Search

Increasingly recognized in biological psychiatry, rodent self-grooming is a complex patterned behavior with evolutionarily conserved cephalo-caudal progression. While grooming is traditionally assessed by the latency, frequency and duration, its sequencing represents another important domain sensitive to various experimental manipulations. Such behavioral complexity requires novel objective approaches to quantify rodent grooming, in addition to time-consuming and highly variable manual observation. The present study combined modern behavior-recognition video-tracking technologies (CleverSys, Inc.) with manual observation to characterize in-depth spontaneous (novelty-induced) and artificial (water-induced) self-grooming in adult male C57BL/6J mice. We specifically focused on individual episodes of grooming (paw licking, head washing, body/leg washing, and tail/genital grooming), their duration and transitions between episodes. Overall, the frequency, duration and transitions detected using the automated approach significantly correlated with manual observations (R=0.51-0.7, p

Development of various multimedia applications is dependent on the availability of fast and efficient storage, browsing, indexing, and retrieval techniques. Given that video is stored efficiently in a compressed format, the costly overhead of decompression can be avoided by analyzing the compressed representation directly. We describe techniques that can be used to extract viable features for indexing shots of video directly from the compressed domain. We develop a type independent representation of frames present in an MPEG video and show how it can be used directly for indexing.

Automated classification of digital video is emerging as an important piece of the puzzle in the design of content management systems for digital libraries. The ability to classify videos into various genres such as sports, news, movies, or documentaries increases the efficiency of indexing, browsing, and retrieval of video in large databases. In this paper, we present an automated technique for identifying slow-motion replays directly from the compressed domain of MPEG video. It uses the macroblock, motion, and bit-rate information that is readily accessible from MPEG video with very minimal decoding, leading to enormous gains in processing speeds.

Fast and efficient storage, indexing, browsing, and retrieval of video is a necessity for the development of various multimedia database applications. This can be achieved by analyzing the video directly in the compressed domain, thereby avoiding the overhead of decompressing video into individual frames in the pixel domain. Our compressed domain parsing of video performs shot change detection and motion detection using the data readily accessible from MPEG, with minimal decoding. Key frames are identified and are used for indexing, retrieval, and browsing. In this paper, we describe feature extraction and key frame indexing and retrieval techniques that are directly applicable to compressed video. The features are derived form the available DCT, macroblock, and motion vector information and the techniques enable fast parsing and archiving of video.

Segmentation of video into shots and scenes in the compressed domain allows rapid real-time analysis of video content using standard hardware. This paper presents robust techniques for parsing MPEG-compressed video sequences into shots based on their physical structure and further into scenes based on their semantic structure by identifying changes in content and camera motion. The analysis is performed in the compressed domain using available macroblock and motion vector information, and if necessary, discrete cosine transform (DCT) information. Motion vector analysis yields a qualitative description of the camera motion and is used to subdivide shots into subshots. Key frames for the shots and scenes can be used for browsing, indexing, and retrieval.

The problem of determining the physical and semantic structure of an extended video sequence is essential for providing appropriate processing, indexing and retrieval capabilities for video databases. In this paper, we describe a novel technique which reduces a sequence of MPEG encoded video frames to a trail of points in a low dimensional space. In thii space, we can cluster frames, analyze transitions between clusters and compute properties of the resulting trail. By classifying portions of the trail as either stationary or transitional, we are able to detect gradual edits between shots. Furthermore, tracking the interaction of clusters over time, we lay the groundwork for the complete analysis and representation of the video’s physical and semantic structure.