多目标跟踪总结(下)-资源汇总

导言

本文主要收集MOT领域的一些资源，包括数据集，相关论文以及部分开源代码等。

Dataset

Dataset	MultiView	Groundtruth	Site
PETS2006	$\checkmark$	$\times$	www.cvg.rdg.ac.uk/PETS2006/data.html
PETS2007	$\checkmark$	$\checkmark$	http://www.cvg.reading.ac.uk/PETS2007/
PETS2009	$\checkmark$	$\checkmark$	www.cvg.rdg.ac.uk/PETS2009/a.html
CAVIAR	$\checkmark$	$\checkmark$	http://groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/
TUD	$\times$	$\checkmark$	www.d2.mpi-inf.mpg.de/datasets
TRECVID	$\checkmark$	$\times$	http://www-nlpir-nist.gov/projects/
Caltech Pedestrian	$\times$	$\checkmark$	www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/
UBC Hockey	$\times$	$\times$	www.cs.ubc.ca/~okumak/research.html
AVSS 2007	$\times$	$\checkmark$	www.eecs.qmul.ac.uk/~andrea/avss2007_d.html
ETH pedestrian	$\checkmark$	$\checkmark$	www.vision.ee.ethz.ch/~aess/dataset/
ETHZ Central	$\times$	$\checkmark$	www.vision.ee.ethz.ch/datasets
Town Centre	$\times$	$\checkmark$	www.robots.ox.ac.uk/ActiveVision/Research/Projects/2009bbenfold_headpose/project.htnl#datasets
Zara	$\times$	$\times$	https://graphics.cs.ucy.ac.cy/research/downloads/crowd-data
UCSD	$\times$	$\times$	http://www.svcl.ucsd.edu/projects/anomaly/dataset.htm
UCF Crowds	$\times$	$\times$	www.crcv.ucf.edu/data/crowd.php
KITTI	$\times$	$\checkmark$	http://www.cvlibs.net/datasets/kitti/eval_tracking.php
MOT2015	$\times$	$\checkmark$	https://motchallenge.net/data/2D_MOT_2015/
MOT2016	$\times$	$\checkmark$	https://motchallenge.net/data/MOT16/
MOT2017	$\times$	$\checkmark$	https://motchallenge.net/data/MOT17/
MOT2019	$\times$	$\checkmark$	https://motchallenge.net/data/CVPR_2019_Tracking_Challenge/

目前多目标跟踪主要使用的数据集是MOTChallenge数据集，包括MOT15， MOT16， MOT17和MOT19.

Papers

Evaluation Metric

CLEAR MOT : Bernardin, K. & Stiefelhagen, R. “Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metric” paper

IDF1: Ristani, E., Solera, F., Zou, R., Cucchiara, R. & Tomasi, C. “Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking” paper

MTMCT Ristani, E., Solera, F., Zou, R. S., Cucchiara, R., & Tomasi, C. (2016). Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. paper

MOT15: Leal-Taixé L, Milan A, Reid I, et al. Motchallenge 2015: Towards a benchmark for multi-target tracking . paper

MOT16 : Milan A, Leal-Taixé L, Reid I, et al. MOT16: A benchmark for multi-object tracking. paper

Evaluation Code: matlab, python

Overview

Emami, P., Pardalos, P. M., Elefteriadou, L., & Ranka, S. (2018). Machine Learning Methods for Solving Assignment Problems in Multi-Target Tracking, 1(1), 1–35. paper

Leal-Taixé, L., Milan, A., Schindler, K., Cremers, D., Reid, I., & Roth, S. (2017). Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking. paper

Luo, W., Xing, J., Milan, A., Zhang, X., Liu, W., Zhao, X., & Kim, T.-K. (2014). Multiple Object Tracking: A Literature Review, 1–18. paper

Li, X., Hu, W., Shen, C., Zhang, Z., & Dick, A. (2013). A Survey of Appearance Models in Visual Object Tracking, 1–42. paper

Poore, A. B., & Gadaleta, S. (2006). Some assignment problems arising from multiple target tracking, 43, 1074–1091. paper

Yilmaz, A., & Javed, O. (2006). Object Tracking : A Survey, 38(4). paper

A 101 slide . paper

2019

NT: Longyin Wen, Dawei Du, Shengkun Li, Xiao Bian, Siwei Lyu Learning Non-Uniform Hypergraph for Multi-Object Tracking, In AAAI 2019. paper

FMA: Zhang, J., Zhou, S., Wang, J., & Huang, D. (2019). Frame-wise Motion and Appearance for Real-time Multiple Object Tracking, (1). paper

STRN: Xu, J., Cao, Y., Zhang, Z., & Hu, H. (2019). Spatial-Temporal Relation Networks for Multi-Object Tracking. paper

LSST: Feng, W., Hu, Z., Wu, W., Yan, J., & Ouyang, W. (2019). Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification. paper

MOTS: Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B. B. G., Geiger, A., & Leibe, B. (2019). MOTS: Multi-Object Tracking and Segmentation. paper

FAMNet: Chu, P., & Ling, H. (2019). FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking. paper

FANTrack: Baser, E., Balasubramanian, V., Bhattacharyya, P., & Czarnecki, K. (2019). FANTrack: 3D Multi-Object Tracking with Feature Association Network. paper, code

IATracker: Chu, P., Fan, H., Tan, C. C., & Ling, H. (2019). Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment. paper

2018

SST: Sun. S., Akhtar, N., Song, H., Mian A., & Shah M. (2018). Deep Affinity Network for Multiple Object Tracking. paper, code

CCC: Keuper, M., Tang, S., Andres, B., Brox, T., & Schiele, B. (2018). Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8828(c), 1–13. paper

HAF: Sheng, H., Zhang, Y., Chen, J., Xiong, Z., & Zhang, J. (2018). Heterogeneous Association Graph Fusion for Target Association in Multiple Object Tracking. IEEE Transactions on Circuits and Systems for Video Technology. paper

TNT: Wang, G., Wang, Y., Zhang, H., Gu, R., & Hwang, J.-N. (2018). Exploit the Connectivity: Multi-Object Tracking with TrackletNet. paper

PHD: Fang, K., Xiang, Y., Li, X., & Savarese, S. (2018). Recurrent Autoregressive Networks for Online Multi-Object Tracking. WACV. paper

DMAN: Zhu, Ji and Yang, Hua and Liu, Nian and Kim, Minyoung and Zhang, Wenjun and Yang, Ming-Hsuan “Online Multi-Object Tracking with Dual Matching Attention Networks” paper

C-DRL: Ren, Liangliang and Lu, Jiwen and Wang, Zifeng and Tian, Qi and Zhou, Jie “Collaborative Deep Reinforcement Learning for Multi-Object Tracking” paper

SADF: Yoon, Y., Boragule, A., Song, Y., Yoon, K., & Jeon, M. (2018). Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering. paper

MOTDT: Long Chen, Haizhou Ai “Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identification” in ICME 2018. paper, code

DeepCC: Ristani and C. Tomasi “Features for Multi-Target Multi-Camera Tracking and Re-Identification” In CVPR 2018 paper, code

THOPA-net: Fabbri, M., Lanzi, F., Calderara, S., & Vezzani, R. (2018). Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World. paper

MHT-bLSTM: Kim, Chanho and Li, Fuxin and Rehg, James M “Multi-object Tracking with Neural Gating Using Bilinear LSTM” . paper

Trajectory Factory: Cong Ma, Changshui Yang, Fan Yang, Yueqing Zhuang, Ziwei Zhang, Huizhu Jia, Xiaodong Xie “Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking” In ICME 2018. paper

MOTBeyondPixels: Sarthak Sharma, Junaid Ahmed Ansari, J. Krishna Murthy, and K. Madhava Krishna Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking In ICRA 2018 paper, code

Henschel, R., Leal-Taixe, L., Cremers, D., & Rosenhahn, B. (2018). Fusion of head and full-body detectors for multi-object tracking. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2018–June, 1509–1518. paper

Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes “Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking” In WACV 2018. paper

2017

D2T: Feichtenhofer, C., Pinz, A., & Zisserman, A. (2017). Detect to Track and Track to Detect. In ICCV2017. paper, code

IOU: Bochinski, E., Eiselein, V., & Sikora, T. (2017). High-Speed tracking-by-detection without using image information. AVSS 2017. paper, code

CIWT: Aljosa Osep, Alexander Hermans Combined Image and World-Space Tracking in Traffic Scenes. In ICRA 2017. paper, code

RCMSS: Naiel, M. A., Ahmad, M. O., Swamy, M. N. S., Lim, J., & Yang, M. H. (2017). Online multi-object tracking via robust collaborative model and sample selection. In CVIU 2017. paper, code

EAMTT: Tang, S., Andriluka, M., Andres, B., & Schiele, B. (2017). Multiple people tracking by lifted multicut and person re-identification. In CVPR 2017. paper

STAM: Chu, Q., Ouyang, W., Li, H., Wang, X., Liu, B., & Yu, N. (2017). Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism. In ICCV2017. paper

DeepSORT: Wojke, N., Bewley, A., & Paulus, D. (2017). Simple Online and Realtime Tracking with a Deep Association Metric. In ICIP2017. paper, code

Quad-CNN: Son, J., Baek, M., Cho, M., & Han, B. (2017). Multi-object tracking with quadruplet convolutional neural networks. In CVPR2017. paper

Art-Tracker: Eldar Insafutdinov, Mykhaylo Andriluka, Leonid Pishchulin, Siyu Tang, Evgeny Levinkov, Bjoern Andres, Bernt Schiele “Art Track: Articulated Multi-Person Tracking in the Wild” In CVPR2017. paper

SOTforMOT: He, Q., Wu, J., Yu, G., & Zhang, C. (2017). SOT for MOT. paper

NMGC-MOT: Maksai, A., Wang, X., Fleuret, F., & Fua, P. (2017). Non-Markovian Globally Consistent Multi-Object Tracking. In ICCV2017. paper , code

RNN_LSTM: Milan, A., Rezatofighi, S. H., Dick, A., Reid, I., & Schindler, K. (2017). Online Multi-Target Tracking Using Recurrent Neural Networks. AAAI 2017. paper, code

ReidTracking: Beyer, L., Breuers, S., Kurin, V., & Leibe, B. (2017). Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters. paper, code

DeepNetworkFlows: Schulter, S., Vernaza, P., Choi, W., & Chandraker, M. (2017). Deep network flow for multi-object tracking. In CVPR 2017. paper

Sadeghian, A., Alahi, A., & Savarese, S. (2017). Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies. In ICCV2017. paper

2016

CPD: Lee, B., Erdenee, E., Jin, S., & Rhee, P. K. (2016). Multi-Class Multi-Object Tracking using Changing Point Detection. paper

POI : Yu, F., Li, W., Li, Q., Liu, Y., Shi, X., & Yan, J. (2016). POI: Multiple Object Tracking with High Performance Detection and Appearance Feature. In BMTT 2016. paper, detections

SORT: Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016). Simple online and realtime tracking. In ICIP 2016. paper, code

RCMSS : Mohamed A. Naiel1, M. Omair Ahmad, M.N.S. Swamy, Jongwoo Lim, and Ming-Hsuan Yang “Online Multi-Object Tracking Via Robust Collaborative Model and Sample Selection. In CVIU2016. paper, code

Social-LSTM: Goel, K., Fei-Fei, L., Savarese, S., Alahi, A., Robicquet, A., & Ramanathan, V. (2016). Social LSTM: Human Trajectory Prediction in Crowded Spaces. In CVPR2016. paper,

2015

MDP: Xiang, Y., Alahi, A., & Savarese, S. (2015). Learning to Track: Online Multi-object Tracking by Decision Making. In ICCV2015. paper, code

CEM: Chari, V., Lacoste-Julien, S., Laptev, I., & Sivic, J. (2014). On Pairwise Costs for Network Flow Multi-Object Tracking. In CVPR2015. paper, code

ALFD: Choi, W. (2015). Near-online multi-target tracking with aggregated local flow descriptor. In ICCV2015. paper

LDCT: Solera, F. (2015). Learning to Divide and Conquer for Online Multi-Target Tracking. In ICCV 2105. paper, code

TMPORT: Ristani, E., & Tomasi, C. (2015). Tracking multiple people online and in real time. paper, code

JPDArevisited: Rezatofighi, S. H., Milan, A., Zhang, Z., Shi, Q., Dick, A., & Reid, I. (2015). Modified Joint Probabilistic Data Association. In ICCV2015. paper

MHTrevisited: Vinet, L., & Zhedanov, A. (2015). Multiple Hypothesis Tracking Revisited. In ICCV2015. paper, code

headTracking: Zhang, S., Wang, J., Wang, Z., Gong, Y., & Liu, Y. (2015). Multi-target tracking by learning local-to-global trajectory models. In PR, 48(2), 580-590. paper, code

2014

H2T: Wen, L., Li, W., Yan, J., Lei, Z., Yi, D., & Li, S. Z. (2014). Multiple target tracking based on undirected hierarchical relation hypergraph. In CSC on CVPR2014. paper, code

CMOT: Bae, S. H., & Yoon, K. J. (2014). Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. In CSC on CVPR2014. paper, code

OPCNF: Chari, V., Lacoste-Julien, S., Laptev, I., & Sivic, J. (2014). Continuous Energy Minimization for Multi-Target Tracking, TPAMI 2014. paper, code

Tang, S., Andriluka, M., & Schiele, B. (2014). Detection and tracking of occluded people. IJCV, 110(1), 58–69. paper

Yang, B., & Nevatia, R. (2014). Multi-target tracking by online learning a CRF model of appearance and motion patterns. IJCV, 107(2), 203–217. paper

2013

SMOT: Dicle, C., Camps, O. I., & Sznaier, M. (2013). The way they move: Tracking multiple targets with similar appearance. In ICCV2013. paper,, code

Milan, A., Schindler, K., & Roth, S. (2013). Detection- and trajectory-level exclusion in multiple object tracking. In CSC on CVPR2013. paper

Salvi, D., Waggoner, J., Temlyakov, A., & Wang, S. (2013). A graph-based algorithm for multi-target tracking with occlusion. In WACV 2013. paper

2012

GMCP-Tracker: Zamir, A. R., Dehghan, A., & Shah, M. (2012). GMCP-Tracker : Global Multi-object Tracking Using Generalized Minimum Clique Graphs, 343–356. paper, code

OMPTTH: Zhang, J., Lo Presti, L., & Sclaroff, S. (2012). Online multi-person tracking by tracker hierarchy. In AVSS 2012. paper, code

Yan, X., Wu, X., Kakadiaris, I. A., & Shah, S. K. (2012). To Track or To Detect ? An Ensemble Framework for Optimal Selection, 594–607. paper

Hu, W., Li, X., Luo, W., Zhang, X., Maybank, S., & Zhang, Z. (2012). Single and multiple object tracking using log-euclidean riemannian subspace and block-division appearance model. PAMI, 34(12), 2420-2440. paper

Yang, B., & Nevatia, R. (2012). Online learned discriminative part-based appearance models for multi-human tracking. In ECCV 2012. paper

Shu, G., Dehghan, A., Oreifej, O., Hand, E., & Shah, M. (2012). Part-based multiple-person tracking with partial occlusion handling. In CSC on CVPR2012. paper

2011 and Before

KSP: Berclaz. (2011). Multiple Object Tracking using K-shortes Paths. PAMI2011. paper, code

MTDF: Pedro F. Felzenszwalb, Ross B. Girshick, D. M. and D. R. (2010). Object detection with discriminatively trained part-based models. in TPAMI 2010. paper

Andriyenko, A., Roth, S., & Schindler, K. (2011). An analytical formulation of global occlusion reasoning for multi-target tracking. ICCV 2011. paper

Andriyenko, A., & Schindler, K. (2011). Multi-target tracking by continuous energy minimization. In CVPR 2011. paper

Pirsiavash, H., Ramanan, D., & Fowlkes, C. (2011). Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. CVPR2011. paper

Mitzel, D., Horbert, E., Ess, A., & Leibe, B. (2010). Multi-person tracking with sparse detection and continuous segmentation. ECCV2010. paper

Hu, M., Ali, S., & Shah, M. Detecting global motion patterns in complex videos. ICPR2008. paper

Breitenstein, M. D., Reichlin, F., Leibe, B., Koller-Meier, E., & Van Gool, L. (2009). Robust tracking-by-detection using a detector confidence particle filter. ICCV2009. paper

Zhang, L., Li, Y., & Nevatia, R. (2008). Global data association for multi-object tracking using network flows. CVPR2008. paper

Other resources

SpyderXu, github , github