项目作者: KaiyangZhou

项目描述 :
Depth-Based Region-of-Interest (ROI) Selection
高级语言: C++
项目地址: git://github.com/KaiyangZhou/ROI-Selection.git
创建时间: 2016-12-08T07:28:30Z
项目社区:https://github.com/KaiyangZhou/ROI-Selection

开源协议:MIT License

下载


Depth-Based ROI Selection

Overview

This is the ROI selection method used in the paper Detecting Humans in RGB-D Data with CNNs. It reduces the search space in an image and produces a set of square proposals. It was particularly designed for human upper body detection, but it can be modified to suit object detection as well.

How to use

  1. in command line run git clone https://github.com/KaiyangZhou/ROI_Selection.git
  2. cd to the ROI_Selection directory and run matlab (if you have installed)
  3. run build() to generate mex files
  4. run demo() to see what happens

img.mat contains a color image and an aligned depth image (unit in meters), which are obtained from RGBD people dataset.

Core functions are enclosed in functions/roi_selection.m. For detailed descriptions, please refer to our paper.

Reference

  1. @inproceedings{kzhou2017humandetect,
  2. title = {Detecting Humans in RGB-D Data with CNNs},
  3. author = {Kaiyang Zhou and Adeline Paiement and Majid Mirmehdi},
  4. year = {2017},
  5. month = {2},
  6. booktitle = {IAPR Conference on Machine Vision Applications (MVA2017)},
  7. }