Information processing device and information processing method
An information processing device ( 100 ) includes a calibration execution unit ( 195 ) that performs calibration between two or more sensors which are attached at different positions and of which visual field regions at least partially overlap each other. The calibration execution unit ( 195 ) performs the calibration between the sensors in a case where a feature point that enables calibration of each of the two or more sensors is acquirable in a region in which visual fields of the two or more sensors overlap each other.
1. An information processing device, comprising:
a central processing unit (CPU) configured to:
perform calibration between two or more sensors which are attached at different positions of a vehicle and of which visual field regions at least partially overlap each other,
wherein the calibration between the two or more sensors is performed in a case where a feature point that enables the calibration of each of the two or more sensors is acquirable in a region in which the visual fields of the two or more sensors overlap each other;
acquire information regarding whether a specific object, having the feature point that enables the calibration between the two or more sensors, is present in an acquirable range around the vehicle, wherein
the acquired information include position information and posture information of the specific object;
determine whether the feature point is acquirable from the specific object, in the region in which the visual fields of the two or more sensors overlap each other, in a case where the specific object is present in the acquirable range around the vehicle,
wherein whether the feature point is acquirable from the specific object is determined based on position information and posture information of the two or more sensors or the vehicle to which the two or more sensors are attached, and the position information and the posture information of the specific object having the feature point that enables the calibration of each of the two or more sensors; and
acquire the feature point in a case where the CPU determines that the feature point is acquirable.
2. The information processing device according to claim 1 , wherein
the two or more sensors comprises a camera and a sensor, and the CPU is further configured to:
recognize an image captured by the camera; and
acquire the feature point, that enables the calibration of each of the camera and the sensor, in the captured image.
3. The information processing device according to claim 1 , wherein the CPU is further configured to receive information regarding whether the specific object is present in the acquirable range around the vehicle by road-to-vehicle communication (V2X communication).
4. The information processing device according to claim 1 , wherein the CPU is further configured to receive information regarding whether the specific object is present in the acquirable range around the vehicle by vehicle-to-vehicle communication.
5. The information processing device according to claim 1 , wherein
at least one of the two or more sensors is a camera, and
the specific object is a checkerboard installed in another vehicle.
6. The information processing device according to claim 1 , wherein
at least one of the two or more sensors is a millimeter wave radar, and
the specific object is a corner reflector installed in another vehicle.
7. The information processing device according to claim 1 , wherein the specific object is another vehicle.
8. An information processing method, comprising:
performing calibration between two or more sensors which are attached at different positions of a vehicle and of which visual field regions at least partially overlap each other,
wherein the calibration between the two or more sensors is performed in a case where a feature point that enables the calibration of each of the two or more sensors is acquirable in a region in which the visual fields of the two or more sensors overlap each other;
acquiring information regarding whether a specific object, having the feature point that enables the calibration between the two or more sensors, is present in an acquirable range around the vehicle, wherein
the acquired information include position information and posture information of the specific object;
determining whether the feature point is acquirable from the specific object, in the region in which the visual fields of the two or more sensors overlap each other, in a case where the specific object is present in the acquirable range around the vehicle,
wherein whether the feature point is acquirable from the specific object is determined based on position information and posture information of the two or more sensors or the vehicle to which the two or more sensors are attached, and the position information and the posture information of the specific object having the feature point that enables the calibration of each of the two or more sensors; and
acquiring the feature point in a case where the feature point is determined as acquirable.
9. A non-transitory computer-readable medium having stored thereon, computer-executable instructions that when executed by a computer, causes the computer to execute operations for causing a wind measuring device to perform a wind speed measuring process, the operations comprising:
performing calibration between two or more sensors which are attached at different positions of a vehicle and of which visual field regions at least partially overlap each other,
wherein the calibration between the two or more sensors is performed in a case where a feature point that enables the calibration of each of the two or more sensors is acquirable in a region in which the visual fields of the two or more sensors overlap each other;
acquiring information regarding whether a specific object, having the feature point that enables the calibration between the two or more sensors, is present in an acquirable range around the vehicle, wherein
the acquired information include position information and posture information of the specific object;
determining whether the feature point is acquirable from the specific object, in the region in which the visual fields of the two or more sensors overlap each other, in a case where the specific object is present in the acquirable range around the vehicle,
wherein whether the feature point is acquirable from the specific object is determined based on position information and posture information of the two or more sensors or the vehicle to which the two or more sensors are attached, and the position information and the posture information of the specific object having the feature point that enables the calibration of each of the two or more sensors; and
acquiring the feature point in a case where the feature point is determined as acquirable.