Abstract
This paper presents an object occlusion detection algorithm using object depth information that is estimated by automatic camera calibration. The object occlusion problem is a major factor to degrade the performance of object tracking and recognition. To detect an object occlusion, the proposed algorithm consists of three steps: (i) automatic camera calibration using both moving objects and a background structure; (ii) object depth estimation; and (iii) detection of occluded regions. The proposed algorithm estimates the depth of the object without extra sensors but with a generic red, green and blue (RGB) camera. As a result, the proposed algorithm can be applied to improve the performance of object tracking and object recognition algorithms for video surveillance systems.
Highlights
The demand for object tracking and recognition algorithms is increasing due to video surveillance
The proposed object occlusion detection algorithm consists of three steps: (i) automatic camera calibration; (ii) object depth estimation; and (iii) occlusion detection
We show the results of the proposed automatic camera calibration and object occlusion detection algorithms
Summary
The demand for object tracking and recognition algorithms is increasing due to video surveillance. Since a stereo camera-based occlusion detection method needs an additional camera, it is not easy to implement in an already installed wide-area surveillance system To solve this problem, single camera based depth map estimation methods were proposed. Im et al proposed a single red, green, and blue (RGB) camera-based object depth estimation method using multiple color-filter apertures (MCA) [5]. Song’s method cannot avoid the camera calibration error when feature points change while the object is moving To solve these problems, the proposed method first performs automatic camera calibration using both moving objects and background structures to estimate camera parameters. Accuracy of the camera calibration result depends on the object detection results To solve these problems, the proposed algorithm combines the background structure lines with human foot and head information to estimate vanishing points and lines.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.