Robust Detection Technique for Abandoned Objects to Overcome Visual Occlusion

다국어 초록 (Multilingual Abstract)

Nowadays it is required to design intelligent visual surveillance systems which automatically detect abandoned objects in public places to strengthen the social safety. Already recognized abandoned objects can be occluded partially or fully by surrounding people in public places after the first recognition. To improve an essential recognition performance index PAT, the system should overcome the occlusion problems. In this research, a design scheme is newly proposed to construct the robust detection system which is comprised of multiple stages considering the occlusion problem. To show the feasibilities of the proposed system, the evaluation was tried for the prepared image streams including 6 various situations and the experimental results show 96% and 75% in PAT performance for intrusion and abandoning events, respectively. Finally in spite of full occlusions by multiple persons, the proposed system shows the capability to continuously recognize the abandoned object after complex occlusions disappear.

참고문헌 (Reference)

1 I. Haritaoglu, "W4 : Real-Time Surveillance of People and Their Activities" 22 (22): 2000

2 F. Porikli, "Robust Abandoned Object Detection Using Dual Foregrounds" 2008

3 N. Bird, "Real Time, Online Detection of Abandoned Objects in Public Areas" 2006

4 K. Mikolajczyk, "Human detection based on a probabilistic assembly of robust part detectors" 69-81, 2004

5 N. Dalal, "Histograms of oriented gradients for human detection" 886-893, 2005

6 A. Mohan, "Example-based object detection in images by components" 349-361, 2001

7 P. Viola, "Detecting pedestrians using patterns of motion and appearance" 734-741, 2003

8 김원, "Automatic Detection System for Dangerous Abandoned Objects Based on Vision Technology" 한국인터넷방송통신학회 9 (9): 69-74, 2009

9 W. Hu, "A Survey on Visual Surveillance of Object Motion and Behaviors" 34 (34): 2004

10 김원, "A Smart Visual Surveillance System with Human Recognition for Enhanced Detection of Abandoned Objects" 한국정보기술학회 8 (8): 209-214, 2010

11 J. Kong, "A Novel Background Extraction and Updating Algorithm for Vehicle Detection and Tracking"