Efficient and reliable digital media archive for content-based retrieval

Abstract

Recent years have witnessed a significant price reduction in many enabling technologies for wide-spread deployment of multimedia to desktop PCs and workstations. This advancement has lead to an increasing demand for systems that can store, retrieve, and manipulate large volumes of multimedia information. For a multimedia information system to better meet information users' needs, it must provide suitable access structures and methods. The answers to this demand fall into the research area of what most people called content-based multimedia indexing and retrieval. Existing approaches to content-based indexing and retrieval have limitations. What we need is a digital-media-archiving system that is both efficient and reliable. By reliable, we mean that users should be able to retrieve documents that have the most potential for being relevant to their queries. On the other hand, an efficient digital-media-archiving system should provide an environment that allows human operators to create document indices without the need to manually watch every multimedia object and enter keyword descriptions. This can be done by providing initial structure information of the video to the user, by guiding the human operator through the indexing process, and by offering tools to create multiple media representations in a hierarchical structure.

Smart VideoText: a video data model based on conceptual graphs

“…One of the earliest annotation-based models is the stratification model proposed by Davenport et al [3,25], which is based on the idea of annotation layering. Other annotationbased models, such as the generic video data model [7] and the Algebraic Video model [30], have been developed since then, while recent techniques [16] use hybrid methods (i.e. segmentation and anotation) for better content-based video indexing.…”

Optimal nonlinear sampling for video streaming at low bit rates

“…Specifically, the accumulative score AcuScore for the th frame can be calculated as (6) At the end, we only need to compare the accumulated scores at the last frames and pick the largest. Backtracking from there shall then reveal the optimal set of key-frames to be selected.…”

“…To facilitate such a streaming task over low-bit-rate channels, two issues shall be addressed: 1) the quantitative analysis of the semantic saliency of each video frame, which is part of an ongoing research effort actively pursued by the signal processing, computer vision, speech, and natural language understanding, and 2) information retrieval communities [6], [7]. Assuming the quantitative saliency assessment of each frame is available, the other issue is: for a low bandwidth and a limited buffer size on the client side, how do we find a streamable (i.e., no buffer overflow/underflow) sequence of frames whose accumulated information (or "saliency score") is maximal?…”

Content-sensitive video streaming over low bitrate and lossy wireless network

“…Our automatic cOntent analysis system automatically detects cuts and selects the first frame in each shot as a keyframe with priority one (the most important) ranking. Readers who are interested in the details of the cut detection algorithm should refer to [5] for more information.…”