MCMOT - GitLite

KO | EN

gitlite — search

#ai #llm #golang #android #machine-learning #rust #linux #docker #kubernetes #vue #security #ios #mcp #open-source

MCMOT

(★ 408)

Real time one-stage multi-class & multi-object tracking based on anchor-free detection and ReID

파일 탐색기

최종 버전 다운로드 (.zip)

- Citypersons_dataset.sh
- all_dla34.sh
- all_hrnet.sh
- all_res50.sh
- ft_mot15_dla34.sh
- ft_mot20_dla34.sh
- - caltech.10k.val
  - caltech.all
  - caltech.train
  - caltech.val
  - citypersons.train
  - citypersons.val
  - cuhksysu.train
  - cuhksysu.val
  - detrac.train
  - eth.train
  - mcmot.train
  - mcmot_det.train
  - mcmot_det.val
  - mcmot_det_bk.train
  - mot15.train
  - mot15.training
  - mot15.val
  - mot15.validation
  - mot17.train
  - mot17.training
  - mot17.validation
  - mot20.train
  - prw.train
  - prw.val
  - visdrone.train
- - logger.py
  - opts.py
- _init_paths.py
- demo.py
- gen_data_path.py
- gen_dataset_visdrone.py
- gen_labels_15.py
- gen_labels_20.py
- gen_labels_detrac_mcmot.py
- gen_labels_mot16_car.py
- gen_mcmot_for_detect.py
- test_det.py
- test_emb.py
- track.py
- train.py
cp_seqinfo_to_MOT15.py
demo.gif
LICENSE
model_down_script.sh
MOT15_dataset_down.sh
README.md
test20_track.gif
test25_track.gif
test27_track.gif
test28_track.gif
test2_track.gif
visdrone_31_track.gif
visdrone_train15_track.gif
visdrone_train17_track.gif
visdrone_train22_track.gif
visdrone_train23_track.gif
visdrone_train39_track.gif
visdrone_train5_track.gif

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# MCMOT: One-shot multi-class multi-object tracking </br>
单阶段实时多类别多目标跟踪
</br>
This is an extention work of FairMOT, which extends the one-class multi-object tracking to multi-class multi-object tracking
</br>
You can refer to origin fork [FairMOT](https://github.com/ifzhang/FairMOT)
## Tracking demo of C5(car, bicycle, person, cyclist, tricycle)
![image](https://github.com/CaptainEven/MCMOT/blob/master/test2_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/test20_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/test25_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/test27_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/test28_track.gif)
</br>
## Tracking demo of VISDrone dataset
![image](https://github.com/CaptainEven/MCMOT/blob/master/visdrone_train5_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/visdrone_train15_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/visdrone_train17_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/visdrone_train22_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/visdrone_train23_track.gif)
![image](https://github.com/CaptainEven/MCMOT/blob/master/visdrone_train39_track.gif)
</br>

## VisDrone dataset training with 10 object classes
[VisDrone link](http://aiskyeye.com/)
</br>
VisDrone is a public dataset for 4 CV challenges: object detection, crowd counting, single class multi-object tracking, multi-class multi-object tracking.
* Download multi-class multi-object tracking part of Visdrone dataset
* Using gen_dataset_visdrone.py script to generate labels.
* Call the gen_dot_train_file function in gen_dataset_visdrone.py to generate the dot train file for VisDrone mcmot training task.
* Uncomment cls2id and id2cls in multitracker.py to use the correct class names and class Ids mapping.
```
from gen_dataset_visdrone import cls2id, id2cls  # visdrone
# from gen_labels_detrac_mcmot import cls2id, id2cls  # mcmot_c5
```
* Set cls ids for visdrone training n opts.py i.e.
```
1~10 object classes are what we need      
        non-interest-zone (0)
        pedestrian        (1)  --> 0       
        people            (2)  --> 1       
        bicycle           (3)  --> 2       
        car               (4)  --> 3       
        van               (5)  --> 4       
        truck             (6)  --> 5        
        tricycle          (7)  --> 6        
        awning-tricycle   (8)  --> 7        
        bus               (9)  --> 8        
        motor             (10) --> 9        
        others            (11)
        self.parser.add_argument('--reid_cls_ids',
                                 default='0,1,2,3,4,5,6,7,8,9',  # '0,1,2,3,4' or '0,1,2,3,4,5,6,7,8,9'
                                 help='')  # the object classes need to do reid
```

## Tracking or detection mode setting
Set id_weight to 1 for tracking and 0 for detection mode.
```
        self.parser.add_argument('--id_weight',
                                 type=float,
                                 default=1,  # 0for detection only and 1 for detection and re-ida
                                 help='loss weight for id')  # ReID feature extraction or not
```

## Pretained model for C5 and VisDrone detection and tracking
HRNet18 backbone with bi-linear upsampling replaced with de-convolution </br>
The pre-trained model is for 5 classes(C5) detection & tracking: car, bicycle, person, cyclist, tricycle, which can be used for road traffic video surveillance and analysis. </br>
</br>
[baidu drive link](https://pan.baidu.com/s/1imrim0kt72_Ay9w-X4kqdw) extract code：ej4p
</br>
[one drive link](https://1drv.ms/u/s!AmgjV-Jny9CqkX2EneIkb6Q8x6WI?e=Lsqx4G)

### Resnet18 backbone for C5，which is much smaller than HRNet18
[ResNet18 one drive link](https://1drv.ms/u/s!AmgjV-Jny9Cqkjiwqx7UY2g2_uZU?e=tws0eQ)

### Resnet18 backbone for VisDrone mcmot
[Resnet18 one drive link](https://1drv.ms/u/s!AmgjV-Jny9CqkjkCXS9QC8mJwMmB?e=XzrH1T)

### Using YOLOV4 as detector
You can also refer to the ropo：[MCMOT_YOLOV4](https://github.com/CaptainEven/YOLOV4_MCMOT) </br>
This is MCMOT with CenterNet detection frame work replaced with an anchor-based detection framework.

### Using ByteTrack
You can also refer to the ropo：[MCMOT-ByteTrack](https://github.com/CaptainEven/MCMOT-ByteTrack) </br>
Using YOLOX as front-end and using ByteTrack as back-end.