==================================================================================================================

This project was done for getting hands on on Machine learning libraries. And as a project for my company.

It happens to find the number of the viewer who sees the person who walk in front of them and in resoponse it shows the total count. Works better in GPU PCS.

===================================================================================================================

Changes

• fix bugs
• refactor code
• accerate detection by adding nms on gpu

Changes

• bug fix (Thanks @JieChen91 and @yingsen1 for bug reporting).
• using batch for feature extracting for each frame, which lead to a small speed up.
• code improvement.

Futher improvement direction

• Train detector on specific dataset rather than the official one.
• Retrain REID model on pedestrain dataset for better performance.
• Replace YOLOv3 detector with advanced ones.

Any contributions to this repository is welcome!

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 YOLOv3 to generate bboxes instead of FasterRCNN.

• python 3 (python2 not sure)
• numpy
• scipy
• opencv-python
• sklearn
• torch >= 0.4
• torchvision >= 0.1
• pillow
• vizer
• edict

0. Check all dependencies installed

pip install -r requirements.txt

for user in china, you can specify pypi source to accelerate install like:

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple 

1. Clone this repository

git clone git@github.com:ZQPei/deep_sort_pytorch.git

2. Download YOLOv3 parameters

cd detector/YOLOv3/weight/
wget https://pjreddie.com/media/files/yolov3.weights
wget https://pjreddie.com/media/files/yolov3-tiny.weights
cd ../../../

3. Download deepsort parameters ckpt.t7

cd deep_sort/deep/checkpoint
# download ckpt.t7 from 
https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6 to this folder
cd ../../../

4. Compile nms module

cd detector/YOLOv3/nms
sh build.sh
cd ../../..

5. Run demo

usage: python yolov3_deepsort.py VIDEO_PATH
                                [--help] 
                                [--frame_interval FRAME_INTERVAL]
                                [--config_detection CONFIG_DETECTION]
                                [--config_deepsort CONFIG_DEEPSORT]
                                [--ignore_display]
                                [--display_width DISPLAY_WIDTH]
                                [--display_height DISPLAY_HEIGHT]
                                [--save_path SAVE_PATH]          
                                [--cpu]          

# yolov3 + deepsort
python yolov3_deepsort.py [VIDEO_PATH]

# yolov3_tiny + deepsort
python yolov3_deepsort.py [VIDEO_PATH] --config_detection ./configs/yolov3_tiny.yaml

If you dont support X server, use --ignore_display to disable display. Results will be saved to ./demo/demo.avi.

All files above can also be accessed from BaiduDisk!
linker：BaiduDisk passwd：fbuw

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.

demo.avi demo2.avi

• paper: Simple Online and Realtime Tracking with a Deep Association Metric

• code: nwojke/deep_sort

• paper: YOLOv3

• code: Joseph Redmon/yolov3

This was collaborative work along with my friends by refering online.