Browse > Article
http://dx.doi.org/10.5302/J.ICROS.2009.15.5.505

Dividing Occluded Humans Based on an Artificial Neural Network for the Vision of a Surveillance Robot  

Do, Yong-Tae (대구대학교 전자공학부)
Publication Information
Journal of Institute of Control, Robotics and Systems / v.15, no.5, 2009 , pp. 505-510 More about this Journal
Abstract
In recent years the space where a robot works has been expanding to the human space unlike traditional industrial robots that work only at fixed positions apart from humans. A human in the recent situation may be the owner of a robot or the target in a robotic application. This paper deals with the latter case; when a robot vision system is employed to monitor humans for a surveillance application, each person in a scene needs to be identified. Humans, however, often move together, and occlusions between them occur frequently. Although this problem has not been seriously tackled in relevant literature, it brings difficulty into later image analysis steps such as tracking and scene understanding. In this paper, a probabilistic neural network is employed to learn the patterns of the best dividing position along the top pixels of an image region of partly occlude people. As this method uses only shape information from an image, it is simple and can be implemented in real time.
Keywords
video surveillance and monitoring (VSAM); security robot; occlusion; probabilistic neural network;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 A. J. Sindhu and T. Morris, 'A region based approach to tracking people before, during, and after occlusions,' Proc. lASTED Int. Conf. Visualization, Imaging, and Image Processing, 2004
2 Z. Lin et aI., 'Simultaneous appearance modeling and segmentation for matching people under occlusion,' Proc. Asian Coriference on Computer Vision, pp. 404-413, 2007
3 J. P. Batista, 'Tracking pedestrians under occlusion using multiple cameras,' Lecture Notes in Computer Science, vol. 3212, pp. 552-562,2004   DOI   ScienceOn
4 J. Heikkila and O. Silven, 'A real-time system for monitoring cyclists and pedestrians,' Proc. IEEE Workshop on Visual Surveillance, pp. 74-81,1999   DOI
5 P. D. Z. Varcheie, M. Sills-Lavoie, and G-A. Bilodeau, 'An efficient region-based background subtraction technique,' Proc. Canadian Conf. Computer and Robot Vision (CRV), pp. 71-78, 2008   DOI
6 W. Abd-Almageed, B. J. Bums, and L. S. Davis, 'IdentifYing and segmenting human-motion for mobile robot navigation using alignment errors,' Proc. Int. Conf. Advanced Robotics (lCAR), pp. 398-403, 2005
7 박수우, 김정대, 도용태, '비디오 카메라 영상 내 동적물체의 그림자 화소 검출 기법,' 멀티미디어학회논문지, 제8권 제10호, pp. 1314-1321,2005
8 I. Haritaoglu, D. Harwood, and L. S. Davis, 'W4: Who? When? Where? What? A real time system for detecting and tracking people,' Proc. Int. Conf. Face and Gesture Recognition, pp. 222-227,1998
9 D. E. Specht, 'Probabilistic neural networks for classification, mapping, or associate memory,' Proc. IEEE Int. Conf Neural Networks, vol. 1, pp. 525-532, 1988   DOI
10 S. Khan and M. Shah, 'Tracking people in presence of occlusion,' Proc. of Asian Conf. Computer Vision, 2000
11 E. Parzen, 'On estimation of a probability density function and mode,' Annals of Mathematical Statistics, vol. 33, pp. 1065- 1076,1962   DOI   ScienceOn
12 T. Kanade, R. T. Collins, and A. J. Lipton, 'Advances in cooperative multi-sensor video surveillance,' Proc. of Image Understanding Workshop, pp. 3-24, 1998
13 A. Treptow, G. Cielniak, and T. Duckett, 'Active people recognition using thennal and grey images on a mobile security robot,' Proc. IEEElRSJ Int. Conf. Intelligent Robots and Systems (lROS), pp. 2103-2108, 2005
14 J. Barandiaran, B. Murguia, and F. Boto, 'Real-time people counting using multiple lines,' Proc. Int. Workshop on Image Analysis for Multimedia Interactive Services, pp. 159-162, 2008   DOI
15 A. T. C. Goh, 'Probabilistic neural network for evaluating seismic liquefaction potential,' Canadian Geotechnical Jounal, vol. 39, no. 1, pp. 219-232, 2002   DOI   ScienceOn