Springer Science & Business Media, Aug 31, 2003 - Computers - 340 pages
Traditionally, scientific fields have defined boundaries, and scientists work on research problems within those boundaries. However, from time to time those boundaries get shifted or blurred to evolve new fields. For instance, the original goal of computer vision was to understand a single image of a scene, by identifying objects, their structure, and spatial arrangements. This has been referred to as image understanding. Recently, computer vision has gradually been making the transition away from understanding single images to analyzing image sequences, or video Video understanding deals with understanding of video understanding. sequences, e.g., recognition of gestures, activities, facial expressions, etc. The main shift in the classic paradigm has been from the recognition of static objects in the scene to motion-based recognition of actions and events. Video understanding has overlapping research problems with other fields, therefore blurring the fixed boundaries. Computer graphics, image processing, and video databases have obvi ous overlap with computer vision. The main goal of computer graphics is to generate and animate realistic looking images, and videos. Re searchers in computer graphics are increasingly employing techniques from computer vision to generate the synthetic imagery. A good exam pIe of this is image-based rendering and modeling techniques, in which geometry, appearance, and lighting is derived from real images using computer vision techniques. Here the shift is from synthesis to analy sis followed by synthesis. Image processing has always overlapped with computer vision because they both inherently work directly with images.
What people are saying - Write a review
We haven't found any reviews in the usual places.
EFFICIENT VIDEO BROWSING Using Multiple Synchronized Views
BEYOND KEYFRAMES THE PHYSICAL SETTING AS A VIDEO MINING PRIMITIVE
TEMPORAL VIDEO BOUNDARIES
VIDEO SUMMARIZATION USING MPEG7 MOTION ACTIVITY AND AUDIO DESCRIPTORS A Compressed Domain Approach to Video Brows...
MOVIE CONTENT ANALYSIS INDEXING AND SKIMMING VIA MULTIMODAL INFORMATION
VIDEO OCR A SURVEY AND PRACTITIONERS GUIDE
VIDEO CATEGORIZATION USING SEMANTICS AND SEMIOTICS
Other editions - View all
acoustic algorithm analysis audio automatically base similarity metric boundaries camera classified clips clustering color histogram combination commercial computed computer vision content-based corresponding cues described detection detector dialog distance documents domain episode evaluate example extraction family histograms film filter Gaussian genres ground truth HHMM hidden Markov models hierarchical identify IEEE key frames key-frame label learning Lienhart Markov blanket matching matrix method model vectors mosaics motion activity movie MPESAR multimedia multiple parameters performance physical settings pixels query ratio recognition relevant represent representation sampling scale scale-space scale-space segmentation scene Section selected semantic space shot shown in Figure shows signal sitcom skim speaker identification speech recognition speech segments speedup story strongly connected component structure summarization techniques temporal text line threshold tion topic track transcript unsupervised unsupervised learning video browsing video indexing video retrieval video segment video summaries visual