Road surface state determination apparatus, imaging apparatus, imaging system, and road surface state determination method
A road surface state determination apparatus of the present disclosure includes an acquisition interface configured to acquire an image representing a road surface imaged by a camera, and a controller configured to determine whether the road surface is wet or dry on the basis of a spatial change in luminance of pixels in a continuous region included in the image.
1. A road surface state determination apparatus comprising:
an acquisition interface configured to acquire an image representing a road surface imaged by a camera; and
a controller configured to determine whether the road surface is wet or dry on the basis of a spatial change in luminance of pixels in a continuous region included in the image,
wherein the controller is configured to calculate a parameter corresponding to a spatial frequency of the luminance and to determine a wet region of the road surface on the basis of the calculated parameter, and
wherein the controller is configured to extract a frequency continuous portion in which the parameter corresponding to the spatial frequency of the continuous region of the image is continuous across at least a predetermined length, and when a plurality of frequency continuous portions is extracted, to determine that the road surface is wet at the frequency continuous portion, among the extracted plurality of frequency continuous portions, in which the parameter corresponds to a lower spatial frequency.
2. The road surface state determination apparatus of claim 1 , wherein the controller is configured to detect a non-vibration component that indicates variation in overall luminance height excluding a luminance vibration component caused by a shape of the road surface and to determine whether at least a portion of the road surface is wet on the basis of a change in the non-vibration component.
3. The road surface state determination apparatus of claim 2 , wherein the controller is configured to extract, from among pixels included in the continuous region of the image, a luminance continuous portion in which the non-vibration component is continuous across at least a predetermined length, and when a plurality of the luminance continuous portions is extracted, to determine whether at least a portion of the road surface is wet by comparing the non-vibration components corresponding to the extracted plurality of the luminance continuous portions.
4. The road surface state determination apparatus of claim 1 , wherein the controller is configured to perform a process to detect a lane marking on the road surface from a change in luminance of the pixels in the continuous region included in the image, to determine that the road surface is dry when detection of the lane marking is successful, and to determine that the road surface is wet when detection of the lane marking is unsuccessful.
5. The road surface state determination apparatus of claim 1 , wherein the acquisition interface is configured to acquire, from a temperature detector configured to measure a temperature of a road surface, a signal related to the temperature of the road surface, and the controller is configured to determine whether the road surface is frozen on the basis of the signal related to the temperature of the road surface.
6. The road surface state determination apparatus of claim 5 , wherein the temperature detector is a far infrared camera configured to image the road surface, and the controller is configured to determine whether a predetermined region on the road surface is frozen on the basis of a far infrared image captured by the far infrared camera.
7. An imaging apparatus comprising:
a camera; and
a road surface state determination apparatus comprising an acquisition interface configured to acquire an image representing a road surface imaged by the camera, and a controller configured to determine whether the road surface is wet or dry on the basis of a spatial change in luminance of pixels in a continuous region included in the image,
wherein the controller is configured to calculate a parameter corresponding to a spatial frequency of the luminance and to determine a wet region of the road surface on the basis of the calculated parameter, and
wherein the controller is configured to extract a frequency continuous portion in which the parameter corresponding to the spatial frequency of the continuous region of the image is continuous across at least a predetermined length, and when a plurality of frequency continuous portions is extracted, to determine that the road surface is wet at the frequency continuous portion, among the extracted plurality of frequency continuous portions, in which the parameter corresponds to a lower spatial frequency.
8. An imaging system comprising:
a temperature detector configured to measure a temperature of a road surface; and
an imaging apparatus comprising a camera and a road surface state determination apparatus, the road surface state determination apparatus comprising an acquisition interface configured to acquire an image representing a road surface imaged by the camera and a signal related to the temperature of the road surface and a controller configured to determine whether the road surface is wet or dry on the basis of a luminance of pixels included in the image and to determine whether the road surface is frozen on the basis of the signal related to the temperature of the road surface,
wherein the controller is configured to calculate a parameter corresponding to a spatial frequency of the luminance and to determine a wet region of the road surface on the basis of the calculated parameter, and
wherein the controller is configured to extract a frequency continuous portion in which the parameter corresponding to the spatial frequency of the continuous region of the image is continuous across at least a predetermined length, and when a plurality of frequency continuous portions is extracted, to determine that the road surface is wet at the frequency continuous portion, among the extracted plurality of frequency continuous portions, in which the parameter corresponds to a lower spatial frequency.
9. A road surface state determination method comprising:
acquiring, using an acquisition interface, an image representing a road surface imaged by a camera, and
determining, using a controller, whether the road surface is wet or dry on the basis of a spatial change in luminance of pixels in a continuous region included in the image, by at least
calculating a parameter corresponding to a spatial frequency of the luminance and determining a wet region of the road surface on the basis of the calculated parameter, and
extracting a frequency continuous portion in which the parameter corresponding to the spatial frequency of the continuous region of the image is continuous across at least a predetermined length, and when a plurality of frequency continuous portions is extracted, determining that the road surface is wet at the frequency continuous portion, among the extracted plurality of frequency continuous portions, in which the parameter corresponds to a lower spatial frequency.