Method for tracking sports participants, device for tracking sports participants, and system for tracking sports participants
A multi-mode tracking method according to the present disclosure includes receiving sensor signals from a plurality of positioning sensors located on a plurality of sport participants wherein the sensor signals each include a participant identifier and location data, receiving a sport image captured from a camera located near a playfield wherein the sport image includes at least a target participant among a plurality of sport participants on the playfield, detecting an occlusion related to the target participant in the sports image, determining the severity of the occlusion on the basis of a sensor signal received from a specific positioning sensor installed on a specific sport player located in a region of interest related to the occlusion, and determining a location of the sport participant on the basis of the severity of the occlusion.
1. A multi-modal tracking method, the method comprising:
receiving, from a plurality of positioning sensors each being disposed at a plurality of sports participants, a plurality of sensor signals each including a participant identifier and location data;
receiving a sports image captured at a camera disposed peripheral to a playfield, the sports image including at least a target participant among the plurality of sports participants in the playfield;
detecting, from the sports image, an occlusion related to the target participant;
determining a severity of the occlusion based on the sensor signal obtained from a specific positioning sensor disposed at specific sports participants located in a region of interest related to the occlusion;
when the occlusion of which the severity reflects a severe occlusion is not detected, determining a location of the target participant using a pixel position related to the target participant in the sports image; and
when the occlusion of which the severity reflects a severe occlusion is detected, determining the location of the target participant using the location data of the sensor signal of which the participant identifier corresponds to the target participant.
2. The method according to claim 1 ,
wherein the region of interest is a predetermined area with reference to the target participant being involved in the occlusion, and
wherein the determining the severity includes determining the severity of the occlusion based on a number of the at least one sensor signal located in the region of interest.
3. The method according to claim 2 ,
wherein the determining the severity includes:
when the number of the at least one sensor signal is greater than a threshold value, assigning a value reflecting the severe occlusion to the severity, and when the number of the at least one sensor signal is smaller than the threshold value, assigning a value reflecting a mild occlusion to the severity.
4. The method according to claim 1 ,
wherein the determining the severity includes:
obtaining team information indicating whether or not the target participant and another participant, among the at least one sport participant, who occludes or is occluded by the target participant are in a same team, based on the participant identifier corresponding to the target participant and the another participant.
5. The method according to claim 4 ,
wherein the determining the severity includes:
when the target participant and the another participant are in the same team, assigning a value reflecting the severe occlusion to the severity, when the target participant and the another participant are in different teams, assigning a value reflecting a mild occlusion to the severity.
6. The method according to claim 4 , wherein the team information is obtained from pixel data corresponding the target participant and the another participant of the sport image.