pprp/simple_deep_sort

deep sort with yolov3. Modify darknet based yolov3 to pytorch based yolov3.

Deep Sort with PyTorch

Latest Update(07-22)

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!

Introduction

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.

Dependencies

• python 3 (python2 not sure)
• numpy
• scipy
• opencv-python
• sklearn
• pytorch 0.4 or 1.x

Quick Start

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 [email protected]:ZQPei/deep_sort_pytorch.git

2. Download YOLOv3 parameters

cd YOLOv3/
wget https://pjreddie.com/media/files/yolov3.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. Run demo

usage: demo_yolo3_deepsort.py VIDEO_PATH
                              [--help] 
                              [--yolo_cfg YOLO_CFG]
                              [--yolo_weights YOLO_WEIGHTS]
                              [--yolo_names YOLO_NAMES]
                              [--conf_thresh CONF_THRESH]
                              [--nms_thresh NMS_THRESH]
                              [--deepsort_checkpoint DEEPSORT_CHECKPOINT]
                              [--max_dist MAX_DIST] [--ignore_display]
                              [--display_width DISPLAY_WIDTH]
                              [--display_height DISPLAY_HEIGHT]
                              [--save_path SAVE_PATH]          

All files above can also be accessed from BaiduDisk!
linker：https://pan.baidu.com/s/1TEFdef9tkJVT0Vf0DUZvrg
passwd：1eqo

Training the RE-ID model

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 videos and images

demo.avi demo2.avi

References

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

• code: nwojke/deep_sort

• paper: YOLOv3

• code: Joseph Redmon/yolov3

simple_deep_sort's Issues

FPS are 3 even on RTX 2080TI

Having RTX 2080TI I even write os.environ["CUDA_VISIBLE_DEVICES"] = "2,3" but FPS didn't increase. Any suggestion.
I observe code isn't running on GPU