SSET: a dataset for shot segmentation, event detection, player tracking in soccer videos
- PDF / 1,437,855 Bytes
- 22 Pages / 439.37 x 666.142 pts Page_size
- 114 Downloads / 330 Views
SSET: a dataset for shot segmentation, event detection, player tracking in soccer videos Na Feng 1 & Zikai Song 1 & Junqing Yu 1,2 & Yi-Ping Phoebe Chen 3 & Yizhu Zhao 1 & Yunfeng He 1 & Tao Guan 1 Received: 11 June 2019 / Revised: 19 June 2020 / Accepted: 21 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Soccer video analysis is the focus of sports video research as it receives widespread attention around the world. However, the lack of soccer datasets hinders the rapid development of this field. In this paper, we construct a soccer dataset named Soccer Dataset for Shot, Event, and Tracking (SSET), which can meet the research needs of shot segmentation, soccer event detection and player tracking. So far, we have collected 350 soccer videos, involving a variety of soccer games, for a total of 282 h. The dataset consists of three parts: (1) Shot, including five shot types and two shot transition types; (2) Event/Story, consisting of 11 fine-grained event and 15 coarse-grained story types where the story extends the event types with 4 extra types; (3) Bounding box of players, giving the coordinates, width and length of the bounding box. In addition, we develop an annotation tool called Sports Video Dataset Markup (SVDM) for sports video data annotation and hope that more people join our work. We conduct event detection and player tracking experiments on our dataset, and the results show that the existing works are not completely suitable for solving soccer video analysis tasks. Our dataset is available at http://media.hust.edu.cn/dataset.htm. Keywords Soccer video dataset . Shot boundary detection . Shot classification . Event detection . Player tracking
1 Introduction Soccer is the most popular and influential sport among many sports. It is considered to be the largest sport in the world. Various soccer games have received wide attention, such as the
* Junqing Yu [email protected] * Yi-Ping Phoebe Chen [email protected] Extended author information available on the last page of the article
Multimedia Tools and Applications
AsianCup, the EuroCup, the PremierLeague, etc., especially the FIFA World Cup held every 4 years, attracting countless soccer fans to cheer. However, since the long duration and variety of soccer games, and the audience may only be interested in the exciting parts of the game, content-based soccer video analysis has become the focus of sports video analysis. Recently, deep learning has made significant progress in video content analysis. It is dedicated to solving the problem of the ‘semantic gap’ and has contributed tremendously to video classification, action detection and object tracking [32, 38, 51, 60, 61, 64]. Unfortunately, there are still many limitations in soccer video analysis, the most important of which is the lack of high-quality datasets. First, there is a lack of large-scale soccer datasets. Although there are many datasets available to choose from, most of them come from human activities, which is very different from the soc
Data Loading...
