[MOT] update mot doc, mot.yml (#3233)

* update mot doc config, test=document_fix

* update citations, test=document_fix

* update title, test=document_fix

configs/datasets/mot.yml

@@ -13,25 +13,15 @@ MOTDataZoo: {
   'demo': ['MOT16-02'],
 }
 
+# for MOT training
 TrainDataset:
   !MOTDataSet
     dataset_dir: dataset/mot
     image_lists: ['mot17.train', 'caltech.all', 'cuhksysu.train', 'prw.train', 'citypersons.train', 'eth.train']
     data_fields: ['image', 'gt_bbox', 'gt_class', 'gt_ide']
 
-# for detection or reid evaluation, no use in MOT evaluation
-EvalDataset:
-  !MOTDataSet
-    dataset_dir: dataset/mot
-    image_lists: ['citypersons.val', 'caltech.val'] # for detection evaluation
-    # image_lists: ['caltech.10k.val', 'cuhksysu.val', 'prw.val'] # for reid evaluation
-    data_fields: ['image', 'gt_bbox', 'gt_class', 'gt_ide']
-
-# for detection inference, no use in MOT inference
-TestDataset:
-  !ImageFolder
-    dataset_dir: dataset/mot
-
+# for MOT evaluation
+# If you want to change the MOT evaluation dataset, please modify 'task' and 'data_root'
 EvalMOTDataset:
   !MOTImageFolder
     task: MOT16_train
@@ -39,7 +29,22 @@ EvalMOTDataset:
     data_root: MOT16/images/train
     keep_ori_im: False # set True if save visualization images or video
 
+# for MOT video inference
 TestMOTDataset:
   !MOTVideoDataset
     dataset_dir: dataset/mot
     keep_ori_im: True # set True if save visualization images or video
+
+
+# for detection or reid evaluation, following the JDE paper, but no use in MOT evaluation
+EvalDataset:
+  !MOTDataSet
+    dataset_dir: dataset/mot
+    image_lists: ['citypersons.val', 'caltech.val'] # for detection evaluation
+    # image_lists: ['caltech.10k.val', 'cuhksysu.val', 'prw.val'] # for reid evaluation
+    data_fields: ['image', 'gt_bbox', 'gt_class', 'gt_ide']
+
+# for detection inference, no use in MOT inference
+TestDataset:
+  !ImageFolder
+    dataset_dir: dataset/mot

configs/mot/README.md

@@ -244,13 +244,6 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
 
 ## Citations
 ```
-@article{wang2019towards,
-  title={Towards Real-Time Multi-Object Tracking},
-  author={Wang, Zhongdao and Zheng, Liang and Liu, Yixuan and Wang, Shengjin},
-  journal={arXiv preprint arXiv:1909.12605},
-  year={2019}
-}
-
 @inproceedings{Wojke2017simple,
   title={Simple Online and Realtime Tracking with a Deep Association Metric},
   author={Wojke, Nicolai and Bewley, Alex and Paulus, Dietrich},
@@ -277,4 +270,11 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
   journal={arXiv preprint arXiv:1909.12605},
   year={2019}
 }
+
+@article{zhang2020fair,
+  title={FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking},
+  author={Zhang, Yifu and Wang, Chunyu and Wang, Xinggang and Zeng, Wenjun and Liu, Wenyu},
+  journal={arXiv preprint arXiv:2004.01888},
+  year={2020}
+}
 ```

configs/mot/README_cn.md

@@ -241,13 +241,6 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
 
 ## 引用
 ```
-@article{wang2019towards,
-  title={Towards Real-Time Multi-Object Tracking},
-  author={Wang, Zhongdao and Zheng, Liang and Liu, Yixuan and Wang, Shengjin},
-  journal={arXiv preprint arXiv:1909.12605},
-  year={2019}
-}
-
 @inproceedings{Wojke2017simple,
   title={Simple Online and Realtime Tracking with a Deep Association Metric},
   author={Wojke, Nicolai and Bewley, Alex and Paulus, Dietrich},
@@ -274,4 +267,11 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
   journal={arXiv preprint arXiv:1909.12605},
   year={2019}
 }
+
+@article{zhang2020fair,
+  title={FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking},
+  author={Zhang, Yifu and Wang, Chunyu and Wang, Xinggang and Zeng, Wenjun and Liu, Wenyu},
+  journal={arXiv preprint arXiv:2004.01888},
+  year={2020}
+}
 ```

configs/mot/deepsort/README.md

 English | [简体中文](README_cn.md)
 
-# DeepSORT (Simple Online and Realtime Tracking with a Deep Association Metric)
+# DeepSORT (Deep Cosine Metric Learning for Person Re-identification)
 
 ## Table of Contents
 - [Introduction](#Introduction)

configs/mot/deepsort/README_cn.md

 简体中文 | [English](README.md)
 
-# DeepSORT
+# DeepSORT (Deep Cosine Metric Learning for Person Re-identification)
 
 ## 内容
 - [简介](#简介)

configs/mot/fairmot/README_cn.md

@@ -77,10 +77,10 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
 
 ## 引用
 ```
-@article{wang2019towards,
-  title={Towards Real-Time Multi-Object Tracking},
-  author={Wang, Zhongdao and Zheng, Liang and Liu, Yixuan and Wang, Shengjin},
-  journal={arXiv preprint arXiv:1909.12605},
-  year={2019}
+@article{zhang2020fair,
+  title={FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking},
+  author={Zhang, Yifu and Wang, Chunyu and Wang, Xinggang and Zeng, Wenjun and Liu, Wenyu},
+  journal={arXiv preprint arXiv:2004.01888},
+  year={2020}
 }
 ```

configs/mot/jde/README.md

 English | [简体中文](README_cn.md)
 
-# JDE (Joint Detection and Embedding)
+# JDE (Towards Real-Time Multi-Object Tracking)
 
 ## Table of Contents
 - [Introduction](#Introduction)
@@ -10,7 +10,7 @@ English | [简体中文](README_cn.md)
 
 ## Introduction
 
-- [JDE](https://arxiv.org/abs/1909.12605) (Joint Detection and Embedding) learns the object detection task and appearance embedding task simutaneously in a shared neural network. And the detection results and the corresponding embeddings are also outputed at the same time. JDE original paper is based on an Anchor Base detector YOLOv3 , adding a new ReID branch to learn embeddings. The training process is constructed as a multi-task learning problem, taking into account both accuracy and speed.
+- [JDE](https://arxiv.org/abs/1909.12605) (Joint Detection and Embedding) learns the object detection task and appearance embedding task simutaneously in a shared neural network. And the detection results and the corresponding embeddings are also outputed at the same time. JDE original paper is based on an Anchor Base detector YOLOv3, adding a new ReID branch to learn embeddings. The training process is constructed as a multi-task learning problem, taking into account both accuracy and speed.
 
 <div align="center">
   <img src="../../../docs/images/mot16_jde.gif" width=500 />
@@ -35,6 +35,7 @@ English | [简体中文](README_cn.md)
 | DarkNet53(paper)   | 864x480 |   62.1  |  56.9  | 1608  |    -    |   -   |   -   |   -  |   -   |
 | DarkNet53          | 864x480 |   63.2  |  57.7  | 1966  |  10070  | 55081 |   -   |[model](https://paddledet.bj.bcebos.com/models/mot/jde_darknet53_30e_864x480.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/jde/jde_darknet53_30e_864x480.yml) |
 | DarkNet53          | 576x320 |   59.1  |  56.4  | 1911  |  10923  | 61789  |   -   |[model](https://paddledet.bj.bcebos.com/models/mot/jde_darknet53_30e_576x320.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/jde/jde_darknet53_30e_576x320.yml) |
+
 **Notes:**
  JDE used 8 GPUs for training and mini-batch size as 4 on each GPU, and trained for 30 epoches.
 
@@ -59,6 +60,16 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/jde/jde_darknet53
 # use saved checkpoint in training
 CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/jde/jde_darknet53_30e_1088x608.yml -o weights=output/jde_darknet53_30e_1088x608/model_final.pdparams
 ```
+**Notes:**
+ The default evaluation dataset is MOT-16 Train Set. If you want to change the evaluation dataset, please refer to the following code and modify `configs/datasets/mot.yml`：
+```
+EvalMOTDataset:
+  !MOTImageFolder
+    task: MOT17_train
+    dataset_dir: dataset/mot
+    data_root: MOT17/images/train
+    keep_ori_im: False # set True if save visualization images or video
+```
 
 ### 3. Inference
 

configs/mot/jde/README_cn.md

 简体中文 | [English](README.md)
 
-# JDE (Joint Detection and Embedding)
+# JDE (Towards Real-Time Multi-Object Tracking)
 
 ## 内容
 - [简介](#简介)
@@ -61,6 +61,16 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/jde/jde_darknet53
 # 使用训练保存的checkpoint
 CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/jde/jde_darknet53_30e_1088x608.yml -o weights=output/jde_darknet53_30e_1088x608/model_final.pdparams
 ```
+**注意:**
+ 默认评估的是MOT-16 Train Set数据集, 如需换评估数据集可参照以下代码修改`configs/datasets/mot.yml`：
+```
+EvalMOTDataset:
+  !MOTImageFolder
+    task: MOT17_train
+    dataset_dir: dataset/mot
+    data_root: MOT17/images/train
+    keep_ori_im: False # set True if save visualization images or video
+```
 
 ### 3. 预测