.uci.edu Dept of Computer Science University
More informationOnline Multi-Target Tracking Using Recurrent Neural Networks
Online Multi-Target Tracking Using Recurrent Neural Networks Anton Milan 1, S. Hamid Rezatofighi 1, Anthony Dick 1, Ian Reid 1 and Konrad Schindler 2 1 School of Computer Science, The University of Adelaide
More informationMULTIPLE OBJECT TRACKING BASED ON SPARSE GENERATIVE APPEARANCE MODELING. Dorra Riahi, Guillaume-Alexandre Bilodeau. LITIV Lab., Polytechnique Montréal
MULTIPLE OBJECT TRACKING BASED ON SPARSE GENERATIVE APPEARANCE MODELING Dorra Riahi, Guillaume-Alexandre Bilodeau LITIV Lab., Polytechnique Montréal ABSTRACT This paper addresses multiple object tracking
More informationTarget Tracking with Kalman Filtering, KNN and LSTMs
Target Tracking with Kalman Filtering, KNN and LSTMs Dan Iter daniter@stanford.edu Jonathan Kuck kuck@stanford.edu December 17, 2016 Philip Zhuang pzhuang@stanford.edu Abstract Tracking an unknown number
More informationRobust Global Tracker based on an Online Estimation of Tracklet Descriptor Reliability
Robust Global Tracker based on an Online Estimation of Tracklet Descriptor Reliability Nguyen Thi Lan Anh Chau Duc Phu Francois Bremond INRIA Sophia Antipolis 2004 Route des Lucioles -BP93 06902 Sophia
More informationJoint Tracking and Segmentation of Multiple Targets
Joint Tracking and Segmentation of Multiple Targets Anton Milan 1 Laura Leal-Taixé 2 Konrad Schindler 2 Ian Reid 1 1 University of Adelaide, Australia 2 Photogrammetry and Remote Sensing Group, ETH Zürich
More informationarxiv: v1 [cs.cv] 8 Jan 2017
Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies Amir Sadeghian, Alexandre Alahi, Silvio Savarese Stanford University {amirabs,alahi,ssilvio}@cs.stanford.edu arxiv:1701.01909v1
More informationMulti-Person Tracking-by-Detection based on Calibrated Multi-Camera Systems
Multi-Person Tracking-by-Detection based on Calibrated Multi-Camera Systems Xiaoyan Jiang, Erik Rodner, and Joachim Denzler Computer Vision Group Jena Friedrich Schiller University of Jena {xiaoyan.jiang,erik.rodner,joachim.denzler}@uni-jena.de
More informationOSMO: Online Specific Models for Occlusion in Multiple Object Tracking under Surveillance Scene
OSMO: Online Specific Models for Occlusion in Multiple Object Tracking under Surveillance Scene Xu Gao, Tingting Jiang National Engineering Laboratory for Video Technology, Cooperative Medianet Innovation
More informationMulti-Object Tracking with Quadruplet Convolutional Neural Networks
Multi-Object Tracking with Quadruplet Convolutional Neural Networks Jeany Son Mooyeol Baek Minsu Cho Bohyung Han Dept. of Computer Science and Engineering, POSTECH, Korea {jeany, mooyeol, mscho, bhhan}@postech.ac.kr
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 informationImproving Multi-Frame Data Association with Sparse Representations for Robust Near-Online Multi-Object Tracking
Improving Multi-Frame Data Association with Sparse Representations for Robust Near-Online Multi-Object Tracking Loïc Fagot-Bouquet 1, Romaric Audigier 1, Yoann Dhome 1, Frédéric Lerasle 2,3 1 CEA, LIST,
More informationarxiv: v1 [cs.cv] 19 Oct 2016
arxiv:1610.06136v1 [cs.cv] 19 Oct 2016 POI: Multiple Object Tracking with High Performance Detection and Appearance Feature Fengwei Yu 1,3 Wenbo Li 2,3 Quanquan Li 3 Yu Liu 3 Xiaohua Shi 1 Junjie Yan 3
More informationA Study of Vehicle Detector Generalization on U.S. Highway
26 IEEE 9th International Conference on Intelligent Transportation Systems (ITSC) Windsor Oceanico Hotel, Rio de Janeiro, Brazil, November -4, 26 A Study of Vehicle Generalization on U.S. Highway Rakesh
More informationPEDESTRIAN DETECTION IN CROWDED SCENES VIA SCALE AND OCCLUSION ANALYSIS
PEDESTRIAN DETECTION IN CROWDED SCENES VIA SCALE AND OCCLUSION ANALYSIS Lu Wang Lisheng Xu Ming-Hsuan Yang Northeastern University, China University of California at Merced, USA ABSTRACT Despite significant
More informationarxiv: v1 [cs.cv] 30 Aug 2016
arxiv:1608.08434v1 [cs.cv] 30 Aug 2016 Multi-Class Multi-Object Tracking using Changing Point Detection Byungjae Lee 1, Enkhbayar Erdenee 1, Songguo Jin 1, and Phill Kyu Rhee 1 Inha University 1 Abstract.
More informationActions Recognition in Crowd Based on Coarse-to-Fine Multi-Object Tracking
Actions Recognition in Crowd Based on Coarse-to-Fine Multi-Object Tracking Sixue Gong, Hu Han, Shiguang Shan, and Xilin Chen Key Lab of Intelligent Information Processing, Chinese Academy of Sciences (CAS),
More informationOcclusion Geodesics for Online Multi-Object Tracking
Occlusion Geodesics for Online Multi-Object Tracking Horst Possegger Thomas Mauthner Peter M. Roth Horst Bischof Institute for Computer Graphics and Vision, Graz University of Techlogy {possegger,mauthner,pmroth,bischof}@icg.tugraz.at
More informationarxiv: v1 [cs.cv] 9 Apr 2015
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor Wongun Choi NEC Laboratories America 8 N. Wolfe Rd, Cupertino, CA, USA arxiv:54.234v [cs.cv] 9 Apr 25 wongun@nec-labs.com Abstract
More informationPerceiving the 3D World from Images and Videos. Yu Xiang Postdoctoral Researcher University of Washington
Perceiving the 3D World from Images and Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World 3 Understand
More informationEnd-to-end Learning of Multi-sensor 3D Tracking by Detection
2018 IEEE International Conference on Robotics and Automation (ICRA) May 21-25, 2018, Brisbane, Australia End-to-end Learning of Multi-sensor 3D Tracking by Detection Davi Frossard 1 and Raquel Urtasun
More informationMOANA: An Online Learned Adaptive Appearance Model for Robust Multiple Object Tracking in 3D
MOANA: An Online Learned Adaptive Appearance Model for Robust Multiple Object Tracking in 3D Zheng Tang 1, Student Member, and Jenq-Neng Hwang 1, Fellow, IEEE 1 Department of Electrical and Computer Engineering,
More informationMulti-object Tracking with Neural Gating Using Bilinear LSTM
Multi-object Tracking with Neural Gating Using Bilinear LSTM Chanho Kim 1, Fuxin Li 2, and James M. Rehg 1 1 Center for Behavioral Imaging Georgia Institute of Technology, Atlanta GA, USA {chkim, rehg}@gatech.edu
More informationTracklet Association with Online Target-Specific Metric Learning
racklet Association with Online arget-specific Metric Learning Bing Wang, Gang Wang, Kap Luk Chan, Li Wang School of Electrical and Electronic Engineering, Nanyang echnological University 50 Nanyang Avenue,
More informationCan appearance patterns improve pedestrian detection?
IEEE Intelligent Vehicles Symposium, June 25 (to appear) Can appearance patterns improve pedestrian detection? Eshed Ohn-Bar and Mohan M. Trivedi Abstract This paper studies the usefulness of appearance
More informationRobust False Positive Detection for Real-Time Multi-Target Tracking
Robust False Positive Detection for Real-Time Multi-Target Tracking Henrik Brauer, Christos Grecos, and Kai von Luck University of the West of Scotland University of Applied Sciences Hamburg Henrik.Brauer@HAW-Hamburg.de
More informationarxiv: v1 [cs.cv] 29 Jun 2018
End-to-end Learning of Multi-sensor 3D Tracking by Detection Davi Frossard Raquel Urtasun Uber Advanced Technologies Group University of Toronto {frossard, urtasun}@uber.com arxiv:1806.11534v1 [cs.cv]
More informationRobust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning
Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning Seung-Hwan Bae and Kuk-Jin Yoon Computer Vision Laboratory, GIST, Korea {bshwan, kjyoon}@gist.ac.kr
More informationDeep Network Flow for Multi-Object Tracking
Deep Network Flow for Multi-Object Tracking Samuel Schulter Paul Vernaza Wongun Choi Manmohan Chandraker NEC Laboratories America, Media Analytics Department Cupertino, CA, USA {samuel,pvernaza,wongun,manu}@nec-labs.com
More informationImproving Object Tracking by Adapting Detectors
Improving Object Tracking by Adapting Detectors Lu Zhang Laurens van der Maaten Vision Lab, Delft University of Technology, The Netherlands Email: {lu.zhang, l.j.p.vandermaaten}@tudelft.nl Abstract The
More informationMulti-Perspective Vehicle Detection and Tracking: Challenges, Dataset, and Metrics
IEEE 19th International Conference on Intelligent Transportation Systems (ITSC) Windsor Oceanico Hotel, Rio de Janeiro, Brazil, November 1-, Multi-Perspective Vehicle Detection and Tracking: Challenges,
More informationTracking The Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies
Tracking The Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies Amir Sadeghian 1, Alexandre Alahi 2, Silvio Savarese 1 1 Stanford University 2 Ecole Polytechnique Federale de Lausanne
More informationAn Analytical Formulation of Global Occlusion Reasoning for Multi-Target Tracking
An Analytical Formulation of Global Occlusion Reasoning for Multi-Target Tracking Anton Andriyenko 1 Stefan Roth 1 Konrad Schindler 2 1 Department of Computer Science, TU Darmstadt, Germany 2 Photogrammetry
More information3D Object Detection and Pose Estimation. Yu Xiang University of Michigan 1st Workshop on Recovering 6D Object Pose 12/17/2015
3D Object Detection and Pose Estimation Yu Xiang University of Michigan 1st Workshop on Recovering 6D Object Pose 12/17/2015 1 2D Object Detection 2 2D detection is NOT enough! 3 Applications that need
More informationarxiv: v2 [cs.cv] 3 Apr 2017
Tracking The Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies mir Sadeghian, lexandre lahi, Silvio Savarese Stanford University {amirabs,alahi,ssilvio}@cs.stanford.edu arxiv:1701.01909v2
More informationarxiv: v1 [cs.cv] 5 Oct 2016
Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions Shaofei Wang Charless C. Fowlkes arxiv:60.0394v [cs.cv] 5 Oct 206 Abstract We describe an end-to-end framework for learning
More informationarxiv: v1 [cs.cv] 18 Jan 2019
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification Weitao Feng 1 Zhihao Hu 1,2 Wei Wu 1 Junjie Yan 1 Wanli Ouyang 3 arxiv:1901.06129v1 [cs.cv] 18 Jan 2019 1 Sensetime Group Limited
More informationTowards Robust Visual Object Tracking: Proposal Selection & Occlusion Reasoning Yang HUA
Towards Robust Visual Object Tracking: Proposal Selection & Occlusion Reasoning Yang HUA PhD Defense, June 10 2016 Rapporteur Rapporteur Examinateur Examinateur Directeur de these Co-encadrant de these
More informationMulti-Object Tracking Based on Tracking-Learning-Detection Framework
Multi-Object Tracking Based on Tracking-Learning-Detection Framework Songlin Piao, Karsten Berns Robotics Research Lab University of Kaiserslautern Abstract. This paper shows the framework of robust long-term
More informationVisual Multiple-Object Tracking for Unknown Clutter Rate
THIS PAPER IS A PREPRINT OF A PAPER SUBMITTED TO IET COMPUTER VISION. IF ACCEPTED, THE COPY OF RECORD WILL BE AVAILABLE AT THE IET DIGITAL LIBRARY1 Visual Multiple-Object Tracking for Unknown Clutter Rate
More informationarxiv: v3 [cs.cv] 21 Sep 2015
Noname manuscript No. (will be inserted by the editor) Multiple Object Tracking: A Literature Review Wenhan Luo 1 Junliang Xing 2 Xiaoqin Zhang 3 Xiaowei Zhao 1 Tae-Kyun Kim 1 arxiv:1409.7618v3 [cs.cv]
More informationRobustifying the Flock of Trackers
1-Feb-11 Matas, Vojir : Robustifying the Flock of Trackers 1 Robustifying the Flock of Trackers Tomáš Vojíř and Jiří Matas {matas, vojirtom}@cmp.felk.cvut.cz Department of Cybernetics, Faculty of Electrical
More informationLearning an image-based motion context for multiple people tracking
Learning an image-based motion context for multiple people tracking Laura Leal-Taix e1,2, Michele Fenzi2, Alina Kuznetsova2, Bodo Rosenhahn2, and Silvio Savarese3 1 2 Photogrammetry and Remote Sensing,
More informationBeyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking
Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking by Sarthak Sharma, Junaid Ahmed Ansari, Krishna Murthy J, Madhava Krishna in International Conference on Robotics and
More informationBOP: Benchmark for 6D Object Pose Estimation
BOP: Benchmark for 6D Object Pose Estimation Hodan, Michel, Brachmann, Kehl, Buch, Kraft, Drost, Vidal, Ihrke, Zabulis, Sahin, Manhardt, Tombari, Kim, Matas, Rother 4th International Workshop on Recovering
More informationGMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs Amir Roshan Zamir, Afshin Dehghan, and Mubarak Shah UCF Computer Vision Lab, Orlando, FL 32816, USA Abstract. Data association
More informationGMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs Amir Roshan Zamir, Afshin Dehghan, and Mubarak Shah UCF Computer Vision Lab, Orlando, FL 32816, USA Abstract. Data association
More informationTracking Multiple People Online and in Real Time
Tracking Multiple People Online and in Real Time Ergys Ristani, Carlo Tomasi Duke University Abstract. We cast the problem of tracking several people as a graph partitioning problem that takes the form
More informationAutomatic Parameter Adaptation for Multi-Object Tracking
Automatic Parameter Adaptation for Multi-Object Tracking Duc Phu CHAU, Monique THONNAT, and François BREMOND {Duc-Phu.Chau, Monique.Thonnat, Francois.Bremond}@inria.fr STARS team, INRIA Sophia Antipolis,
More informationPersistent Tracking for Wide Area Aerial Surveillance
Persistent Tracking for Wide Area Aerial Surveillance Jan Prokaj J Gradient Ge rard Medioni University of Southern California jan@jgradient.com medioni@usc.edu Abstract Persistent surveillance of large
More informationExploring Local Context for Multi-target Tracking in Wide Area Aerial Surveillance
2017 IEEE Winter Conference on Applications of Computer Vision Exploring Local Context for Multi-target Tracking in Wide Area Aerial Surveillance Bor-Jeng Chen University of Southern California borjengc@usc.edu
More informationA data set for evaluating the performance of multi-class multi-object video tracking
A data set for evaluating the performance of multi-class multi-object video tracking Avishek Chakraborty a, Victor Stamatescu a, Sebastien C. Wong b, Grant Wigley a, David Kearney a a Computational Learning
More informationarxiv: v1 [cs.cv] 28 Mar 2016
arxiv:1603.08592v1 [cs.cv] 28 Mar 2016 Exploring Local Context for Multi-target Tracking in Wide Area Aerial Surveillance Bor-Jeng Chen and Gérard Medioni University of Southern California {borjengc, medioni}@usc.edu
More informationUnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss AAAI 2018, New Orleans, USA Simon Meister, Junhwa Hur, and Stefan Roth Department of Computer Science, TU Darmstadt 2 Deep
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 informationFollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation
FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation Philip Lenz Karlsruhe Institute of Technology lenz@kit.edu Andreas Geiger MPI Tübingen andreas.geiger@tue.mpg.de Raquel
More informationLearning to Divide and Conquer for Online Multi-Target Tracking
Learning to Divide and Conquer for Online Multi-Target Tracing Francesco Solera Simone Calderara Rita Cucchiara Department of Engineering University of Modena and Reggio Emilia name.surname@unimore.it
More informationDeep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Supplementary Material
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Supplementary Material Chi Li, M. Zeeshan Zia 2, Quoc-Huy Tran 2, Xiang Yu 2, Gregory D. Hager, and Manmohan Chandraker 2 Johns
More informationReal Time Person Detection and Tracking by Mobile Robots using RGB-D Images
Real Time Person Detection and Tracking by Mobile Robots using RGB-D Images Duc My Vo, Lixing Jiang and Andreas Zell Abstract Detecting and tracking humans are key problems for human-robot interaction.
More informationCustomized Multi-Person Tracker
Customized Multi-Person Tracker Liqian Ma 1 Siyu Tang 2,3 Michael J. Black 2 Luc Van Gool 1,4 1 KU-Leuven/PSI, TRACE (Toyota Res in Europe) {liqian.ma, luc.vangool}@esat.kuleuven.be 2 Max Planck Institute
More informationHypergraphs for Joint Multi-View Reconstruction and Multi-Object Tracking
2013 IEEE Conference on Computer Vision and Pattern Recognition Hypergraphs for Joint Multi-View Reconstruction and Multi-Object racking Martin Hofmann 1, Daniel Wolf 1,2, Gerhard Rigoll 1 1 Institute
More information3D Object Recognition and Scene Understanding from RGB-D Videos. Yu Xiang Postdoctoral Researcher University of Washington
3D Object Recognition and Scene Understanding from RGB-D Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World
More informationGMMCP Tracker: Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking
GMMCP without ADN GMMCP Tracker: Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking Afshin Dehghan Shayan Modiri Assari Mubarak Shah Center for Research in Computer
More informationThe Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking Dawei Du 1[0000 0001 9404 524X], Yuankai Qi 2[0000 0003 4312 5682], Hongyang Yu 2[0000 0003 0036 531X], Yifan Yang 1[0000 0003 1455
More informationDense Tracking and Mapping for Autonomous Quadrocopters. Jürgen Sturm
Computer Vision Group Prof. Daniel Cremers Dense Tracking and Mapping for Autonomous Quadrocopters Jürgen Sturm Joint work with Frank Steinbrücker, Jakob Engel, Christian Kerl, Erik Bylow, and Daniel Cremers
More informationarxiv: v1 [cs.ro] 5 Jan 2019
IEEE ROBOTICS AND AUTOMATION LETTERS. PREPRINT VERSION. ACCEPTED JANUARY, 209 The Oxford Multimotion Dataset: Multiple SE(3) Motions with Ground Truth arxiv:90.0445v [cs.ro] 5 Jan 209 Kevin M. Judd and
More informationHidden Hands: Tracking Hands with an Occlusion Aware Tracker
Hidden Hands: Tracking Hands with an Occlusion Aware Tracker Akshay Rangesh, Eshed Ohn-Bar, and Mohan M. Trivedi Computer Vision and Robotics Research Lab University of California, San Diego La Jolla,
More informationClose-Range Human Detection for Head-Mounted Cameras
D. MITZEL, B. LEIBE: CLOSE-RANGE HUMAN DETECTION FOR HEAD CAMERAS Close-Range Human Detection for Head-Mounted Cameras Dennis Mitzel mitzel@vision.rwth-aachen.de Bastian Leibe leibe@vision.rwth-aachen.de
More informationOnline Multi-Object Tracking with Dual Matching Attention Networks
Online Multi-Object Tracking with Dual Matching Attention Networks Ji Zhu 1,2, Hua Yang 1, Nian Liu 3, Minyoung Kim 4, Wenjun Zhang 1, and Ming-Hsuan Yang 5,6 1 Shanghai Jiao Tong University 2 Visbody
More information[Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors
[Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors Junhyug Noh Soochan Lee Beomsu Kim Gunhee Kim Department of Computer Science and Engineering
More informationComparative analysis of multiple target tracking methods
International Journal of Advances in Intelligent Informatics ISSN: 2442-6571 Vol 2, No 2, July 2016, pp. 65-76 65 Comparative analysis of multiple target tracking methods Michael Kamara Devadoss a,1,*,
More informationOnline Object Tracking with Proposal Selection. Yang Hua Karteek Alahari Cordelia Schmid Inria Grenoble Rhône-Alpes, France
Online Object Tracking with Proposal Selection Yang Hua Karteek Alahari Cordelia Schmid Inria Grenoble Rhône-Alpes, France Outline 2 Background Our approach Experimental results Summary Background 3 Tracking-by-detection
More informationJoint Vanishing Point Extraction and Tracking. 9. June 2015 CVPR 2015 Till Kroeger, Dengxin Dai, Luc Van Gool, Computer Vision ETH Zürich
Joint Vanishing Point Extraction and Tracking 9. June 2015 CVPR 2015 Till Kroeger, Dengxin Dai, Luc Van Gool, Computer Vision Lab @ ETH Zürich Definition: Vanishing Point = Intersection of 2D line segments,
More informationNon-Markovian Globally Consistent Multi-Object Tracking
Non-Markovian Globally onsistent Multi-Object Tracking Supplementary Material Andrii Maksai 1, Xinchao Wang 2, François Fleuret 3, and Pascal Fua 1 1 omputer Vision Laboratory, EPFL, Lausanne, Switzerland,
More informationLatent Data Association: Bayesian Model Selection for Multi-target Tracking
2013 IEEE International Conference on Computer Vision Latent Data Association: Bayesian Model Selection for Multi-target Tracking Aleksandr V. Segal Department of Engineering Science, University of Oxford
More informationSocial Robotics Seminar
SS 2015 Social Robotics Seminar Welcome! Prof. Kai Arras Timm Linder, Billy Okal, Luigi Palmieri 1 SS 2015 Social Robotics Seminar Contents Brief presentation of the Social Robotics Lab Introduction How
More informationGrant agreement no: FP SPENCER: Project start: April 1, 2013 Duration: 3 years XXXXXXXXXXDELIVERABLE 2.1XXXXXXXXXX
Grant agreement no: FP7-600877 SPENCER: Social situation-aware perception and action for cognitive robots Project start: April 1, 2013 Duration: 3 years XXXXXXXXXXDELIVERABLE 2.1XXXXXXXXXX People detection
More information