Figure - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Comparison of the overall tracking performance on test videos of the hockey player tracking dataset. (↓ means lower is better, ↑ mean higher is better)
Contexts in source publication
Context 1
... sports player tracking, the IDF1 is considered a better accuracy measure than Multi Object Tracking accuracy (MOTA) since it measures how consistently the identity of a tracked object is preserved with respect to the ground truth identity. The overall results are shown in Table 3. The best tracking performance is achieved using the MOT Neural Solver tracking model [4] re-trained on the hockey dataset. ...Similar publications
Student’s social status within the context of physical education group work can influence engagement and behaviour during group tasks (Cohen [1994]. Restructuring the classroom: Conditions for productive small groups. Review of Educational Research, 64(1), 1–35. https://doi.org/10.3102/00346543064001001). According to Bourdieu ([1985]. The forms of...
The Hockey World Cup 2023 is re-examined using Ramanujacharyulu's Power-Weakness approach.
Objective
The objective of this study was to identify the main determinants of heart rate variability (HRV) in male athletes aged 14 to 21 years who practice competitive contact sports and to integrate these determinants with the aim of defining normative values of short-term HRV in the time and frequency domains.
Methods
Participants ( n = 369) w...
Citations
... Each tracking sample records features such as timestep, player ID, spatial coordinates, and velocity for each player and the ball or puck, typically amounting to millions of data points in each game. Tracking systems function through physical hardware on each player and ball or puck, or vision-based systems that extract detailed events or attributes such as hockey stick location and pose, a significant area of hardware and computer vision research itself [5,33,49]. Tracking data can also be modeled as a Markov chain of events where the action space includes player movement within the playing surface and can be joined with event data to add additional event context to player movements [15]. Many sports datasets are freely available for download. ...
This paper draws correlations between several challenges and opportunities within the area of team sports analytics and key research areas within multiagent systems (MAS). We specifically consider invasion games, defined as sports where players invade the opposing team's territory and can interact anywhere on a playing surface such as ice hockey, soccer, and basketball. We argue that MAS is well-equipped to study invasion games and will benefit both MAS and sports analytics fields. Our discussion highlights areas for MAS implementation and further development along two axes: short-term in-game strategy (coaching) and long-term team planning (management).
