monkut / deep_sort_pytorch

MOT tracking using deepsort and yolov3 with pytorch

Deep Sort with PyTorch

Introduction

This is an implementation of MOT (Multiple Object Tracking) tracking algorithm deep sort. Deep sort is basically the same with sort but has an added 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 using FasterRCNN, and the original source code is HERE.

This implementation replaces the tensorflow-based CNN modle with a PyTorch implementation, and replaces FasterRCNN with YOLOv3 for bbox generation.

Dependencies

• python 3
• numpy
• scipy
• opencv-python
• sklearn
• torch >= 0.4
• torchvision >= 0.1
• pillow
• vizer
• edict

Quick Start

Pre-requisites:

• pre-commit
• pipenv

0. Check all dependencies installed

pipenv install

# configure pre-commit hooks (black, isort)
pre-commit install

1. Download YOLOv3 parameters

   make get-yolov3-weights

OR

cd detector/YOLOv3/weights/
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 ../../..

Notice: If compiling failed, the simplist way is to **Upgrade your pytorch >= 1.1 and torchvision >= 0.3" and you can avoid the troublesome compiling problems which are most likely caused by either gcc version too low or libraries missing.

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

# yolov3 + deepsort on webcam
python3 yolov3_deepsort.py /dev/video0 --camera 0

# yolov3_tiny + deepsort on webcam
python3 yolov3_deepsort.py /dev/video0 --config_detection ./configs/yolov3_tiny.yaml --camera 0

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

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