USING HOG FOR VIDEO-BASED HUMAN DETECTION FOR IN-BUILDING EMERGENCY RESPONSE
Albert. Y. Chen.1 and Cheng-Yi Chang2
1) Assistant Professor, Department of Civil Engineering, National Taiwan University, Taipei, Taiwan.
2) Graduate Research Assistant, Department of Civil Engineering, National Taiwan University, Taipei, Taiwan.
Abstract: Human detection and tracking is an important application in intelligent transportation systems. In this paper, we present an approach for people tracking and counting to be used in in-building emergency situations. By combining the Histograms of Oriented Gradients (HOG) detection with background subtraction, the detection algorithm could achieve a more rapid and accurate detection. The Kalman Filter is utilized for the establishment of human trajectory tracking. The automated pedestrian counting system for in-building emergency response has shown its potential with the presented tracking results.
Keywords: human detection, HOG, people counting, background subtraction
Albert. Y. Chen. and Cheng-Yi Chang. “USING HOG FOR VIDEO-BASED HUMAN DETECTION FOR IN-BUILDING EMERGENCY RESPONSE.” In Proceedings of International Conference on Civil and Building Engineering Informatics (ICCBEI 2015), 107. Tokyo, Japan, 2015.