GithubHelp home page GithubHelp logo

lhy20 / aogdetector Goto Github PK

View Code? Open in Web Editor NEW

This project forked from tfwu/aogdetector

0.0 2.0 0.0 10.98 MB

Source code for object detection with And-Or Graphs

Home Page: http://www.stat.ucla.edu/~tfwu/projects.htm

License: MIT License

CMake 1.08% MATLAB 2.73% C++ 96.18%

aogdetector's Introduction

AOGDetector

Implementation of the papers

    Xi Song, Tianfu Wu, Yunde Jia and Song-Chun Zhu, "Discriminatively Trained And-Or Tree Model for Object Detection",  In CVPR2013.        
    Bo Li, Wenze Hu, Tianfu Wu and Song-Chun Zhu, "Modeling Occlusion by Discriminative AND-OR Structures", In ICCV2013        
    Bo Li, Tianfu Wu and Song-Chun Zhu, "Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model", In ECCV2014
    Tianfu Wu, Bo Li and Song-Chun Zhu, "Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation",  TPAMI, 2015 (arXiv 1501.07359)

Copyright (c) 2014 Center for Vision, Cognition, Learning and Autonomy at UCLA http://vcla.stat.ucla.edu/,

    Written by Matt Tianfu Wu (primary contact) <[email protected]>,  
    Xi Song                          <[email protected]> (object detection module),                        
    Bo Li                            <[email protected]>  (occlusion module),                      

Code Release Log

 10-14-2014: Release detection code  (full code will be released in future)                    

MODULE 1: object detection

VOC Configuration

All the configuration can be specified in voc_config.xml in "<PATH_TO_RGM_Source_Code>/config" folder.

VOC Testing

Use Terminal and cd to the <PATH_TO_Build>/bin where the executable "Entry" is built,

Run: Entry vocEval PATH_To_voc_config_xml,

e.g., Entry vocEval /home/tfwu/Code/RGM/config/voc_config.xml

DetectionInASingleImage

Use Terminal and cd to the PATH_TO_Build/bin where the executable "Entry" is built,

Run: Entry detect PATH_To_voc_config_xml,

e.g., Entry detect /home/tfwu/Code/RGM/config/voc_config.xml

BatchDetectionInDirectory

Use Terminal and cd to the PATH_TO_Build/bin where the executable "Entry" is built,

Run: Entry detectBatch PATH_To_voc_config_xml,

e.g., Entry detectBatch /home/tfwu/Code/RGM/config/voc_config.xml

ConvertVOCRel5Model

Use Terminal and cd to the <PATH_TO_Build>/bin where the executable "Entry" is built,

Run: Entry cvtVOCRel5Model PATH_To_VOCRel5_Model_Mat_File,

e.g., Entry cvtVOCRel5Model /home/tfwu/Code/RGM/externalModels/VOC2007/bicycle_final.mat,

The converted model will be saved (e.g., /home/tfwu/Code/RGM/data/bicycle_final.mat.bin) which can be used to test detection.

Note: Before using this to convert a matlab model trained using VOC-Release 5 by Dr. Ross Girshick, please use PATH_TO_RGM_Source_Code/matlab/convertVOCR5.m to add a "DFS" field to the model structure.

aogdetector's People

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.