Object tracking apparatus, object tracking system, object tracking method, display control device, object detection device, and computer-readable medium

An object tracking method performed by a computer, the object tracking method comprising:

• generating, via a first detector, a first detection result of a plurality of objects from a first image captured by a first camera, the first detection result including individual coordinate system position information expressed in an individual coordinate system specific to the first camera for each of the plurality of objects;
• generating, via a second detector, a second detection result of the plurality of objects from a second image captured by a second camera, the second image being different from the first image, the second detection result including individual coordinate system position information expressed in an individual coordinate system specific to the second camera for each of the plurality of objects;
• calculating, based on the first detection result and the second detection result, common coordinate system position information expressed in a common coordinate system for each of the plurality of objects;
• predicting positions of the plurality of objects at timing of next capturing, based on the first detection result and the second detection result;
• estimating, based on the positions of the plurality of objects and dispositions of the first camera and the second camera, whether the plurality of objects will overlap with each other and their front-back relationships in a subsequent image to be captured next by each of the first camera and the second camera at the timing of the next capturing;
• and
• generating appearance information indicating that one object is estimated to overlap and be in front of other object in the subsequent image when the plurality of objects are estimated to overlap in the subsequent image;
• and
• outputting the common coordinate system position information and the appearance information for each of the plurality of objects, wherein
• at least one of the first detector or the second detector performs controlling of detection of the plurality of objects based on the appearance information, and
• the controlling includes, when it is estimated that the one object will overlap and be in front of the other object in the subsequent image, detecting the one object based on tracking information including the individual coordinate system position information, transformed from the common coordinate system position information, and the appearance information, and stopping detection of the other object.

A non-transitory computer-readable medium storing instructions executed by a processor to perform processing comprising:

• generating, via a first detector, a first detection result of a plurality of objects from a first image captured by a first camera, the first detection result including individual coordinate system position information expressed in an individual coordinate system specific to the first camera for each of the plurality of objects;
• generating, via a second detector, a second detection result of the plurality of objects from a second image captured by a second camera, the second image being different from the first image, the second detection result including individual coordinate system position information expressed in an individual coordinate system specific to the second camera for each of the plurality of objects;
• calculating, based on the first detection result and the second detection result, common coordinate system position information expressed in a common coordinate system for each of the plurality of objects;
• predicting positions of the plurality of objects at timing of next capturing, based on the first detection result and the second detection result;
• estimating, based on the positions of the plurality of objects and dispositions of the first camera and the second camera, whether the plurality of objects will overlap with each other and their front-back relationships in a subsequent image to be captured next by each of the first camera and the second camera at the timing of the next capturing;
• and
• generating appearance information indicating that one object is estimated to overlap and be in front of other object in the subsequent image when the plurality of objects are estimated to overlap in the subsequent image;
• and
• outputting the common coordinate system position information and the appearance information for each of the plurality of objects, wherein
• at least one of the first detector or the second detector performs controlling of detection of the plurality of objects based on the appearance information, and
• the controlling includes, when it is estimated that the one object will overlap and be in front of the other object in the subsequent image, detecting the one object based on tracking information including the individual coordinate system position information, transformed from the common coordinate system position information, and the appearance information, and stopping detection of the other object.