L.-H. Chen, B.-C. Hsu, and H.-Y.M. Liao (Taiwan)
Video content analysis, supervised learning, support vector machine.
Shot boundary detection is a fundamental step of video in dexing. One crucial issue of this step is the discrimination of abrupt shot change from flashlight, because flashlight of ten induces a false shot boundary. Support vector machine (SVM) is a supervised learning technique for data classifi cation. In this paper, we propose a SVM based technique to detect flashlights in video. Our approach to flashlight detection is based on the facts that the duration of flash light is short and the video contents before and after a flash light should be similar. So we design a sliding window in temporal domain to monitor the instantaneous video vari ation and extract color and edge features to compare the visual contents between two video segments. Then, a sup port vector machine is employed to classify the luminance variation into flashlight or shot cut. Experimental results indicate that the proposed approach is effective and outper forms some existing techniques.
Important Links:
Go Back
