SVARS: symbolic video archival and retrieval system
ABSTRACT In this paper, we present a novel approach for higher level semantic video archival and retrieval based on symbolic representation. Topological triangular spatial relationship has been introduced to study the higher level relationship (spatial and topological) among the objects in a frame. A two dimensional time series representation to preserve the variations in relationship among objects across frames is also proposed. A modification is recommended to make Dynamic Time Wrapping (DTW) suit for matching and retrieval of symbolic videos. To corroborate the efficacy of the proposed method an experimentation has been carried out on sports videos and results are encouraging.
Article: Information retrieval[Show abstract] [Hide abstract]
ABSTRACT: Information retrieval (IR) is concerned with the structure, analysis, organization, storage, searching, and dissemination of information. An IR system is designed to make a given stored collection of information items available to a user population. At one time that information consisted of stored bibliographic items, such as online catalogs of books in a library or abstracts of scientific articles. However, in today's world, the information is more likely to be full-length documents, either stored in a single location, such as newspaper archives, or available in a widely distributed form, such as the World Wide Web (WWW).
Conference Paper: Topological triangular spatial relationship[Show abstract] [Hide abstract]
ABSTRACT: In this paper, we present a novel scheme for archival and retrieval of symbolic images from a symbolic image database based on Triangular Spatial Relationship . Conventionally, Triangular Spatial Relationship was designed to preserve only spatial relationship among the components in a symbolic image neglecting the topological relationship existing between them, where topological relationship plays a major role in preserving the structure of the symbolic image. Hence in this paper we extend the concept of Triangular Spatial Relationship to Topological Triangular Spatial Relationship. The proposed can handle both spatial as well as topological relationships existing among the components present in the image which is suitable for high level image archival and retrieval. Also, we propose a new similarity measure which takes care of both spatial as well as topological relation for similarity match retrieval and is invariant to image transformations. To study the efficacy of the proposed method we have conducted experimentation on video frames of cartoon film and on a set of personal photographs taken during outings..Indian International Conference on Artificial Intelligence (IICAI); 01/2009
- [Show abstract] [Hide abstract]
ABSTRACT: In this paper, we propose a new knowledge structure called 3D Z-string, extended from the 2D Z-string, to represent the spatial and temporal relations between objects in a video and to keep track of the motions and size changes of the objects. Since there are no cuttings between objects in the 3D Z-string, the integrity of objects is preserved. The string generation and video reconstruction algorithms for the 3D Z-string representation of video objects are also developed. The string generated by the string generation algorithm is unique for a given video and the video reconstructed from a given 3D Z-string is unique too. The experimental results show that the 3D Z-string is more compact and efficient than the 3D C-string in terms of storage space and execution time.Pattern Recognition Letters 12/2005; DOI:10.1016/j.patrec.2005.04.018 · 1.55 Impact Factor