Paper Details: Downloads: 530
Serial Number: P1151223208
Title: Image Fusion Based Video Content Enhancement for Surveillance and Tracking
Authors: Melih Altun and Mehmet Celenk
Abstract: This paper describes a surveillance video content enhancement and object tracking method using multi-spectral image data fusion and optical flow. Multi-spectral video in this context consists of the visual and infrared (IR) bands. Although the implementation described herein focuses on these two distinct bands, the algorithm is sufficiently general to be applied to remotely sensed videos in arbitrarily selected bands. The method integrates visual and IR information by detecting changes in the scene under surveillance. The foreground regions are then selected as candidate regions for image fusion. By comparing the edges detected in the foreground with the ones detected in the estimated background the method determines occluded regions; hence, recovery is sought via information available in IR images. This approach uses IR information only where necessary and preserves visual information in all other regions. To highlight the objects of interest foreground regions in the IR frames are clustered and marked with bounding boxes in the resultant fused image. The motions of these detected objects are tracked using optical fusion.
Keywords: Image Fusion, Video Content Enhancement, Edge Detection, Background Extraction, Optical Flow, Occlusion Detection, Surveillance
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 12
Issue: 2
Submission Date: 6/1/2012 12:00:00 AM
Review Date: 6/3/2012 12:00:00 AM
Publishing Date: 6/9/2012 12:00:00 AM
Article Downloads: 530
Download:

Facebook