## MDNet: Multi-Domain Convolutional Neural Network Tracker
Created by [Hyeonseob Nam](https://kr.linkedin.com/in/hyeonseob-nam/) and [Bohyung Han](http://cvlab.postech.ac.kr/~bhhan/) at POSTECH
Project Webpage: http://cvlab.postech.ac.kr/research/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](http://www.votchallenge.net/vot2015/).
Detailed description of the system is provided by our [arXiv technical report](http://arxiv.org/abs/1510.07945).
This software is implemented using [MatConvNet](http://www.vlfeat.org/matconvnet/) and part of [R-CNN](https://github.com/rbgirshick/rcnn).
### 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](http://www.vlfeat.org/matconvnet/install/) will be needed.
### Installation
0. Compile MatConvNet according to the [installation guideline](http://www.vlfeat.org/matconvnet/install/). An example script is provided in 'compile_matconvnet.m'.
0. 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/mdnet_vot-otb.mat (trained on VOT13,14,15 excluding OTB)
0. models/mdnet_otb-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/mdnet_init.m'.
You can also disable the GPU support by setting *opts.useGpu* in 'tracking/mdnet_init.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](http://cvlab.hanyang.ac.kr/tracker_benchmark/datasets.html) and [VOT](http://www.votchallenge.net/) 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.
没有合适的资源?快使用搜索试试~ 我知道了~
基于多域学习卷积神经网络的目标跟踪 Matlab程序
共127个文件
m:47个
cpp:20个
hpp:19个
5星 · 超过95%的资源 需积分: 34 121 下载量 155 浏览量
2017-03-30
22:31:24
上传
评论 8
收藏 156KB ZIP 举报
温馨提示
基于多域学习卷积神经网络的目标跟踪 Matlab程序
资源推荐
资源详情
资源评论
收起资源包目录
基于多域学习卷积神经网络的目标跟踪 Matlab程序 (127个子文件)
COPYING 735B
normalize_cpu.cpp 12KB
pooling_cpu.cpp 10KB
tinythread.cpp 8KB
im2row_cpu.cpp 8KB
imread_libjpeg.cpp 6KB
imread_quartz.cpp 5KB
imread_gdiplus.cpp 5KB
subsample_cpu.cpp 4KB
copy_cpu.cpp 595B
nnfullyconnected.cpp 121B
vl_nnnormalize.cpp 116B
vl_imreadjpeg.cpp 115B
nnsubsample.cpp 112B
vl_nnpool.cpp 111B
vl_nnconv.cpp 111B
nnnormalize.cpp 111B
datamex.cpp 109B
nnpooling.cpp 107B
data.cpp 106B
nnconv.cpp 101B
nnconv_cudnn.cu 15KB
vl_nnconv.cu 13KB
pooling_gpu.cu 12KB
datamex.cu 11KB
im2row_gpu.cu 10KB
data.cu 9KB
vl_nnpool.cu 9KB
vl_imreadjpeg.cu 9KB
nnfullyconnected.cu 8KB
nnpooling_cudnn.cu 8KB
nnsubsample.cu 7KB
nnpooling.cu 7KB
subsample_gpu.cu 6KB
datacu.cu 6KB
vl_nnnormalize.cu 5KB
normalize_gpu.cu 5KB
nnnormalize.cu 4KB
nnconv.cu 4KB
copy_gpu.cu 625B
.gitignore 254B
.gitignore 252B
.gitmodules 0B
tinythread.h 21KB
mexutils.h 21KB
fast_mutex.h 7KB
imread_helpers.hpp 14KB
nnconv_blas.hpp 12KB
pooling.hpp 6KB
blashelper.hpp 5KB
data.hpp 4KB
subsample.hpp 3KB
im2row.hpp 3KB
normalize.hpp 3KB
nnpooling_cudnn.hpp 2KB
nnconv_cudnn.hpp 2KB
datacu.hpp 2KB
datamex.hpp 2KB
nnpooling.hpp 1KB
nnconv.hpp 1KB
nnsubsample.hpp 1KB
nnfullyconnected.hpp 1KB
nnnormalize.hpp 961B
copy.hpp 874B
imread.hpp 678B
LICENSE 2KB
vl_compilenn.m 23KB
vl_test_nnlayers.m 14KB
vl_simplenn.m 8KB
mdnet_run.m 7KB
mdnet_train.m 6KB
mdnet_pretrain.m 6KB
mdnet_finetune_hnm.m 6KB
vl_simplenn_display.m 5KB
train_bbox_regressor.m 5KB
mdnet_simplenn.m 5KB
genConfig.m 4KB
im_crop.m 4KB
mdnet_prepare_model.m 3KB
vl_nnconv.m 3KB
seq2roidb.m 3KB
vl_simplenn_diagnose.m 3KB
gen_samples.m 3KB
vl_nnpool.m 3KB
vl_argparse.m 2KB
vl_nnsoftmaxloss.m 2KB
mdnet_init.m 2KB
vl_nnloss.m 2KB
vl_bench_imreadjpeg.m 2KB
vl_imreadjpeg.m 2KB
predict_bbox_regressor.m 2KB
get_batch.m 1KB
vl_nndropout.m 1KB
demo_pretraining.m 1KB
vl_test_gpureset.m 1KB
vl_nnnormalize.m 1KB
vl_nnsoftmax.m 1KB
vl_simplenn_move.m 963B
vl_test_imreadjpeg.m 900B
vl_nnnoffset.m 896B
共 127 条
- 1
- 2
资源评论
- lyx6350599672017-04-07怎么用呢???
Tank_wick
- 粉丝: 1
- 资源: 7
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功