Information processing device, information processing method, and storage medium storing a program

A sensor-based object detection apparatus for a vehicle, comprising:

• a first image sensor provided in the vehicle and configured to capture images of an object at a first frame rate, the first image sensor having a variable frame rate and including a left image sensor and a right image sensor;
• a second image sensor provided in the vehicle and configured to capture images of the object at a second frame rate lower than the first frame rate, the second image sensor facing a direction in which an imaging range of the second image sensor overlaps with an imaging range of the first image sensor;
• a radar provided in the vehicle and configured to acquire three-dimensional point cloud data of the object;
• and
• circuitry configured to:
• output point information obtained by recognizing the object as coordinate values on at least two coordinate axes of a three-dimensional orthogonal coordinate system from the images captured by the first image sensor,
• derive a z coordinate value of the object by combining coordinate values derived from the images captured by the left image sensor and the right image sensor using a principle of a stereo camera with a z coordinate value indicated by the three-dimensional point cloud data acquired by the radar,
• output identification information indicating a type of the object from the images captured by the second image sensor,
• associate the point information with the identification information,
• change the frame rate of the first image sensor according to a risk score related to an external environment of the vehicle, and
• perform driving control of the vehicle based on a result obtained by simulating a movement of the object on a digital map on which the point information and the identification information which are associated with each other are plotted.

A sensor-based object detection method executed by a computer, the method comprising:

• capturing, by a first image sensor provided in a vehicle, images of an object at a first frame rate;
• capturing, by a second image sensor provided in the vehicle and facing a direction in which an imaging range of the second image sensor overlaps with an imaging range of the first image sensor, images of the object at a second frame rate lower than the first frame rate;
• outputting point information obtained by recognizing the object as coordinate values on at least two coordinate axes of a three-dimensional orthogonal coordinate system from the images captured by the first image sensor, the point information including position information and movement information indicating a movement of the object;
• outputting identification information indicating a type of the object from the images captured by the second image sensor;
• associating the point information with the identification information;
• and
• performing driving control of the vehicle based on a result obtained by simulating a movement of the object on a digital map on which the point information and the identification information which are associated with each other are plotted.