DC-Image for Real Time Compressed Video Matching

Abstract

This chapter presents a suggested framework for video matching based on local features extracted directly from the DC-image of MPEG compressed videos, without full decompression. In addition, the relevant arguments and supporting evidences are discussed. Several local feature detectors will be examined to select the best for matching using the DC-image. Two experiments are carried to support the above. The first is comparing between the DC-image and I-frame, in terms of matching performance and computation complexity. The second experiment compares between using local features and global features regarding compressed video matching with respect to the DC-image. The results confirmed that the use of DC-image, despite its highly reduced size, is promising as it produces higher matching precision, compared to the full I-frame. Also, SIFT, as a local feature, outperforms most of the standard global features. On the other hand, its computation complexity is relatively higher, but it is still within the real-time margin which leaves a space for further optimizations that could be done to improve this computation complexity.