영상 내 사람의 검출을 위한 에지 기반 방법
Edge-based Method for Human Detection in an Image
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Human sensing is an important but challenging technology. Unlike other methods for sensing humans, a vision sensor has manyadvantages, and there has been active research in automatic human detection in camera images. The combination of Histogram of Ori-ented Gradients (HOG) and Support Vector Machine (SVM) is currently one of the most successful methods in vision-based humandetection. However, extracting HOG features from an image is computer intensive, and it is thus hard to employ the HOG method inreal-time processing applications. This paper describes an efficient solution to this speed problem of the HOG method. Our methodobtains edge information of an image and finds candidate regions where humans very likely exist based on the distribution pattern ofthe detected edge points. The HOG features are then extracted only from the candidate image regions. Since complex HOG processingis adaptively done by the guidance of the simpler edge detection step, human detection can be performed quickly. Experimental resultsshow that the proposed method is effective in various images.
Abstract
Human sensing is an important but challenging technology. Unlike other methods for sensing humans, a vision sensor has manyadvantages, and there has been active research in automatic human detection in camera images. The combination of Histogram of Ori-ented Gradients (HOG) and Support Vector Machine (SVM) is currently one of the most successful methods in vision-based humandetection. However, extracting HOG features from an image is computer intensive, and it is thus hard to employ the HOG method inreal-time processing applications. This paper describes an efficient solution to this speed problem of the HOG method. Our methodobtains edge information of an image and finds candidate regions where humans very likely exist based on the distribution pattern ofthe detected edge points. The HOG features are then extracted only from the candidate image regions. Since complex HOG processingis adaptively done by the guidance of the simpler edge detection step, human detection can be performed quickly. Experimental resultsshow that the proposed method is effective in various images.
참고문헌 (11)
- 권성열, "P(VDF", TrFE) 필름의 두께에 따른 인체 감지형 초전형 PIR 적외선 센서의 특성, 2011, pp.20(2), 114~117[DOI]
- J. R. Choi, "Pyroelectric infrared microsensors made for human body detection", J. Sensor Sci. & Tech, 7(2), pp.21~28 (1998)
- A. Lipton, "Moving target classification and tracking from real-time video", Proc. IEEE Workshop Applications of Computer Vision, pp.8~14 (1998)
- H. Fujiyoshi, "Real-time human motion analysis by image skeletonization", Proc. IEEE Workshop Applications of Computer Vision, pp.15~21 (1998)
- Y. Do, "Counting people from image sequences", Proc. Int. Conf. on Imaging Sci., System &Tech., 1, pp.185~190 (2000)
- D. M. Gavrila, "Shape-based pedestrian detection and tracking", Proc. IEEE Intelligent Vehicle Symposium, pp.8~14 (2002)
- T. N. Duc, "Human detection based on weighted template matching", Proc. IEEE Conference on Multimedia and Expo, pp.634~637 (2009)
- N. Dalal, "Histograms of oriented gradients for human detection", Proc. Computer Vision and Pattern Recognition, pp.886~893 (2005)
- V. Vapnik, "Pattern recognition using generalized portrait method", Automation and Remote Control, 24, pp.774~780 (1963)
- G. Xu, "Real-time pedestrian detection based on edge factor and Histogram of Oriented Gradient", Proc. IEEE Conference on Information and Automation, pp.384~389 (2011)