Integrated Real-Time Data Stream Analysis and Sketch-Based Video Retrieval in Team Sports

Big data in sports comes with two closely related challenges: first, the online analysis of continuous data streams to identify characteristic events and second, advanced retrieval in video collections and/or event data that help game analysts to search for characteristic video scenes. For both challenges, dedicated big data stream processing and retrieval systems have been developed. However, there is no infrastructure yet that integrates retrieval and automatic online data stream analysis. In this paper, we close this gap by seamlessly combining STREAMTEAM, our real-time team sports analysis system, and SPORTSENSE, our team sports video retrieval system, to an integrated team sports analysis infrastructure that (i) automatically detects (collaborative) events and generates statistics in real-time based on a continuous stream of raw positions, (ii) visualizes the analysis results in real-time, (iii) stores the analysis results persistently for offline activities, and (iv) leverages the stored analysis results for intuitive sketch-based video retrieval.

[1]  Shinji Ozawa,et al.  A System for Automatic Judgment of Offsides in Soccer Games , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[2]  Daniel Wolf,et al.  A Real-Time Tracking System for Football Match and Training Analysis , 2011 .

[3]  R. Zemel,et al.  Classifying NBA Offensive Plays Using Neural Networks , 2016 .

[4]  A. Stelzer,et al.  Concept and application of LPM - a novel 3-D local position measurement system , 2004, IEEE Transactions on Microwave Theory and Techniques.

[5]  Martin Lames,et al.  Information Systems for Top-Level Football with Focus on Performance Analysis and Healthy Reference Patterns , 2017 .

[6]  sarthak agarwal,et al.  Performance Analysis of MongoDB Vs. PostGIS/PostGreSQL Databases For Line Intersection and Point Containment Spatial Queries , 2015 .

[7]  K. S. Rajan,et al.  Performance analysis of MongoDB versus PostGIS/PostGreSQL databases for line intersection and point containment spatial queries , 2016, Spatial Information Research.

[8]  Yisong Yue,et al.  Chalkboarding: A New Spatiotemporal Query Paradigm for Sports Play Retrieval , 2016, IUI.

[9]  Matthias Weidlich,et al.  Grand challenge: the TechniBall system , 2013, DEBS '13.

[10]  Keven Richly,et al.  Recognizing Compound Events in Spatio-Temporal Football Data , 2016, IoTBD.

[11]  Stephan Schmid.  Performance investigation of selected SQL and NoSQL databases , 2015 .

[12]  Heiko Schuldt,et al.  Towards Sketch-Based Motion Queries in Sports Videos , 2013, 2013 IEEE International Symposium on Multimedia.

[13]  Heiko Schuldt,et al.  Real-Time Football Analysis with StreamTeam: Demo , 2017, DEBS.

[14]  Thomas B. Moeslund,et al.  Thermal Tracking of Sports Players , 2014, Sensors.

[15]  Li Su,et al.  Grand challenge: MapReduce-style processing of fast sensor data , 2013, DEBS '13.

[16]  Herakles: real-time sport analysis using a distributed data stream management system , 2015, DEBS.

[17]  Heiko Schuldt,et al.  SportSense: User Interface for Sketch-Based Spatio-Temporal Team Sports Video Scene Retrieval , 2018, IUI Workshops.

[18]  Alan Fern,et al.  Play type recognition in real-world football video , 2014, IEEE Winter Conference on Applications of Computer Vision.

[19]  Jay Kreps,et al.  Kafka : a Distributed Messaging System for Log Processing , 2011 .

[20]  Thomas B. Moeslund,et al.  Identifying Basketball Plays from Sensor Data; Towards a Low-Cost Automatic Extraction of Advanced Statistics , 2017, 2017 IEEE International Conference on Data Mining Workshops (ICDMW).

[21]  Heiko Schuldt,et al.  Enhancing sketch-based sport video retrieval by suggesting relevant motion paths , 2014, SIGIR.

[22]  Reza Sherafat Kazemzadeh,et al.  Grand challenge: the bluebay soccer monitoring engine , 2013, DEBS '13.

[23]  Daniel A. Keim,et al.  Bring It to the Pitch: Combining Video and Movement Data to Enhance Team Sport Analysis , 2018, IEEE Transactions on Visualization and Computer Graphics.

[24]  Cheng Xu,et al.  Grand challenge: implementation by frequently emitting parallel windows and user-defined aggregate functions , 2013, DEBS '13.

[25]  Ralf Hartmut Güting,et al.  An introduction to spatial database systems , 1994, VLDB J..

[26]  David Maier,et al.  Grand challenge: SPRINT stream processing engine as a solution , 2013, DEBS '13.

[27]  Heiko Schuldt,et al.  PAN - Distributed Real-Time Complex Event Detection in Multiple Data Streams , 2016, DAIS.

[28]  Ulrich Rückert,et al.  AN INTEGRATED MONITORING AND ANALYSIS SYSTEM FOR PERFORMANCE DATA OF INDOOR SPORT ACTIVITIES , 2010 .

[29]  Carlo Curino,et al.  Apache Hadoop YARN: yet another resource negotiator , 2013, SoCC.

[30]  Indranil Gupta,et al.  Stateful Scalable Stream Processing at LinkedIn , 2017, Proc. VLDB Endow..

[31]  Deb Roy,et al.  Unsupervised content-based indexing of sports video , 2007, MIR '07.

[32]  Hans-Arno Jacobsen,et al.  Grand challenge: real-time soccer analytics leveraging low-latency complex event processing , 2013, DEBS '13.

[33]  Thomas B. Moeslund,et al.  Constrained multi-target tracking for team sports activities , 2018, IPSJ Transactions on Computer Vision and Applications.