期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：3
页码：5044
DOI：10.15680/IJIRSET.2017.0603305
出版社：S&S Publications
摘要：In the compressed video is transmitted over a communication network and analyzed by a server. Theserver includes key point detection, descriptor calculation, and feature matching. Video compression has negative effecton image feature matching performance. The negative impact of compression can be minimized by using the key pointsextracted from the uncompressed video to calculate descriptors from the compressed video. The proposed systemprovides these key points to the server as side information and to extract only the descriptors from the compressedvideo. First, we introduce four different frame types for key point encoding to address different types of changes invideo content. These frame types represent a new scene, the same scene, a slowly changing scene, or a rapidly movingscene, and are determined by comparing features between successive video frames. Intra skip and inter modes ofencoding the key points for different frame types. For example, key points for new scenes are encoded using the Intramode and key points for unchanged scenes are skipped. As a result, the bitrate of the side information related to keypoint encoding is significantly reduced. Finally, present pair wise matching and image retrieval experiments conductedto evaluate the performance of the proposed approach using the Stanford mobile augmented reality dataset and 720pformat videos. The results show that the proposed approach offers significantly improved feature matching and imageretrieval performance at a given bitrates.
