Title :
Scene segmentation based on video structure and spectral methods
Author :
Zhang, Zhenyuan ; Li, Bin ; Lu, Hong ; Xue, Xiangyang
Author_Institution :
Sch. of Comput. Sci., Fudan Univ., Shanghai
Abstract :
Scene is an important semantic unit for video analysis, retrieval and browsing. However, due to the lack of a generic algorithm, many studies focus on specific methods for certain video genes, e.g., news, sports, etc. In this paper, we propose a general framework for scene segmentation. First, we construct a graph, in which the elements encode the shot-to-shot coherent characteristics of a video clip based on visual similarity and temporal relation between shots. In this step, we only exploit the inherent property of video itself and it is independent of video genres. Second, spectral method is applied on the graph to group shots into scenes. The proposed method is not only simple but also effective to deal with organized features. Experimental results validate the robustness of our method on different kinds of videos.
Keywords :
image segmentation; video retrieval; video signal processing; scene segmentation; semantic unit; shot-to-shot coherent characteristics; spectral method; video analysis; video browsing; video clip; video retrieval; video structure; visual similarity; Automatic control; Computer science; Hidden Markov models; Layout; Motion detection; Robot control; Robot vision systems; Robotics and automation; Robustness; TV; JSEG; scene segmentation; spectral methods; video structure;
Conference_Titel :
Control, Automation, Robotics and Vision, 2008. ICARCV 2008. 10th International Conference on
Conference_Location :
Hanoi
Print_ISBN :
978-1-4244-2286-9
Electronic_ISBN :
978-1-4244-2287-6
DOI :
10.1109/ICARCV.2008.4795672