Vehicle driving hazard recognition and avoidance apparatus and vehicle control device
A vehicle exterior environment recognition apparatus includes a computer configured to serve as a target region setting unit, an edge counter, and a wheel determiner. The target region setting unit sets, as one or more target regions, one or more predetermined ranges of a screen. The edge counter provides setting of a plurality of divided sections, by dividing each of the one or more target regions with borderlines radiated from a center of each of the one or more target regions, and counts the number of predetermined slant edges and the total number of blocks in each of the plurality of divided sections. The wheel determiner determines wheel-likeliness of each of the one or more target regions, based on a rate of the number of the slant edges to the total number of blocks in each of the plurality of divided sections.
1. A vehicle exterior environment recognition apparatus, comprising:
a central processing unit (CPU); and
a machine-readable medium comprising instructions stored therein, which when executed by the CPU, cause the CPU to perform operations comprising:
obtaining, from an image capturing device, at least one image of vehicle exterior environment in a traveling direction of an vehicle;
setting, as one or more target regions, one or more predetermined ranges in the at least one image when at least part of an object in the traveling direction of the vehicle is captured in the at least one image, wherein the one or more predetermined ranges encompass the at least part of the object;
dividing each of the one or more target regions into a plurality of divided sections, wherein each of the one or more target regions comprises borderlines between adjacent divided sections of the plurality of divided sections, and wherein the borderlines cross a center of the target region, and wherein each of the plurality of divided sections comprises a plurality of blocks;
counting a number of blocks comprising predetermined slant edges and a total number of blocks in each of the plurality of divided sections;
determining a ratio of the number of blocks comprising the slant edges to the total number of blocks in each of the plurality of divided sections; and
determining that the at least part of the object in the one or more target regions is a wheel based on determining wheel-likeliness of the at least part of the object in the one or more target regions based on the determined ratio.
2. The vehicle exterior environment recognition apparatus according to claim 1 , wherein the borderlines crosses the center of the target region horizontally and vertically.
3. The vehicle exterior environment recognition apparatus according to claim 1 , further comprising deriving one or more centers of gravity of the slant edges for each of the plurality of divided sections, and
determining the wheel-likeliness of each of the one or more target regions further based on relative distances from the centers of gravity to a reference position that is predetermined for each of the plurality of divided sections.
4. The vehicle exterior environment recognition apparatus according to claim 2 , further comprising deriving one or more centers of gravity of the slant edges for each of the plurality of divided sections, and
determining the wheel-likeliness of each of the one or more target regions further based on relative distances from the centers of gravity to a reference position that is predetermined for each of the plurality of divided sections.
5. The vehicle exterior environment recognition apparatus according to claim 1 , wherein one of the plurality of divided sections is given more weight than remaining ones of the plurality of divided sections based on a moving direction of a section of the at least part of the object in the one of the plurality of divided sections and a position of the section of the at least part of the object in with respect to a road surface.
6. The vehicle exterior environment recognition apparatus according to claim 2 , wherein one of the plurality of divided sections is given more weight than remaining ones of the plurality of divided sections based on a moving direction of a section of the at least part of the object in the one of the plurality of divided sections and a position of the section of the at least part of the object in with respect to a road surface.
7. The vehicle exterior environment recognition apparatus according to claim 3 , wherein one of the plurality of divided sections is given more weight than remaining ones of the plurality of divided sections based on a moving direction of a section of the at least part of the object in the one of the plurality of divided sections and a position of the section of the at least part of the object in with respect to a road surface.
8. The vehicle exterior environment recognition apparatus according to claim 4 , wherein one of the plurality of divided sections is given more weight than remaining ones of the plurality of divided sections based on a moving direction of a section of the at least part of the object in the one of the plurality of divided sections and a position of the section of the at least part of the object in with respect to a road surface.
9. The vehicle exterior environment recognition apparatus according to claim 1 , wherein each of the one or more target regions is differently sized from one another based on a plurality of specifications of a wheel of a bicycle.
10. The vehicle exterior environment recognition apparatus according to claim 2 , wherein each of the one or more target regions is differently sized from one another based on a plurality of specifications of a wheel of a bicycle.
11. The vehicle exterior environment recognition apparatus according to claim 3 , wherein each of the one or more target regions is differently sized from one another based on a plurality of specifications of a wheel of a bicycle.
12. The vehicle exterior environment recognition apparatus according to claim 4 , wherein each of the one or more target regions is differently sized from one another based on a plurality of specifications of a wheel of a bicycle.
13. The vehicle exterior environment recognition apparatus according to claim 5 , wherein each of the one or more target regions is differently sized from one another based on a plurality of specifications of a wheel of a bicycle.
14. The vehicle exterior environment recognition apparatus according to claim 6 , wherein each of the one or more target regions is differently sized from one another based on a plurality of specifications of a wheel of a bicycle.
15. The vehicle exterior environment recognition apparatus according to claim 7 , wherein each of the one or more target regions is differently sized from one another based on a plurality of specifications of a wheel of a bicycle.
16. The vehicle exterior environment recognition apparatus according to claim 8 , wherein each of the one or more target regions is differently sized from one another based on a plurality of specifications of a wheel of a bicycle.
17. A vehicle control device, comprising:
a central processing unit (CPU); and
a machine-readable medium comprising instructions stored therein, which when executed by the CPU, cause the CPU to perform operations comprising:
obtaining, from an image capturing device, at least one image of vehicle exterior environment in a traveling direction of an vehicle;
setting, as one or more target regions, one or more predetermined ranges in the at least one image when at least part of an object in the traveling direction of the vehicle is captured in the at least one image, wherein the one or more predetermined ranges encompass the at least part of the object;
dividing each of the one or more target regions into a plurality of divided sections, wherein each of the one or more target regions comprises borderlines between adjacent divided sections of the plurality of divided sections, and wherein the borderlines cross a center of the target region, and wherein each of the plurality of divided sections comprises a plurality of blocks;
counting a number of blocks comprising predetermined slant edges of the plurality of blocks and a total number of the plurality of blocks in each of the plurality of divided sections;
determining a ratio of the number of blocks comprising the slant edges to the total number of blocks in each of the plurality of divided sections;
determining that the at least part of the object in the one or more target regions is a wheel based on determining wheel-likeliness of the at least part of the object in the one or more target regions based on the determined ratio; and
executing a collision avoidance control to avoid a collision with the object based on determining that the at least part of the object in the one or more target regions is a wheel.