Need help with MDNet?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

hyeonseobnam
429 Stars 175 Forks Other 15 Commits 11 Opened issues

Description

Learning Multi-Domain Convolutional Neural Networks for Visual Tracking

Services available

!
?

Need anything else?

Contributors list

No Data

MDNet: Multi-Domain Convolutional Neural Network Tracker

Created by Hyeonseob Nam and Bohyung Han at POSTECH

Project Webpage: http://cvlab.postech.ac.kr/research/mdnet/

News

(May 28, 2017) Python implementation of MDNet is avaliable! [py-MDNet]

Introduction

MDNet is the state-of-the-art visual tracker based on a CNN trained on a large set of tracking sequences, and the winner tracker of The VOT2015 Challenge.

Detailed description of the system is provided by our paper.

This software is implemented using MatConvNet and part of R-CNN.

Citation

If you're using this code in a publication, please cite our paper.

@InProceedings{nam2016mdnet,
author = {Nam, Hyeonseob and Han, Bohyung},
title = {Learning Multi-Domain Convolutional Neural Networks for Visual Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}

License

This software is being made available for research purpose only. Check LICENSE file for details.

System Requirements

This code is tested on 64 bit Linux (Ubuntu 14.04 LTS).

Prerequisites 0. MATLAB (tested with R2014a) 0. MatConvNet (tested with version 1.0-beta10, included in this repository) 0. For GPU support, a GPU (~2GB memory) and CUDA toolkit according to the MatConvNet installation guideline will be needed.

Installation

  1. Compile MatConvNet according to the installation guideline. An example script is provided in 'compile_matconvnet.m'.
  2. Run 'setup_mdnet.m' to set the environment for running MDNet.

Online Tracking using MDNet

Pretrained Models

If you only need to run the tracker, you can use the pretrained MDNet models: 0. models/mdnetvot-otb.mat (trained on VOT13,14,15 excluding OTB) 0. models/mdnetotb-vot14.mat (trained on OTB excluding VOT14) 0. models/mdnet_otb-vot15.mat (trained on OTB excluding VOT15)

Demo 0. Run 'tracking/demo_tracking.m'.

The demo performs online tracking on 'Diving' sequence using a pretrained model 'models/mdnet_vot-otb.mat'.

In case of out of GPU memory, decrease opts.batchSize_test in 'tracking/mdnetinit.m'. You can also disable the GPU support by setting opts.useGpu in 'tracking/mdnetinit.m' to false (not recommended).

Learning MDNet

Preparing Datasets

You may need OTB and VOT datasets for learning MDNet models. You can also use other datasets by configuring 'utils/genConfig.m'. 0. Download OTB and VOT datasets. 0. Locate the OTB sequences in 'dataset/OTB' and VOT201x sequences in 'dataset/VOT/201x', or modify the variables benchmarkSeqHome in 'utils/genConfig.m' properly.

Demo 0. Run 'pretraining/demo_pretraining.m'.

The demo trains new MDNet models using OTB or VOT sequences.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.