Study on the Detection of Moving Target in the Mining Method Based on Hybrid Algorithm for Sports Video Analysis

• Main Authors: Huang Tian, Wang Xiao Jun
• Format: Article
• Language: English
• Published: IFSA Publishing, S.L. 2014-10-01
• Series: Sensors & Transducers
• Subjects: Tracking of moving video; Target detection; Histogram equalization; Image process.
• Online Access: http://www.sensorsportal.com/HTML/DIGEST/october_2014/Vol_181/P_2464.pdf

Moving object detection and tracking is the computer vision and image processing is a hot research direction, based on the analysis of the moving target detection and tracking algorithm in common use, focus on the sports video target tracking non rigid body. In sports video, non rigid athletes often have physical deformation in the process of movement, and may be associated with the occurrence of moving target under cover. Media data is surging to fast search and query causes more difficulties in data. However, the majority of users want to be able to quickly from the multimedia data to extract the interested content and implicit knowledge (concepts, rules, rules, models and correlation), retrieval and query quickly to take advantage of them, but also can provide the decision support problem solving hierarchy. Based on the motion in sport video object as the object of study, conducts the system research from the theoretical level and technical framework and so on, from the layer by layer mining between low level motion features to high-level semantic motion video, not only provides support for users to find information quickly, but also can provide decision support for the user to solve the problem.