Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments
Video-based trajectory analysis might be rather well discussed in sports, such as soccer or basketball, but in cycling, this is far less common. In this paper, a video processing pipeline to extract riding lines in cyclocross races is presented. The pipeline consists of a stepwise analysis process t...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7619 |
| _version_ | 1797508465723179008 |
|---|---|
| author | Jelle De Bock Steven Verstockt |
| author_facet | Jelle De Bock Steven Verstockt |
| author_sort | Jelle De Bock |
| collection | DOAJ |
| description | Video-based trajectory analysis might be rather well discussed in sports, such as soccer or basketball, but in cycling, this is far less common. In this paper, a video processing pipeline to extract riding lines in cyclocross races is presented. The pipeline consists of a stepwise analysis process to extract riding behavior from a region (i.e., the fence) in a video camera feed. In the first step, the riders are identified by an Alphapose skeleton detector and tracked with a spatiotemporally aware pose tracker. Next, each detected pose is enriched with additional meta-information, such as rider modus (e.g., sitting on the saddle or standing on the pedals) and detected team (based on the worn jerseys). Finally, a post-processor brings all the information together and proposes ride lines with meta-information for the riders in the fence. The presented methodology can provide interesting insights, such as intra-athlete ride line clustering, anomaly detection, and detailed breakdowns of riding and running durations within the segment. Such detailed rider info can be very valuable for performance analysis, storytelling, and automatic summarization. |
| first_indexed | 2024-03-10T05:05:17Z |
| format | Article |
| id | doaj.art-b2f1525ead9f4306a3e170c859915328 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:05:17Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b2f1525ead9f4306a3e170c8599153282023-11-23T01:26:43ZengMDPI AGSensors1424-82202021-11-012122761910.3390/s21227619Video-Based Analysis and Reporting of Riding Behavior in Cyclocross SegmentsJelle De Bock0Steven Verstockt1IDLab, Ghent University—IMEC, Technologiepark-Zwijnaarde 122, 9052 Ghent, BelgiumIDLab, Ghent University—IMEC, Technologiepark-Zwijnaarde 122, 9052 Ghent, BelgiumVideo-based trajectory analysis might be rather well discussed in sports, such as soccer or basketball, but in cycling, this is far less common. In this paper, a video processing pipeline to extract riding lines in cyclocross races is presented. The pipeline consists of a stepwise analysis process to extract riding behavior from a region (i.e., the fence) in a video camera feed. In the first step, the riders are identified by an Alphapose skeleton detector and tracked with a spatiotemporally aware pose tracker. Next, each detected pose is enriched with additional meta-information, such as rider modus (e.g., sitting on the saddle or standing on the pedals) and detected team (based on the worn jerseys). Finally, a post-processor brings all the information together and proposes ride lines with meta-information for the riders in the fence. The presented methodology can provide interesting insights, such as intra-athlete ride line clustering, anomaly detection, and detailed breakdowns of riding and running durations within the segment. Such detailed rider info can be very valuable for performance analysis, storytelling, and automatic summarization.https://www.mdpi.com/1424-8220/21/22/7619pose estimationsportsobject detectionsports data analysis |
| spellingShingle | Jelle De Bock Steven Verstockt Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments Sensors pose estimation sports object detection sports data analysis |
| title | Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments |
| title_full | Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments |
| title_fullStr | Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments |
| title_full_unstemmed | Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments |
| title_short | Video-Based Analysis and Reporting of Riding Behavior in Cyclocross Segments |
| title_sort | video based analysis and reporting of riding behavior in cyclocross segments |
| topic | pose estimation sports object detection sports data analysis |
| url | https://www.mdpi.com/1424-8220/21/22/7619 |
| work_keys_str_mv | AT jelledebock videobasedanalysisandreportingofridingbehaviorincyclocrosssegments AT stevenverstockt videobasedanalysisandreportingofridingbehaviorincyclocrosssegments |