Soccer Video Event Detection Based on Deep Learning

被引：14

作者：

Yu, Junqing ^{[1
,2
]}

Lei, Aiping ^{[1
]}

Hu, Yangliu ^{[1
]}

机构：

[1] Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan 430074, Peoples R China

[2] Huazhong Univ Sci & Technol, Ctr Network & Computat, Wuhan 430074, Peoples R China

来源：

MULTIMEDIA MODELING, MMM 2019, PT II | 2019年 / 11296卷

基金：

中国国家自然科学基金;

关键词：

Soccer video; Event detection; Deep learning; Video analysis; BAYESIAN NETWORK;

D O I：

10.1007/978-3-030-05716-9_31

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Automatically identifying the most interesting content in a long video remains a challenging task. Event detection is an important aspect of soccer game research. In this paper, we propose a model that is able to detect events in long soccer games with a single pass through the video. Combined with replay detection, we generate story clips, which contain more complete temporal context, meeting audiences' needs. We also introduce a soccer game dataset that contains 222 broadcast soccer videos, totaling 170 video hours. The dataset covers three annotation types: (1) shot annotations (type and boundary), (2) event annotations (with 11 event labels), and (3) story annotations (with 15 story labels). Finally, we report the performance of the proposed model for soccer events and story analysis.

引用

页码：377 / 389

页数：13

共 39 条

[1]

Arbat S., 2014, INT J SCI TECHNOL RE, V3, P282

[2] SST: Single-Stream Temporal Action Proposals [J].

Buch, Shyamal ;

Escorcia, Victor ;

Shen, Chuanqi ;

Ghanem, Bernard ;

Niebles, Juan Carlos .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :6373-6382

[3]

Heilbron FC, 2015, PROC CVPR IEEE, P961, DOI 10.1109/CVPR.2015.7298698

[4] P-CNN: Pose-based CNN Features for Action Recognition [J].

Cheron, Guilhem ;

Laptev, Ivan ;

Schmid, Cordelia .

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :3218-3226

[5] A review of vision-based systems for soccer video analysis [J].

D'Orazio, T. ;

Leo, M. .

PATTERN RECOGNITION, 2010, 43 (08) :2911-2926

[6] Event Detection based on Twitter Enthusiasm Degree for Generating a Sports Highlight Video [J].

Doman, Keisuke ;

Tomita, Taishi ;

Ide, Ichiro ;

Deguchi, Daisuke ;

Murase, Hiroshi .

PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14), 2014, :949-952

[7]

Donahue J, 2015, PROC CVPR IEEE, P2625, DOI 10.1109/CVPR.2015.7298878

[8] Learning Spatiotemporal Features with 3D Convolutional Networks [J].

Du Tran ;

Bourdev, Lubomir ;

Fergus, Rob ;

Torresani, Lorenzo ;

Paluri, Manohar .

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :4489-4497

[9] DAPs: Deep Action Proposals for Action Understanding [J].

Escorcia, Victor ;

Heilbron, Fabian Caba ;

Niebles, Juan Carlos ;

Ghanem, Bernard .

COMPUTER VISION - ECCV 2016, PT III, 2016, 9907 :768-784

[10] Spatiotemporal Multiplier Networks for Video Action Recognition [J].

Feichtenhofer, Christoph ;

Pinz, Axel ;

Wildes, Richard P. .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :7445-7454

← 1 2 3 4 →