Abstract
Users must quickly and effectively classify, browse, and retrieve videos due to the explosive growth of video data. A variety of shots make up the video data stream. The most important technology in video retrieval is shot detection, which can fundamentally solve many problems, resulting in improved detection effects and even directly affecting video retrieval performance. This paper investigates the shot transition detection algorithm in digital video live broadcasts based on sporting events. To solve the problem of shot transition detection using a single training sample, an AMNN (Associative Memory Neural Network) model with online learning ability is proposed. Experiments on a large football video data set show that this algorithm detects shear and gradual change better than existing algorithms and meets the application requirements of sports video retrieval in most cases.
Highlights
Among the many new forms of communication, video has the most content, and it can provide a wide range of information that is more specific, rich, and vivid than text, sound, or image [1]
Keyframes should be able to reflect the main movements and changes in shots. e lens is the continuous image frame recorded by the camera from opening to closing, and it is the smallest physical unit in the video
The middle-level features proposed in this paper obviously improve the performance of the shot transition detection algorithm
Summary
Among the many new forms of communication, video has the most content, and it can provide a wide range of information that is more specific, rich, and vivid than text, sound, or image [1]. Shot transition detection in sports video is the most difficult application field [2, 3]. AMNN (Associative Memory Neural Network), as a shot change detection method, has certain advantages. It can acquire the implicit expression of the rules and rules of shot change detection through learning. In the keyframe extraction and content-based video retrieval, it is necessary to switch the detection shot. A discrete Hough transform based on a feedforward neural network [8] is used, and for recognition and classification, a third-order AMNN based on mean-field theory is used. The BPNN (BP neural network) connection weight has a direct impact on the detection effect of shot transition in sports video [9]. Wireless Communications and Mobile Computing method, pixel-based method, motion feature method, and others. is paper examines the detection algorithm for shot transition in sports video based on sporting events
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
