Multiple-camera tracking: UK government requirements

AbstractReal Madrid was named as the best club of the 20th century by the International Federation of Football History and Statistics. The aim of this study was to compare if players from Real Madrid covered shorter distances than players from the opposing team. One hundred and forty-nine matches including league, cup and UEFA Champions League matches played by the Real Madrid were monitored during the 2001-2002 to the 2006-2007 seasons. Data from both teams (Real Madrid and the opponent) were recorded. Altogether, 2082 physical performance profiles were examined, 1052 from the Real Madrid and 1031 from the opposing team (Central Defenders (CD) = 536, External Defenders (ED) = 491, Central Midfielders (CM) = 544, External Midfielders (EM) = 233, and Forwards (F) = 278). Match performance data were collected using a computerized multiple-camera tracking system (Amisco Pro®, Nice, France). A repeated measures analysis of variance (ANOVA) was performed for distances covered at different intensities (sprinting (>24.0 km/h) and high-speed running (21.1-24.0 km/h) and the number of sprints (21.1-24.0 km/h and >24.0 km/h) during games for each player sectioned under their positional roles. Players from Real Madrid covered shorter distances in high-speed running and sprint than players from the opposing team (p < 0.01). While ED did not show differences in their physical performance, CD (p < 0.05), CM (p < 0.01), EM (p < 0.01) and F (p > 0.01) from Real Madrid covered shorter distances in high-intensity running and sprint and performed less sprints than their counterparts. Finally, no differences were found in the high-intensity running and sprint distances performed by players from Real Madrid depending on the quality of the opposition.

Download Full-text

Multiple-camera tracking system with seamless object handover

10.1117/12.424949 ◽

2001 ◽

Cited By ~ 1

Author(s):

SangKyu Kang ◽

Jihong Min ◽

Joon-Ki Paik

Keyword(s):

Tracking System ◽

Camera Tracking ◽

Multiple Camera ◽

Object Handover

Download Full-text

STAM-CCF: Suspicious Tracking Across Multiple Camera Based on Correlation Filters

Sensors ◽

10.3390/s19133016 ◽

2019 ◽

Vol 19 (13) ◽

pp. 3016 ◽

Cited By ~ 1

Author(s):

Ruey-Kai Sheu ◽

Mayuresh Pardeshi ◽

Lun-Chi Chen ◽

Shyan-Ming Yuan

Keyword(s):

Gait Recognition ◽

Geographical Information ◽

Volume Data ◽

Multiple Cameras ◽

Camera Tracking ◽

Correlation Filters ◽

Data Set ◽

Multiple Camera ◽

Public Areas ◽

Feature Based

There is strong demand for real-time suspicious tracking across multiple cameras in intelligent video surveillance for public areas, such as universities, airports and factories. Most criminal events show that the nature of suspicious behavior are carried out by un-known people who try to hide themselves as much as possible. Previous learning-based studies collected a large volume data set to train a learning model to detect humans across multiple cameras but failed to recognize newcomers. There are also several feature-based studies aimed to identify humans within-camera tracking. It would be very difficult for those methods to get necessary feature information in multi-camera scenarios and scenes. It is the purpose of this study to design and implement a suspicious tracking mechanism across multiple cameras based on correlation filters, called suspicious tracking across multiple cameras based on correlation filters (STAM-CCF). By leveraging the geographical information of cameras and YOLO object detection framework, STAM-CCF adjusts human identification and prevents errors caused by information loss in case of object occlusion and overlapping for within-camera tracking cases. STAM-CCF also introduces a camera correlation model and a two-stage gait recognition strategy to deal with problems of re-identification across multiple cameras. Experimental results show that the proposed method performs well with highly acceptable accuracy. The evidences also show that the proposed STAM-CCF method can continuously recognize suspicious behavior within-camera tracking and re-identify it successfully across multiple cameras.

Download Full-text