Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1995 · 180 citations · 0 references
ComputingComputer ScienceComputer VisionMachine VisionStatistical ComputingChange DetectionData CompressionImage CompressionImage SegmentationScene ChangesVideo AnalysisCut PointsDigital Video ArchivingExperimental Results InterpretationShot Boundary DetectionVideo CompressionVideo Scene UnderstandingVideo Segmentation
Video databases require organization, and segmenting videos into clips with characterizations is one strategy that demands automatic cut‑point detection, typically by locating boundaries between consecutive camera shots. The study formulates cut‑point detection as a statistical hypothesis‑testing problem and proposes three tests to identify scene changes. These tests are designed to operate directly on compressed video, avoiding the need for decompression. Experiments show that this method eliminates decompression steps and accurately detects scene changes from both straight and optical cuts.
One of the challenging problems in video databases is the organization of video information. Segmenting a video into a number of clips and characterizing each clip has been suggested as one mechanism for organizing video information. This approach requires a suitable method to automatically locate cut points in a video. One way of finding such cut points is to determine the boundaries between consecutive camera shots. In this paper, we address this as a statistical hypothesis testing problem and present three tests to determine cut locations. All the three tests are such that they can be applied directly to the compressed video. This avoids an unnecessary decompression-compression cycle, since it is common to store and transmit digital video in compressed form. As our experimental results indicate, the statistical approach permits accurate detection of scene changes induced through straight as well as optical cuts.