The Community for Technology Leaders
2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (2013)
Krakow, Poland
Aug. 27, 2013 to Aug. 30, 2013
ISBN: 978-1-4799-0703-8
pp: 141-146
Yiliang Xu , Kitware Inc
Sangmin Oh , Kitware Inc
Fan Yang , Dept. of Computer Science, Univ. of Maryland at College Park
Zhuolin Jiang , Dept. of Computer Science, Univ. of Maryland at College Park
Naresh Cuntoor , Kitware Inc
Anthony Hoogs , Kitware Inc
Larry Davis , Dept. of Computer Science, Univ. of Maryland at College Park
ABSTRACT
In this work, we present a framework to detect objects embedded in complex perspective geometry. Our goal is to accurately identify objects such as people standing in balconies or windows on building facades of surrounding buildings. Compared to traditional computer vision work focused on activity analysis from a horizontal view, our framework provides a solution for the application domain of mobile surveillance in urban areas. A novel solution for a monocular camera is formulated by tightly coupling various computational modules including geometric analysis, segmentation, scale estimation, and object detection. In particular, our proposed approach alleviates the effect of the perspective geometry and corresponding distortion in object appearance effectively, and provides accurate scale priors to eliminate unlikely object detection hypotheses. The experimental results on collected video dataset show that the proposed approach is more accurate than traditional detection approaches based on brute-force scanning windows.
INDEX TERMS
Cameras, Buildings, Geometry, Object detection, Image segmentation, Surveillance, Estimation
CITATION

Y. Xu et al., "System and algorithms on detection of objects embedded in perspective geometry using monocular cameras," 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance(AVSS), Krakow, Poland Poland, 2013, pp. 141-146.
doi:10.1109/AVSS.2013.6636630
95 ms
(Ver 3.3 (11022016))