Object recognition apparatus

1. An object recognition apparatus mounted to a moving body, the moving body being provided with a plurality of object detecting apparatuses for detecting an object present within a predetermined detectable area including a reference axis, the plurality of object detecting apparatus including a first object detecting apparatus and a second object detecting apparatus, the detectable area of the first object detecting apparatus and the detectable area of the second object detecting apparatus overlapping each other, the object recognition apparatus comprising:

a processor, wherein the processor is configured to:

learn an axis displacement amount of the reference axis of the first object detecting apparatus;

combine and integrate, as information belonging to a same object, a plurality of pieces of information present within a first combining area and a second combining area, when a positional relationship between the first combining area and the second combining area meets a predetermined combinable condition, the first combining area being set as an area in which pieces of information related to the object acquired by the first object detecting apparatus are combined, the second combining area being set as an area in which pieces of information related to the object acquired by the second object detecting means apparatus are combined; and

variably set sizes of the first combining area and the second combining area based on a learning state of the axis displacement amount learned by the processor.

2. The object recognition apparatus according to claim 1 , wherein:

the processor reduces the first combining area and the second combining area as accuracy of learning by the processor increases.

3. The object recognition apparatus according to claim 2 , wherein:

the first object detecting apparatus is an imaging apparatus that captures an image of a peripheral environment including a road;

the processor is further configured to recognize a lane marking on the road based on an image captured by the first object detecting apparatus;

the processor learns the axis displacement amount of the reference axis of the first object detecting apparatus based on lane marking information that is information related to the lane marking recognized by the processor; and

the processor reduces the first combining area and the second combining area from those before completion of learning when learning of the axis displacement amount based on the lane marking information by the processor is completed after start of operation of the moving body.

4. The object recognition apparatus according to claim 3 , wherein:

the processor is further configured to calculate an optical flow based on an image captured by the first object detecting apparatus, wherein:

the processor performs a first learning process to learn the axis displacement amount of the reference axis of the first object detecting apparatus based on the optical flow calculated by the processor and performs a second learning process to learn the axis displacement amount of the reference axis of the first object detecting apparatus based on the lane marking information, and the first learning process is completed earlier than the second learning process after the start of operation of the moving body; and

the processor reduces the first combining area and the second combining area from those before completion of each learning when the first learning process is completed and the second learning process is completed after the start of operation of the moving body.

5. The object recognition apparatus according to claim 4 , wherein:

the first object detecting apparatus is an imaging apparatus that captures an image of a peripheral environment including a road; and

the second object detecting apparatus is a detection apparatus that detects an object by transmitting transmission waves and receiving the transmitted transmission waves.

6. The object recognition apparatus according to claim 5 , wherein:

the processor sets a reduction ratio in a distance direction to be greater than a reduction ratio in a width direction that is perpendicular to the distance direction, when the first combining area is reduced based on the learning state of the axis displacement amount by the processor.

7. The object recognition apparatus according to claim 6 , wherein:

the processor sets the reduction ratio in the width direction that is perpendicular to the distance direction to be greater than the reduction ratio in the distance direction when the second combining area is reduced based on the learning state of the axis displacement amount by the processor.

8. The object recognition apparatus according to claim 7 , wherein:

the moving body is a vehicle.

9. The object recognition apparatus according to claim 1 , wherein:

the first object detecting apparatus is an imaging apparatus that captures an image of a peripheral environment including a road;

a the processor is further configured to recognize a lane marking on the road based on an image captured by the first object detecting apparatus is further included;

the processor learns the axis displacement amount of the reference axis of the first object detecting apparatus based on lane marking information that is information related to the lane marking recognized by the processor; and

the processor reduces the first combining area and the second combining area from those before completion of learning when learning of the axis displacement amount based on the lane marking information by the processor is completed after start of operation of the moving body.

10. The object recognition apparatus according to claim 1 , wherein:

the first object detecting apparatus is an imaging apparatus that captures an image of a peripheral environment including a road; and

the second object detecting apparatus is a detection apparatus that detects an object by transmitting transmission waves and receiving the transmitted transmission waves.

11. The object recognition apparatus according to claim 1 , wherein:

the processor sets the reduction ratio in the width direction that is perpendicular to the distance direction to be greater than the reduction ratio in the distance direction when the second combining area is reduced based on the learning state of the axis displacement amount by the processor.

12. The object recognition apparatus according to claim 1 , wherein:

the moving body is a vehicle.

13. An object recognition system comprising:

a plurality of object detecting apparatus for detecting an object present in a predetermined detectable area including a reference axis that are mounted to a moving body; and

an object recognition apparatus that is mounted to the moving body,

the plurality of object detecting apparatuses including a first object detecting apparatus and a second object detecting means apparatus, the detectable area of the first object detecting apparatus and the detectable area of the second object detecting apparatus overlapping each other, and

the object recognition apparatus including:

a processor, wherein the processor is configured to:

learn an axis displacement amount of the reference axis of the first object detecting apparatus;

combine and integrate, as information belonging to a same object, a plurality of pieces of information present within a first combining area and a second combining area, when a positional relationship between the first combining area and the second combining area meets a predetermined combinable condition, the first combining area being set as an area in which pieces of information related to the object acquired by the first object detecting apparatus are combined, the second combining area being set as an area in which pieces of information related to the object acquired by the second object detecting apparatus are combined; and

variably set sizes of the first combining area and the second combining area based on a learning state of the axis displacement amount learned by the processor.

14. A processing method of an object recognition apparatus that is a processing method of an object recognition apparatus mounted to a moving body, the moving body being provided with a plurality of object detecting apparatus for detecting an object present within a predetermined detectable area including a reference axis, the plurality of object detecting apparatuses including a first object detecting apparatus and a second object detecting apparatus, and the detectable area of the first object detecting apparatus and the detectable area of the second object detecting apparatus overlapping each other; and

the processing method of the object recognition apparatus comprising:

learning, by a processor provided in the object recognition apparatus, an axis displacement amount of the reference axis of the first object detecting apparatus,

combining and integrating, by the processor, as information belonging to a same object, a plurality of pieces of information present within a first combining area and a second combining area, when a positional relationship between the first combining area and the second combining area meets a predetermined combinable condition, the first combining area being set as an area in which pieces of information related to the object acquired by the first object detecting apparatus are combined, the second combining area being set as an area in which pieces of information related to the object acquired by the second object detecting apparatus are combined; and

variably setting, by the processor, sizes of the first combining area and the second combining area based on a learning state of the axis displacement amount learned by the processor.