Video retrieval using salient foreground region of motion vector based extracted keyframes and spatial pyramid matching
- PDF / 3,281,801 Bytes
- 28 Pages / 439.642 x 666.49 pts Page_size
- 54 Downloads / 175 Views
Video retrieval using salient foreground region of motion vector based extracted keyframes and spatial pyramid matching Ajay Kumar Mallick1
· Susanta Mukhopadhyay1
Received: 19 September 2019 / Revised: 13 June 2020 / Accepted: 9 July 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Despite enormous research efforts devoted by the research community to effectively and precisely perform video matching and retrieval among heterogeneous videos from largescale video repositories still remains a complex and most challenging task. In order to address this complex challenge, a content based video retrieval technique is required, which can exploit the visual content of the videos for effective retrieval from the videos repositories. In our proposed method, we introduce a computer assisted video retrieval technique which can retrieve the visually similar videos stored in the repositories. To accomplish this task, video summarization based on motion vector is employed to select keyframes based on similar segments. To estimate the video content, salient foreground extraction is executed, and matching based on the spatial pyramid is employed for matching the keyframe features of query video with videos in the repositories. The contribution of the former process has two major sections for superior saliency map generation. Firstly, it heuristically integrates the regional property, contrast, and foreground descriptors together. Secondly, it introduces a new feature vector to characterize the foreground as an object descriptor, while the latter process is the extension of orderless bag-of-features representation, which has significant performance with respect to scene categorization. The video retrieval performance is compared with standard state-of-the-art techniques using real-time datasets. Experimental and usability studies provide satisfactory results for video retrieval based on evaluation metrics such as video sampling error, fidelity, precision, and recall. Keywords Content based video retrieval · Estimation of motion vector · Key frame extraction · Outlier detection · Pyramid matching · Saliency region detection
Ajay Kumar Mallick
[email protected] Susanta Mukhopadhyay [email protected] 1
Department of Computer Science and Engineering, Indian Institute of Technology (ISM), Dhanbad, 826004, Jharkhand, India
Multimedia Tools and Applications
1 Introduction Execution of complex multimodal digital data for analysis and retrieval is a real challenge. Among the various form of the multimedia data, video is the most imperative. Video retrieval needs a scheme that can quickly index these varied and huge data content. Keyframes of video are primary, as well as essential information. To analyze and index video summarization for its effective application, comprehensive reduction of the data as keyframes is essential to comprehensibly represent the video content as illustrated in Kernel Locality Sensitivity Discriminative Sparse Representative (KLSDSR) [5] method which employ
Data Loading...
