Figure - available from: Mobile Networks and Applications
This content is subject to copyright. Terms and conditions apply.
Source publication
In view of the obvious deviation of traditional methods in the analysis of basketball flight state, a basketball trajectory analysis method based on intelligent image of mobile terminal is designed. Firstly, the mobile terminal network equipment is used to effectively collect the basketball trajectory. The gray pixel set of basketball image is obta...
Citations
... Basketball is popular among the public in daily life due to its few restrictions on venues and ease of play [1,2]. It is very easy to record the basketball game and collect data about players and games, which can be analyzed and processed efficiently. ...
During a basketball game, the ball moves are dynamic, and it is very hard for athletes and trainers to track every move of the ball. An accurate image tracking of a basketball flight path provides the basis for basketball training and other applications. The flight trajectory tracking method based on video signal filtering is studied in this paper. Specifically, the adaptive median filtering algorithm is used to filter the basketball flight video signal. After applying median filtering, the image difference is selected to enhance the basketball trajectory flight images, followed by the Harris corner detection algorithm enhancing the images. Moreover, the SURF algorithm is used to extract features of basketball targets according to the detection results of corner points in the images. Finally, the Particle Swarm Optimization algorithm optimizes the basketball flight trajectory tracking results obtained through the Kalman filter algorithm. The experimental results show that the proposed method can accurately track the flight path of basketball, the real rate is 97%, and the maximum difference between the number of frames and the actual result is 1 frame. The position error and the end position error of the tracking result are both less than 5 cm, which is suitable for basketball training and other practical applications.
... The first section of this issue includes five papers, which focuses on the image processing under mobile network environment, including feature learning and recognition, key frame extraction, trajectory analysis, and quick search [6][7][8][9][10]. Discriminative feature learning is important when classifies remote images. ...
