https://github.com/jizhu1023/DMAN_MOT

Code for Online Multi-Object Tracking with Dual Matching Attention Network, ECCV 2018
https://github.com/jizhu1023/DMAN_MOT

dman dual-matching-attention-network mot multi-object-tracker multi-object-tracking multi-pedestrian-tracking multi-person-tracking object-tracking online-mot

Last synced: 29 days ago
JSON representation

Code for Online Multi-Object Tracking with Dual Matching Attention Network, ECCV 2018

• Host: GitHub
• URL: https://github.com/jizhu1023/DMAN_MOT
• Owner: jizhu1023
• License: gpl-3.0
• Created: 2019-04-13T15:49:37.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-07-10T15:54:01.000Z (over 5 years ago)
• Last Synced: 2024-08-03T22:14:15.250Z (4 months ago)
• Topics: dman, dual-matching-attention-network, mot, multi-object-tracker, multi-object-tracking, multi-pedestrian-tracking, multi-person-tracking, object-tracking, online-mot
• Language: MATLAB
• Homepage: https://jizhu1023.github.io/eccv18_mot/index.html
• Size: 18.6 MB
• Stars: 84
• Watchers: 2
• Forks: 15
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-multiple-object-tracking - [code - Object_Tracking_ECCV_2018_paper.pdf) (算法论文 / **2018**)

README

        
# Online Multi-Object Tracking with DMANs

This is the implementation of our ECCV 2018 paper [Online Multi-Object Tracking with Dual Matching Attention Networks](https://arxiv.org/abs/1902.00749). We integrate the ECO [1] for single object tracking. The code framework for MOT benefits from the MDP [2].



  





# Prerequisites

- Cuda 8.0

- Cudnn 5.1

- Python 2.7

- Keras 2.0.5

- Tensorflow 1.1.0

For example:

conda create -n mot anaconda python=2.7

conda activate mot

conda install -c menpo opencv

pip install tensorflow-gpu==1.1.0

pip install keras==2.0.5



# Usage

1. Download the [DMAN model](https://zhiyanapp-build-release.oss-cn-shanghai.aliyuncs.com/zhuji_file/spatial_temporal_attention_model.h5) and put it into the "model/" folder.

2. Download the [MOT16 dataset](https://motchallenge.net/data/MOT16/), unzip it to the "data/" folder.

3. Cd to the "ECO/" folder, run the script install.m to compile libs for the ECO tracker

4. Run the socket server script:

python calculate_similarity.py



5. Run the socket client script DMAN_demo.m in Matlab.

# Citation


If you use this code, please consider citing:

@inproceedings{zhu-eccv18-DMAN,

    author    = {Zhu, Ji and Yang, Hua and Liu, Nian and Kim, Minyoung and Zhang, Wenjun and Yang, Ming-Hsuan},

    title     = {Online Multi-Object Tracking with Dual Matching Attention Networks},

    booktitle = {European Computer Vision Conference},

    year      = {2018},

}



# References

[1] Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ECO: Efficient convolution operators for tracking. In: CVPR (2017)

[2] Xiang, Y., Alahi, A., Savarese, S.: Learning to track: Online multi-object tracking by decision making. In: ICCV (2015)