This is an implement of MOT tracking algorithm deep sort. Deep sort is basicly the same with sort but added a CNN model to extract features in image of human part bounded by a detector. This CNN model is indeed a RE-ID model and the detector used in PAPER is FasterRCNN , and the original source code is HERE.
However in original code, the CNN model is implemented with tensorflow, which I'm not familier with. SO I re-implemented the CNN feature extraction model with PyTorch, and changed the CNN model a little bit. Also, I use YOLO3 to generate bboxes instead of FasterRCNN.
- python 3 (python2 not sure)
- numpy
- cv2
- sklearn
- pytorch 0.4.0
-
Check all dependencies installed
-
Clone this repository
git clone git@github.com:ZQPei/deep_sort_pytorch.git
- Download YOLO3 parameters
cd YOLO3/
wget https://pjreddie.com/media/files/yolov3.weights
cd ..
- Download deepsort parameters ckpt.t7
cd deep/checkpoint
# download ckpt.t7 from
https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6 to this folder
cd ../../
- Run demo
python demo_yolo3_deepsort.py [YOUR_VIDEO_PATH]
The original model used in paper is in original_model.py, and its parameter here original_ckpt.t7.
To train the model, first you need download Market1501 dataset or Mars dataset.
Then you can try train.py to train your own parameter and evaluate it using test.py and evaluate.py.
All files can also be accessed by BaiduDisk!
linker：https://pan.baidu.com/s/1TEFdef9tkJVT0Vf0DUZvrg
passwd：1eqo
-
paper: Simple Online and Realtime Tracking with a Deep Association Metric
-
code: nwojke/deep_sort
-
paper: YOLOv3
-
code: Joseph Redmon/yolov3