Object detection device and object detection method

1. An object detection device comprising:

a range image generating unit that generates a range image based on a pair of gray-scaled images;

a grouping unit that groups adjacent regions having range data representing close distances in the range image; and

a dividing unit that divides a group region created by the grouping based on the gray-scaled images;

wherein the dividing unit divides the group region into laterally separated sub-regions, based on differences between the luminance values of pixels in a vertical line below a ground plane above which objects are imaged and the luminance values of pixels in a vertical line above the ground plane in the gray-scaled images; and

wherein the dividing unit divides the group region into laterally separated sub-regions, based on a boundary between a region where the luminance difference is large and a region where the luminance difference is small.

2. An object detection device comprising:

a range image generating unit that generates a range image based on a pair of gray-scaled images;

a grouping unit that groups adjacent regions having range data representing close distances in the range image;

a dividing unit that divides a group region created by the grouping based on the gray-scaled images; and

a merging unit that merges sub-regions made based on the gray-scaled images, based on vertical edges in the sub-regions made based on the gray-scaled images;

wherein the dividing unit divides the group region into laterally separated sub-regions, based on differences between the luminance values of pixels in a vertical line below a ground plane above which objects are imaged and the luminance values of pixels in a vertical line above the ground plane in the gray-scaled images; and

wherein, if a section without vertical edge exists in either of the left and right areas of each of sub-regions made based on the gray-scaled images, the merging unit merges sub-regions whose areas including a section without vertical edge are next to each other.

3. The object detection device according to claim 2 ,

wherein the pair of gray-scaled images is gray-scaled images based on images captured by a pair of image capturing units mounted on a vehicle, and

wherein the object detection device further comprises a vehicle detecting unit that detects, as a vehicle, an object imaged in a merged region by the merging unit.

4. An object detection method comprising the steps of:

generating a range image based on a pair of gray-scaled images;

grouping adjacent regions having range data representing close distances in the range image; and

dividing a group region created by the grouping based on the gray-scaled images;

wherein the dividing step divides the group region into laterally separated sub-regions, based on differences between the luminance values of pixels in a vertical line below a ground plane above which objects are imaged and the luminance values of pixels in a vertical line above the ground plane in the gray-scaled images;

wherein the dividing step comprises the steps of:

calculating differences between the luminance values of pixels in a vertical line below a ground plane above which objects are imaged and the luminance values of pixels in a vertical line above the ground plane in the gray-scaled images; and

dividing the group region into laterally separated sub-regions based on the differences between the luminance values.

5. An object detection method comprising the steps of:

generating a range image based on a pair of gray-scaled images;

grouping adjacent regions having range data representing close distances in the range image;

dividing a group region created by the grouping based on the gray-scaled images;

wherein the dividing step divides the group region into laterally separated sub-regions, based on differences between the luminance values of pixels in a vertical line below a ground plane above which objects are imaged and the luminance values of pixels in a vertical line above the ground plane in the gray-scaled images;

determining whether or not a section without vertical edge exists in either of the left and right areas of each of sub-regions made based on the gray-scaled images; and

merging sub-regions whose areas including a section without vertical edge are next to each other.