Vehicle surroundings monitoring device
View Patent ↗When it is determined that a type of a physical body in real space corresponding to an image portion is a crossing pedestrian, a distance calculating unit 13 performs a first distance calculating process of calculating a distance between a vehicle 1 and the physical body, on the basis of a correlative relationship between the distance from the vehicle 1 set on assumption of a height of the pedestrian and a height of the image portion, according to the height of the image portion. When it is determined that the type of the physical body is not the crossing pedestrian, then the distance calculating unit 13 performs a second distance calculating process which calculates the distance between the physical body and the vehicle, on the basis of a change in size of the image portions of the physical body extracted from time-series captured images.
1. A vehicle surroundings monitoring device, comprising:
a distance calculating unit which calculates, on a basis of a captured image by a single camera mounted on a vehicle, a distance between the vehicle and a physical body in real space corresponding to an image portion extracted from the captured image; and
a physical body type judging unit which judges a type of the physical body in real space corresponding to the image portion;
wherein the distance calculating unit
determines a change in shape of the image portion or a change in shape of the physical body in real space corresponding to the image portion, in a predetermined period,
determines whether to execute a first distance calculating process or a second distance calculating process based on whether the change in shape of the image portion or the change in shape of the physical body in real space corresponding to the image portion, in a predetermined period exceeds a predetermined level,
executes the first distance calculating process, when the change in shape exceeds the predetermined level, of calculating a distance between the physical body and the vehicle, by applying the size of the image portion of the physical body extracted from the captured image to a correlative relationship between a distance from the vehicle in real space set on assumption of the type of the physical body and a size of the image portion in the captured image, and
executes the second distance calculating process, when the change in shape is equal to or less than the predetermined level, of calculating the distance between the physical body and the vehicle, on the basis of the change in size of image portions of the physical body extracted from time-series captured images by the camera.
2. The vehicle surroundings monitoring device according to claim 1 ,
wherein the physical body is a pedestrian crossing a road, and
the distance calculating unit calculates, in the first distance calculating process, of calculating the distance between the physical body in real space corresponding to the image portion and the vehicle, by applying a height of the image portion extracted from the captured image to a correlative relationship between the distance from the vehicle in real space and the height of the image portion in the captured image, set such that a height of the pedestrian is a predetermined value.
3. A vehicle surroundings monitoring method, comprising:
capturing a captured image by a single camera mounted on a vehicle;
extracting an image portion from the captured image;
calculating a distance, using the a captured image, between the vehicle and a physical body in real space corresponding to the image portion; and
judging a type of the physical body in real space corresponding to the image portion;
wherein the step of calculating the distance includes:
determining a change in shape of the image portion or a change in shape of the physical body in real space corresponding to the image portion, in a predetermined period,
determining whether to execute a first distance calculating process or a second distance calculating process based on whether the change in shape of the image portion or the change in shape of the physical body in real space corresponding to the image portion, in a predetermined period exceeds a predetermined level,
executing the first distance calculating process, when the change in shape exceeds the predetermined level, of calculating a distance between the physical body and the vehicle, by applying the size of the image portion of the physical body extracted from the captured image to a correlative relationship between a distance from the vehicle in real space set on assumption of the type of the physical body and a size of the image portion in the captured image, and
executing the second distance calculating process, when the change in shape is equal to or less than the predetermined level, of calculating the distance between the physical body and the vehicle, on the basis of the change in size of image portions of the physical body extracted from time-series captured images by the camera.
4. The vehicle surroundings monitoring method according to claim 3 ,
wherein the physical body is a pedestrian crossing a road, and
the calculation of the distance between the physical body in real space corresponding to the image portion and the vehicle in the first distance calculating process includes applying a height of the image portion extracted from the captured image to a correlative relationship between the distance from the vehicle in real space and the height of the image portion in the captured image, set such that a height of the pedestrian is a predetermined value.
5. A vehicle surroundings monitoring system, comprising:
a single camera mounted on a vehicle; and
an electronic control unit including a processor and a non-transitory computer readable medium storing instructions to be executed by the processor,
wherein the instructions include steps of:
capturing a captured image by the single camera mounted on the vehicle;
extracting an image portion from the captured image;
calculating a distance, using the a captured image, between the vehicle and a physical body in real space corresponding to the image portion; and
judging a type of the physical body in real space corresponding to the image portion;
wherein the step of calculating the distance includes:
determining a change in shape of the image portion or a change in shape of the physical body in real space corresponding to the image portion, in a predetermined period,
determining whether to execute a first distance calculating process or a second distance calculating process based on whether the change in shape of the image portion or the change in shape of the physical body in real space corresponding to the image portion, in a predetermined period exceeds a predetermined level,
executing the first distance calculating process, when the change in shape exceeds the predetermined level, of calculating a distance between the physical body and the vehicle, by applying the size of the image portion of the physical body extracted from the captured image to a correlative relationship between a distance from the vehicle in real space set on assumption of the type of the physical body and a size of the image portion in the captured image, and
executing the second distance calculating process, when the change in shape is equal to or less than the predetermined level, of calculating the distance between the physical body and the vehicle, on the basis of the change in size of image portions of the physical body extracted from time-series captured images by the camera.
6. The vehicle surroundings monitoring system according to claim 5 ,
wherein the physical body is a pedestrian crossing a road, and
the instructions for the calculation of the distance between the physical body in real space corresponding to the image portion and the vehicle in the first distance calculating process include applying a height of the image portion extracted from the captured image to a correlative relationship between the distance from the vehicle in real space and the height of the image portion in the captured image, set such that a height of the pedestrian is a predetermined value.