[Papers] Keep Your Eye on the Ball: Detection of Kicking Motions in Multi-view 4K Soccer Videos

Abstract

For automated game analysis, it is essential to detect the kicking motions of players in soccer videos in order to understand each player's actions. This paper presents a fast and accurate approach to detecting kicking motions with a ball-centric window in multi-view 4K soccer videos. Based on powerful object detection techniques like SSD or YOLOv3 and pose estimation techniques like OpenPose or CPN, we propose novel solutions to overcome two challenges in 4K soccer videos. The first challenge is that it is basically too computationally heavy to process the massive amount of data in multi-view 4K videos. The solution to this challenge is that we only process a small portion (i.e. a ball-centric window) of 4K video, benefiting from an object tracking technique and homography transformation. The second challenge is that kicking motions may be incorrectly detected due to two factors. One is the absence of depth information and the other is the inaccuracy of pose estimation. We fuse multiple views to avoid the depth problem. In addition, we propose enlarging the person areas to effectively improve the accuracy of pose estimation. The experiments on real data from the J1 League demonstrate that the proposed approach achieves both faster and more accurate detection of kicking motions than conventional methods.

Athlete Health Status Assessment Based on Edge Computing Model and Large-Scale Multimedia Health Data Analysis

“…This module provides data support for the operation of the upper-layer core subsystems [ 11 ]; the transmission module is mainly responsible for the data interaction between the client and the back-end server, and the exchanged information mainly includes user heat consumption ranking information, friend-related information, etc. [ 12 ]; the activity recognition subsystem is mainly used to reliably identify the user's basic activities and provide activity information for the quality of life assessment subsystem, including the type of activity and its duration [ 13 ]; the quality of life assessment subsystem integrates activity information as well as diet, weight, height, gender, and other information to judge whether the user's life is in a healthy state [ 14 ].…”

Multiscale Motion Detection and Recognition Combining Still Images and Video Sequences

“…However, since athletes consume a lot of physical strength in the previous running stage, some techniques can be used to help athletes maintain their maximum speed when running at the finish line. When athletes are 15-20 meters away from the finish line, their upper body should lean forward and their center of gravity should move forward, which can increase the power of the back-push of the calf and at the same time increase the swing amplitude and step length of the arms, and always maintain the same cadence as the previous running stage [14]. In the sports running stage, athletes are required to have strong physical endurance and strength to support athletes rushing to the finish line [15].…”

The Visual Movement Analysis of Physical Education Teaching considering the Generalized Hough Transform Model

“…According to the description, by counting the pixels in the support set, the covariance matrix is obtained, and then the eigenvectors and eigenvalues are obtained. The covariance matrix is as follows [ 19 ]: …”