This article presents an automatic video editing method for video stream selection in a multi-camera environment. The specific context of this study is Basketball game recording and broadcasting. In order to offer the best view to spectator our method is based on action detection in order to select the right camera. We use an azimuth camera to detect the center of gravity of the players representing the action in the match. The effectiveness of our method has been tested by comparing the editing obtained with that carried out by a human operator.
Abstract-We propose a novel method for the localization and the identification of a speaker in the context of conference situations. For doing this, LED lights attached to the microphones are used as visible light communications transmitters. Once the speaker activate the microphone, LED transmits the speaker identification. At the receiver side, LED lights are identified and separated from video streams acquired by a low cost IP CMOS camera. Then, identification of the speaker is performed by recovering the data from the separated image. Results in terms of BER acquired from experimental demonstration are presented for different distances between the camera and the light source, i.e., 35 cm, 1, 2 and 5 meters.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.