Year: 2008
Type: article
Abstract: This paper presents methods for moving object detection in airborne video surveillance. The motion segmentation in the\nabove scenario is usually difficult because of small size of the object, motion of camera, and inconsistency in detected\nobject shape etc. Here we present a motion segmentation system for moving camera video, based on background\nsubtraction. An adaptive background building is used to take advantage of creation of background based on most recent\nframe. Our proposed system suggests CPU efficient alternative for conventional batch processing based background\nsubtraction systems. We further refine the segmented motion by meanshift based mode association.
Authors: G. Santhosh Kumar, K Ratheesh, Supriya Rao
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2111691507