High-speed tracking system based on Multi-parallel-core processor and CNN algorithm

Individual insects flying in crowded assemblies perform complex aerial maneuvers by sensing and feeding back neighbor measurements to small changes in their wing motions. To understand the individual feedback rules that permit these fast, adaptive behaviors in group flight, a high-speed tracking system is needed capable of tracking both body motions and more subtle wing motion changes for multiple insects in simultaneous flight. This capability extends tracking beyond the previous focus on individual insects to multiple insects. This paper presents Hi-VISTA, which provides a capability to track wing and body motions of multiple insects using high speed cameras (9000 fps). Processing steps consist of automatic background identification, data association, hull reconstruction, segmentation, and feature measurement. To improve the biological relevance of laboratory experiments and develop a platform for interaction studies, this paper applies the Hi-VISTA measurement system to Apis mellifera foragers habituated to transit flights through a transparent tunnel. Binary statistical analysis (Welch's t-test, Cohen's d effect size) of 95 flight trajectories is presented, quantifying the differences between flights in an unobstructed tunnel and in a confined tunnel volume. The results indicate that body pitch angle, heading rate, flapping frequency, and vertical speed (heave) are all affected by confinement, and other flight variables show minor or statistically insignificant changes. These results form a baseline as swarm tracking and analysis begins to isolate the effects of neighbors from environment.

Download Full-text

Do elite soccer players cover longer distance when losing? Differences between attackers and defenders

International Journal of Sports Science & Coaching ◽

10.1177/1747954120982270 ◽

2020 ◽

pp. 174795412098227

Author(s):

Carlos Lago-Peñas ◽

Anton Kalén ◽

Miguel Lorenzo-Martinez ◽

Roberto López-Del Campo ◽

Ricardo Resta ◽

...

Keyword(s):

New York ◽

High Speed ◽

Large Scale ◽

Tracking System ◽

Soccer Players ◽

Running Performance ◽

Situational Variables ◽

Total Distance ◽

Professional Soccer ◽

Score Line

This study aimed to evaluate the effects playing position, match location (home or away), quality of opposition (strong or weak), effective playing time (total time minus stoppages), and score-line on physical match performance in professional soccer players using a large-scale analysis. A total of 10,739 individual match observations of outfield players competing in the Spanish La Liga during the 2018–2019 season were recorded using a computerized tracking system (TRACAB, Chyronhego, New York, USA). The players were classified into five positions (central defenders, players = 94; external defenders, players = 82; central midfielders, players = 101; external midfielders, players = 72; and forwards, players = 67) and the following match running performance categories were considered: total distance covered, low-speed running (LSR) distance (0–14 km · h−1), medium-speed running (MSR) distance (14–21 km · h−1), high-speed running (HSR) distance (>21 km · h−1), very HSR (VHSR) distance (21–24 km · h−1), sprint distance (>24 km · h−1) Overall, match running performance was highly dependent on situational variables, especially the score-line condition (winning, drawing, losing). Moreover, the score-line affected players running performance differently depending on their playing position. Losing status increased the total distance and the distance covered at MSR, HSR, VHSR and Sprint by defenders, while attacking players showed the opposite trend. These findings may help coaches and managers to better understand the effects of situational variables on physical performance in La Liga and could be used to develop a model for predicting the physical activity profile in competition.

Download Full-text