Real-time Pedestrian Detection based on GMM and HOG Cascade

被引:0
作者
Jin, Moonyong [1 ]
Jeong, Kiseon [1 ]
Yoon, Sook [2 ]
Park, Dong Sun [1 ,3 ]
机构
[1] Chonbuk Natl Univ, Dept Elect Engn, Jeonju, Jeonbuk, South Korea
[2] Mokpo Natl Univ, Dept Multimedia Engn, Jeonnam, South Korea
[3] Chonbuk Natl Univ, IT Convergence Res Ctr, Jeonju, Jeonbuk, South Korea
来源
SIXTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2013) | 2013年 / 9067卷
基金
新加坡国家研究基金会;
关键词
Pedestrian detection; GM; M; HOG; HOG based cascade; Coarse-to-fine detection;
D O I
10.1117/12.2051382
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Most of the human detection methods are using HOG (Histogram of Oriented Gradients). In the case of fixed camera environment, it is possible to make background model using GMINI (Gaussian mixture model) and easily extract motions using background subtraction. However, it is difficult to recognize pedestrians among extracted motions. In this paper, we propose an efficient coarse-to-fine pedestrian detection framework which combines motion detection and HOG cascade to make a faster pedestrian detector. Firstly, motion detection is used as the coarse detection in order to reduce the area of interest to be covered by the pedestrian detector. Then HOG cascade which detects pedestrians is executed only on the blobs or ROIs selected from the coarse detection. The experimental results on PET2009 768X576 dataset show that proposed method of which processing speed is 11.46 fps is 7.5 times faster than HOG and 2.2 times faster than HOG cascade.
引用
收藏
页数:5
相关论文
共 16 条
[1]  
[Anonymous], 231009 U OXF
[2]  
[Anonymous], 2010, BRIT MACH VIS C AB U
[3]  
[Anonymous], P IEEE INT VEH S PAR
[4]  
[Anonymous], C COMP VIS PATT REC
[5]  
[Anonymous], 2009, PETS 2009 11 IEEE IN
[6]  
[Anonymous], INT C COMP VIS ICCV
[7]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[8]  
Ellis A., 2009, 12 IEEE INT WORKSH P
[9]  
Hu W., 2004, IEEE Trans, on Systems, Man, and Cybernetics, V34
[10]  
Kasturi R., 2009, FRAMEWORK PERFORMANC