代码整洁之道 clean code pdf_多目标跟踪MOT相关论文和代码资源列表

​ 这段时间在整理毕设，所以这里结合了SpyderXu 分享的内容把多目标跟踪相关的文献资源共享一下，由于文章很多，所以我这里只整理3年以内的，对于年限久远的，这里只取提供了代码的和比较经典的。各自算法的性能比较可以看论文以及MOT官网。由于知乎不支持表格，所以具体见我的博客或github（提供了算法在MOT数据集上的简称以及期刊会议名称）。关于最新的论文，我会优先在github上更新，知乎不提供markdown表格，很麻烦。

以下每栏内容为：文章名、文章和代码链接、文章发布位置（期刊会议）、文章对应简称。当前MOT数据集上排名靠前的都加粗了。（收藏的同时别忘了点赞哦~）

在线跟踪（Online)

1. DeepMOT:A Differentiable Framework for Training Multiple Object Trackers |[pdf] [code] | CVPR2020 | DeepMOT
2. Online multiple pedestrian tracking using deep temporal appearance matching association | [pdf] [code] | arXiv(2019) | DD_TAMA19
3. Spatial-temporal relation networks for multi-object tracking | [pdf] | ICCV2019 | STRN
4. Towards Real-Time Multi-Object Tracking | [pdf] [code] | arXiv(2019) | JDE(private)
5. Multi-object tracking with multiple cues and switcher-aware classification | [pdf] | arXiv(2019) | LSST
6. FAMNet: Joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking | [pdf] | ICCV2019 | FAMNet
7. Online multi-object tracking with instance-aware tracker and dynamic model refreshment | [pdf] | WACV2019 | KCF
8. Tracking without bells and whistles | [pdf] [code] | ICCV2019 | Tracktor
9. Deep affinity network for multiple object tracking | [pdf][code] | PAMI(2019) | DAN
10. MOTS: Multi-Object Tracking and Segmentation | [pdf] [code] | CVPR2019 | Track R-CNN
11. Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking | [pdf] | CVPR2019 | SAS_MOT17
12. Recurrent autoregressive networks for online multi-object tracking | [pdf] | WACV2018 | RAN
13. Real-time multiple people tracking with deeply learned candidate selection and person re-identification | [pdf] [code] | ICME2018 | MOTDT
14. Online multi-object tracking with dual matching attention networks | [pdf] [code] | ECCV2018 | DMAN
15. Extending IOU Based Multi-Object Tracking by Visual Information | [pdf] [code] | AVSS2018 | V-IOU
16. Online Multi-target Tracking using Recurrent Neural Networks | [pdf] [code] | AAAI2017 | MOT-RNN
17. Detect to Track and Track to Detect | [pdf] [code] | ICCV2017 | D&T(private)
18. Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism | [pdf] | ICCV2017 | STAM
19. Tracking the untrackable: Learning to track multiple cues with long-term dependencies | [pdf] | ICCV2017 | AMIR
20. Simple online and realtime tracking with a deep association metric | [pdf] [code] | ICIP2017 | DeepSort
21. High-speed tracking-by-detection without using image information | [pdf] [code] | AVSS2017 | IOU Tracker
22. Simple online and realtime tracking | [pdf] [code] | ICIP2016 | Sort
23. Temporal dynamic appearance modeling for online multi-person tracking | [pdf] | CVIU(2016) | TDAM
24. Online multi-object tracking via structural constraint event aggregation | [pdf] | CVPR2016 |SCEA
25. Online Multi-Object Tracking Via Robust Collaborative Model and Sample Selection | [pdf] [code] | CVIU2016 | RCMSS
26. Learning to Track: Online Multi-Object Tracking by Decision Making | [pdf] [code] | ICCV2015 | MDP
27. Learning to Divide and Conquer for Online Multi-Target Tracking | [pdf][code] | ICCV2015 | LDCT
28. Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning | [pdf] [code] | CVPR2014 | CMOT
29. The Way They Move: Tracking Targets with Similar Appearance | [pdf] [code] | ICCV2013 | SMOT
30. Online Multi-Person Tracking by Tracker Hierarchy | [pdf] [code] | AVSS2012 | OMPTTH

离线跟踪（Batch)

1. Learning non-uniform hypergraph for multi-object tracking | [pdf] | AAAI2019 | NT
2. Learning a Neural Solver for Multiple Object Tracking | [pdf] [code] | CVPR2020 | MPNTracker
3. Deep learning of graph matching | [pdf] | CVPR2018
4. muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking | [pdf] [code] | NIPS(2019) | muSSP
5. Exploit the connectivity: Multi-object tracking with trackletnet | [pdf] [code] | ACM mm 2019 | TNT(eTC)
6. Multiple people tracking using body and joint detections | [pdf] | CVPRW2019 | JBNOT
7. Aggregate Tracklet Appearance Features for Multi-Object Tracking | [pdf] | SPL(2019) | NOTA
8. Customized multi-person tracker | [pdf] | ACCV2018 | HCC
9. Multi-object tracking with neural gating using bilinear lstm |[pdf] | ECCV2018 | MHT_bLSTM
10. Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking | [pdf] | ICME2018 |GCRE
11. Multiple People Tracking with Lifted Multicut and Person Re-identification | [pdf] | CVPR2017 | LMP
12. Deep network flow for multi-object tracking | [pdf] | CVPR2017
13. Non-markovian globally consistent multi-object tracking | [pdf] [code] | ICCV2017
14. Multi-Object Tracking with Quadruplet Convolutional Neural Networks | [pdf] | CVPR2017 | Quad-CNN
15. Enhancing detection model for multiple hypothesis tracking | [pdf] | CVPRW2017 | EDMT
16. POI: Multiple Object Tracking with High Performance Detection and Appearance Feature | [pdf] | ECCV2016 | KNDT
17. Multiple hypothesis tracking revisited | [pdf] [code] | ICCV2015 | MHT-DAM
18. Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor | [pdf] | ICCV2015 | NOMT
19. On Pairwise Costs for Network Flow Multi-Object Tracking | [pdf] [code]| CVPR2015
20. Multiple Target Tracking Based on Undirected Hierarchical Relation Hypergraph | [pdf] [code] | CVPR2014 | H2T
21. Continuous Energy Minimization for Multi-Target Tracking | [pdf] [code] | CVPR2014 | CEM
22. GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs | [pdf] [code] | ECCV2012 | GMCP
23. Multiple Object Tracking using K-Shortest Paths Optimization | [pdf] [code] | PAMI2011 | KSP
24. Global data association for multi-object tracking using network flows | [pdf] [code] | CVPR2008

跨摄像头跟踪（MTMC）

1. CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification | [pdf] | CVPR2019 | CityFlow
2. Features for multi-target multi-camera tracking and re-identification | [pdf] [code] | CVPR2018 | DeepCC(MTMC)
3. Rolling Shutter and Radial Distortion Are Features for High Frame Rate Multi-Camera Tracking | [pdf] | CVPR2018
4. Towards a Principled Integration of Multi-Camera Re-Identification andTracking through Optimal Bayes Filters | [pdf] [code] | CVPR2017 | towards-reid-tracking

3D&多模态跟踪

1. Robust Multi-Modality Multi-Object Tracking | [pdf] [code] | ICCV2019 | mmMOT
2. A baseline for 3D Multi-Object Tracking | [pdf] [code]
3. MOTSFusion: Track to Reconstruct and Reconstruct to Track | [pdf] [code] |ICRA2020 & RA-L

综述

Multiple Object Tracking: A Literature Review

Machine Learning Methods for Solving Assignment Problems in Multi-Target Tracking

Deep Learning in Video Multi-Object Tracking_ A Survey

Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects

数据集

MOT：包含2D MOT2015、3D MOT2015、MOT16、MOT17和MOT17Det等多个子数据集，提供了ACF、DPM、Faster RCNN、SDP等多个检测器输入。包含不同的相机视角、相机运动、场景和时间变化以及密集场景。

KITTI：提供了汽车和行人的标注，场景较稀疏。

TUD Stadtmitte：包含3D人体姿态识别、多视角行人检测和朝向检测、以及行人跟踪的标注，相机视角很低，数据集不大。

ETHZ：由手机拍摄的多人跟踪数据集，包含三个场景。

EPFL：多摄像头采集的行人检测和跟踪数据集，每隔摄像头离地2米，实验人员就是一个实验室的，分为实验室、校园、平台、通道、篮球场这5个场景，每个场景下都有多个摄像头，每个摄像头拍摄2分钟左右。

KIT AIS：空中拍摄的，只有行人的头

PETS：比较早期的视频，有各式各样的行人运动。

DukeMTMC：多摄像头多行人跟踪。

MOTS：多目标跟踪与分割。

评价体系

ClearMOT

IDF1

Code: python、matlab

---

2020.4.3更新

上面的DeepMOT和MPN Tracker都被CVPR2020录用了，跟Tracktor++都是同一个作者团队，有新增了一些MOT榜前的论文和代码：

Tracking Objects as Points | [pdf][code] | arXiv(2019) | CenterTrack

Refinements in Motion and Appearance for Online Multi-Object Tracking| [pdf][code] | arXiv(2019) | MIFT

Multiple Object Tracking by Flowing and Fusing |[pdf] |arXiv(2019) |FFT

A Unified Object Motion and Affinity Model for Online Multi-Object Tracking |[pdf][code] |CVPR2020 |UMA

完整的在github上：