Object tracking device, object tracking method, and recording medium
In an object tracking device, the extraction means extracts target candidates from images in a time-series. The first setting means sets a first search range based on frame information and reliability of a target in a previous image in the time-series. The tracking means searches the target from the target candidates extracted within the first search range using the reliability indicating similarity to a target model, and tracks the target. The second setting means sets a second search range which includes the first search range and which is larger than the first search range. The model updating means updates the target model using the target candidates extracted within the first search range and the target candidates extracted within the second search range.
1. An object tracking device comprising:
a memory configured to store instructions; and
one or more processors configured to execute the instructions to:
extract target candidates from images in a time-series;
set a first search range based on frame information and reliability of a target in a previous image in the time-series;
search the target from the target candidates extracted within the first search range using the reliability indicating similarity to a target model and track the target;
set a second search range which includes the first search range and which is larger than the first search range; and
update the target model using the target candidates extracted within the first search range and the target candidates extracted within the second search range.
2. The object tracking device according to claim 1 , wherein the one or more processors set the second search range to be larger than the first search range by a size equal to or larger than the target.
3. The object tracking device according to claim 1 , wherein the one or more processors set the first search range so as to include a moving destination of the target based on a moving direction and a moving speed of the target.
4. The object tracking device according to claim 1 , wherein the one or more processors calculate the reliability for each of the target candidates extracted within the first search range and determines the target candidate of highest reliability to be the target.
5. The object tracking device according to claim 4 , wherein the one or more processors calculate the reliability by weighting based on movement information of the target.
6. The object tracking device according to claim 4 ,
wherein the one or more processors are further configured to execute the instructions to:
extract, from among the target candidates extracted within the first search range, the target candidate whose reliability belongs to a first value range as a positive sample; and
extract, from among the target candidates extracted within the second search range, the target candidate whose reliability belongs to a second value range as a negative sample, and
wherein the one or more processors update the target model using at least one of the positive sample and the negative sample.
7. The object tracking device according to claim 6 , wherein the first value range and the second value range are partially overlapped.
8. The object tracking device according to claim 6 , wherein the one or more processors extract, from among the target candidates extracted within the second search range, at least one of the target candidates which is other than the target, whose reliability belong to the second value range and whose overlap with the target is equal to or smaller than a constant value as the negative sample.
9. An object tracking method comprising:
extracting target candidates from images in a time-series;
setting a first search range based on frame information and reliability of a target in a previous image in the time-series;
searching the target from the target candidates extracted within the first search range using the reliability indicating similarity to a target model and tracking the target;
setting a second search range which includes the first search range and which is larger than the first search range; and
updating the target model using the target candidates extracted within the first search range and the target candidates extracted within the second search range.
10. A non-transitory computer-readable recording medium recording a program, the program causing a computer to execute:
extracting target candidates from image in a time-series;
setting a first search range based on frame information and reliability of a target in a previous image in the time-series;
searching the target from the target candidates extracted within the first search range using the reliability indicating similarity to a target model and tracking the target;
setting a second search range which includes the first search range and which is larger than the first search range; and
updating the target model using the target candidates extracted within the first search range and the target candidates extracted with in the second search range.