文件列表:

det_code-1.0beta (0, 2008-02-14)
det_code-1.0beta\codebook (0, 2008-02-14)
det_code-1.0beta\codebook\get_mask_center.m (243, 2008-01-14)
det_code-1.0beta\codebook\load_anno_data.m (1233, 2008-01-23)
det_code-1.0beta\codebook\load_codebook.m (6835, 2008-02-14)
det_code-1.0beta\codebook\proc_codebook_oneimage_circlebin.m (1330, 2008-01-24)
det_code-1.0beta\data (0, 2008-02-14)
det_code-1.0beta\data\codebook (0, 2008-02-14)
det_code-1.0beta\data\codebook\cb_pb_height_150_bin_30.mat (6855172, 2008-01-24)
det_code-1.0beta\data\edge (0, 2008-02-14)
det_code-1.0beta\data\images (0, 2008-02-14)
det_code-1.0beta\data\images\FudanPed00001.png (497496, 2008-01-24)
det_code-1.0beta\data\images\PennPed00001.png (437808, 2008-01-24)
det_code-1.0beta\data\result (0, 2008-02-14)
det_code-1.0beta\data\train (0, 2008-02-14)
det_code-1.0beta\data\train\images (0, 2008-02-14)
det_code-1.0beta\data\train\images\train001.png (21557, 2008-01-23)
det_code-1.0beta\data\train\images\train002.png (23877, 2008-01-23)
det_code-1.0beta\data\train\images\train003.png (32073, 2008-01-23)
det_code-1.0beta\data\train\images\train004.png (25799, 2008-01-23)
det_code-1.0beta\data\train\images\train005.png (26042, 2008-01-23)
det_code-1.0beta\data\train\images\train006.png (26895, 2008-01-23)
det_code-1.0beta\data\train\images\train007.png (21824, 2008-01-23)
det_code-1.0beta\data\train\images\train008.png (17527, 2008-01-23)
det_code-1.0beta\data\train\images\train009.png (22655, 2008-01-23)
det_code-1.0beta\data\train\images\train010.png (20081, 2008-01-23)
det_code-1.0beta\data\train\images\train011.png (30492, 2008-01-23)
det_code-1.0beta\data\train\images\train012.png (38888, 2008-01-23)
det_code-1.0beta\data\train\images\train013.png (27051, 2008-01-23)
det_code-1.0beta\data\train\images\train014.png (33082, 2008-01-23)
det_code-1.0beta\data\train\images\train015.png (30652, 2008-01-23)
det_code-1.0beta\data\train\images\train016.png (27771, 2008-01-23)
det_code-1.0beta\data\train\images\train017.png (26381, 2008-01-23)
det_code-1.0beta\data\train\images\train018.png (21692, 2008-01-23)
det_code-1.0beta\data\train\images\train019.png (27864, 2008-01-23)
det_code-1.0beta\data\train\images\train020.png (33750, 2008-01-23)
det_code-1.0beta\data\train\mask (0, 2008-02-14)
det_code-1.0beta\data\train\mask\train001.png (569, 2008-01-23)
det_code-1.0beta\data\train\mask\train002.png (538, 2008-01-23)
det_code-1.0beta\data\train\mask\train003.png (583, 2008-01-23)
... ...

I) About the code This code is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License.This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. This code is written for the paper [1]. It was initially developed by Gang and Liming, and cleaned up by Liming in Jan 2008. It's tested under Matlab 7.0. The version number is now 1.0beta. The main part of the code uses improved Shape Context as feature descriptor and fit into a Hough Voting framework to detect objects. It can be used for initial hypothesis proposal. I hope you find this code helpful! II) The related paper is: Object Detection Combining Recognition and Segmentation, Liming Wang, Jianbo Shi, Gang Song, I-Fan Shen, Eighth Asian Conference on Computer Vision (ACCV), 2007 Please cite this paper if you use this code in your work. III) How to use the code a) Prerequisite: 1. Matlab 7.0 or upper, with image processing toolbox installed. ( I have not tested it under Matlab 6.5, it should work in most cases.) 2. In order to use 'pb' edge detector, you need to download it from 'http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/segbench/' if you don't have it, and make sure add it to your matlab directory. b) Using this software: 1. Copy unzipped 'det_code_beta1.0' to your working directory. 2. Open Matlab and enter the detectory 'det_code-1.0beta'. 3. run 'startup' first 4. run 'demo_one_image' to see the demo There are three demo files: 1. demo_train.m You can get your own codebook by use this script to train on your own images. 2. demo_one_image.m Shows how to detect object (pedestrian) on one image. 3. demo_multi_image.m Shows how to detect a list of images and generate the result files. IV) This is still a code beta version. I will keep it updated in the future. Copyleft @2008 -Liming Wang

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：