Object recognition apparatus
An object recognition apparatus is provided with: a first output device configured to output a provisional position of a first object and a tracking priority by using a neural network; and a second output device configured to receive entries of the first image data, the provisional position and the tracking priority, and configured (i) to perform a time-series tracking process and output a position and a speed, for the first object in which the tracking priority satisfies a predetermined condition, and (ii) to output a position without performing the time-series tracking process, for the first object in which the tracking priority does not satisfy the predetermined condition. The neural network is a learned neural network that has learned by using teacher data, wherein the teacher data includes second image data, and correct answer data.
1. An object recognition apparatus configured to recognize a first object included in first image data on the basis of the first image data inputted in a time-series manner, said object recognition apparatus comprising:
a first output device configured to output a provisional position of the first object and a tracking priority, which indicates a degree to which a time-series tracking process is to be performed, by using a neural network that receives an entry of the first image data; and
a second output device configured to receive entries of the first image data, the provisional position and the tracking priority, and configured (i) to perform the time-series tracking process and output a position and a speed, for the first object in which the tracking priority satisfies a predetermined condition, and (ii) to output a position without performing the time-series tracking process, for the first object in which the tracking priority does not satisfy the predetermined condition, wherein
the neural network is a learned neural network that has learned by using teacher data, wherein the teacher data includes second image data, which is different from the first image data, and correct answer data of the tracking priority and a position of a second object included in the second image data, the correct answer data of the tracking priority of the second object being determined on the basis of a rate of the second object that is hidden by overlapping with another object located on a near side closer than the second object.
2. The object recognition apparatus according to claim 1 , wherein the correct answer data of the tracking priority of the second object is determined on the basis of a degree of an influence of the second object on driving of a vehicle on which said object recognition apparatus is mounted.
3. An object recognition apparatus configured to recognize a first object included in first image data on the basis of the first image data inputted in a time-series manner, said object recognition apparatus comprising:
a first output device configured to output a provisional position of the first object and a tracking priority, which indicates a degree to which a time-series tracking process is to be performed, by using a neural network that receives an entry of the first image data: and
a second output device configured to receive entries of the first image data, the provisional position and the tracking priority, and configured (i) to perform the time-series tracking process and output a position and a speed, for the first object in which the tracking priority satisfies a predetermined condition, and (ii) to output a position without performing the time-series tracking process, for the first object in which the tracking priority does not satisfy the predetermined condition, wherein
the neural network is a learned neural network that has learned by using teacher data, wherein the teacher data includes second image data, which is different from the first image data, and correct answer data of the tracking priority and a position of a second object included in the second image data, the correct answer data of the tracking priority of the second object being determined on the basis of a rate of the second object that is hidden by protruding from a frame of the second image data.
4. The object recognition apparatus according to claim 3 , wherein the correct answer data of the tracking priority of the second object is determined on the basis of a degree of an influence of the second object on driving of a vehicle on which said object recognition apparatus is mounted.