Abstract
This chapter describes a moving object detection-and-localization method based on forward-backward motion history images (MHIs). Detecting moving objects automatically is a key component of an automatic visual surveillance and tracking system. In airborne thermal video especially, the moving objects may be small, color information is not available, and intensity appearance may be camouflaged. Although it is challenging for an appearance-or shape-based detector to detect the small objects in thermal images, pixel-level change detection or optical flow can provide powerful motion-based cues for detecting and localizing the objects. Previous motion detection approaches often use background subtraction, interframe difference, or three-frame difference, which are either costly or can only partially detect the object. We propose an MHI-based method that can accurately detect location and shape of moving objects for initializing a tracker or recovering from tracking failure. The effectiveness of this method is quantified using long and varied video sequences.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
