SportSense - Sketch-based spatio-temporal Query Support for Sports Videos (Finished)
Game analysis is an important task in sports, especially in team sports. The objective is to analyze the behavior (strengths, weaknesses) of other teams. Currently, this is mainly a manual task, done by coaches or dedicated game analysts based on videos of the teams to be analyzed.
The goal of the SportSense project is to apply novel sketch-based and content-based approaches to video retrieval to support the tasks of coaches and game analysts. The objective is to facilitate the search for scenes in sport videos. In most cases, queries are formulated on the basis of specific motion characteristics the coach is interested in or remembers from previous views of the video. Providing sketching interfaces for graphically specifying query input is thus a very natural user interaction for a retrieval application. However, the quality of the query (the sketch) heavily depends on the memory of the user and her ability to accurately formulate the intended search query by transforming this 3D memory of the known item(s) into 2D sketch query. Therefore, appropriate user interfaces have to be provided that are easy to use and that allow for the specification of rough sketches. The retrieval back-end then needs to execute these queries by allowing a certain degree of tolerance between the query sketch and the actual motion.
So far, SportSense automatically links event data (such as those procuded by StreamTeam) to a video of a game and provides coaches and game analysts the possibility to search within the video on the basis of sketches on the motion of players or the ball as well as on the basis of chains of events, both in backward and forward direction, by specifying spatio-temporal information. The latter is supported by user-friendly interfaces such as tablets, interactive paper, or novel gesture-based interactions.
As a next step, SportSense will be extended towards supporting i.) more sports disciplines, ii.) sketch-based queries for complex events without clear spatial reference, and iii.) jointly analyzing position data and physiological data of the individuals.
The SportSense project will continue focussing on team sports, and in particular on football, based on the existing collaboration between the DBIS group at UNIBAS and the BFH Centre for Technologies in Sports and Medicine. As the Swiss Federal Institute of Sport Magglingen (SFISM) is part of the BFH centre, the latter acts as interface between technology and especially computer science and sports. The BFH centre closely collaborates with the Swiss Football Association (SFV) and in particular with the coaches of the youth national teams of the SFV. In addition, the BFH centre has also a close collaboration with the International Ice Hockey Federation (IIHF). Therefore, ice hockey will be considered as a second use case for the evaluation of the project results.
A video showing the user interface of SportSense is published on Youtube:
The whole code of SportSense is published on GitHub under the GNU Affero General Public License v3.0.
Start / End Dates
01.01.2013 - 01.01.1970
Partners
BFH Centre for Technologies in Sports and Medicine (Martin Rumo)
Funding
Funded since September 2017 by the Hasler Foundation in the Cyber-Human Sytems program (contract no. 16074).
Staff
- Heiko Schuldt
- Ivan Giangreco
- Claudiu-Ioan Tănase
- Ihab Al Kabary
- Lukas Probst
- Luca Rossetto
- Philipp Seidenschwarz
- Rufus Peter Lobo
- Fabian Rauschenbach
- Michael Plüss
- Adalsteinn Jonsson
- Patrick Zumsteg
Research Topics
Publications
2021
- Philipp Seidenschwarz
Data-Driven Analytics for Decision Making in Game Sports
PhD Thesis, Department of Mathematics and Computer Science, University of Basel, Switzerland 2021/9
2020
- Lukas Probst, Heiko Schuldt, Philipp Seidenschwarz, Martin Rumo
StreamTeam-Football: Analyzing Football Matches in Real-Time on the Basis of Position Streams
Proceedings of the IEEE International Conference on Big Data (BigData 2020) , Atlanta, GA, USA (held virtually) 2020/12 - Philipp Seidenschwarz, Martin Rumo, Lukas Probst, Heiko Schuldt
High-Level Tactical Performance Analysis with SportSense
Proceedings of the 3rd International ACM Workshop on Multimedia Content Analysis in Sports (MMSports 2020), Seattle, WA, USA (held virtually) 2020/10 - Ihab Al Kabary, Heiko Schuldt
Scalable Sketch-based Sport Video Retrieval in the Cloud
Proceedings of the International Conference on Cloud Computing (CLOUD’20), Honolulu, Hi, USA (held virtually) 2020/9 - Philipp Seidenschwarz, Adalsteinn Jonsson, Michael Plüss, Martin Rumo, Lukas Probst, Heiko Schuldt
The SportSense User Interface for Holistic Tactical Performance Analysis in Football
Proceedings of the 25th International Conference on Intelligent User Interfaces Companion (IUI 2020 Companion), Cagliari, Italy (held virtually) 2020/3
2019
- Philipp Seidenschwarz, Adalsteinn Jonsson, Fabian Rauschenbach, Martin Rumo, Lukas Probst, Heiko Schuldt
Combining Qualitative and Quantitative Analysis in Football with SportSense
Proceedings of the 2nd International ACM Workshop on Multimedia Content Analysis in Sports (MMSports 2019), Nice, France 2019/10
2018
- Lukas Probst, Fabian Rauschenbach, Heiko Schuldt, Philipp Seidenschwarz, Martin Rumo
Integrated Real-Time Data Stream Analysis and Sketch-Based Video Retrieval in Team Sports
Proceedings of the 2018 IEEE International Conference on Big Data (BigData 2018), Seattle, WA, USA 2018/12 - Lukas Probst, Ihab Al Kabary, Rufus Lobo, Fabian Rauschenbach, Heiko Schuldt, Philipp Seidenschwarz, Martin Rumo
SportSense: User Interface for Sketch-Based Spatio-Temporal Team Sports Video Scene Retrieval
Proceedings of the IUI 2018 Workshop on User Interfaces for Spatial and Temporal Data Analysis (UISTDA 2018), Tokyo, Japan 2018/3
2014
- Fabio Sulser, Ivan Giangreco, Heiko Schuldt
Crowd-based Semantic Event Detection and Video Annotation for Sports Videos
Proceedings of the International ACM Workshop on Crowdsourcing for Multimedia (CrowdMM), Orlando, FL, USA 2014/11 - Ihab Al Kabary, Heiko Schuldt
Enhancing Sketch-based Sport Video Retrieval by Suggesting Relevant Motion Paths
Proceedings of the 37th ACM SIGIR Conference, Gold Coast, Australia 2014/7 - Ihab Al Kabary, Heiko Schuldt
Using Hand Gestures for Specifying Motion Path Queries in Sketch-based Video Retrieval
Proceedings of the 36th European Conference on Information Retrieval (ECIR), Amsterdam, Netherlands 2014/4
2013
- Ihab Al Kabary, Heiko Schuldt
Towards Sketch-based Motion Queries in Sports Videos
Proceedings of the 15th IEEE International Symposium on Multimedia (ISM 2013), Anaheim, CA, USA 2013/12 - Ihab Al Kabary, Heiko Schuldt
SportSense: Using Motion Queries to Find Scenes in Sports Videos
Proceedings of the 22nd ACM International Conference on Information and Knowledge Management (CIKM 2013), San Francisco, CA, USA 2013/10