Image processing device and image processing method
US-10812735-B2 · Oct 20, 2020 · US
US11373418B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11373418-B2 |
| Application number | US-201816634580-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jul 25, 2018 |
| Priority date | Aug 4, 2017 |
| Publication date | Jun 28, 2022 |
| Grant date | Jun 28, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An information processing apparatus capable of detecting a plane constituting a movement-enabling region. A normal direction of a plane constituting a road surface is detected on the basis of polarized images in multiple polarizing directions acquired by a polarization camera. A laser ranging sensor measures a distance to a point on the road surface so as to measure a position of the point. The plane constituting the road surface is identified on the basis of information regarding the normal direction of the plane constituting the road surface and information regarding the position of the point on the road surface.
Opening claim text (preview).
The invention claimed is: 1. An information processing apparatus comprising: a polarization camera configured to acquire polarized images in a plurality of polarizing directions, circuitry configured to: detect a normal direction of a plane constituting a movement-enabling region for a mobile object on a basis of the polarized images; identify a position of a point on the plane constituting the movement-enabling region; and recognize the plane constituting the movement-enabling region on a basis of the normal direction of the movement-enabling region and the position of the point in the movement-enabling region, wherein the detecting the normal direction of the plane constituting the movement-enabling region for the mobile object on the basis of the polarized images comprises: detecting, in units of pixels, a normal direction of a surface of a subject in the polarized images before outputting the detected normal direction as a normal vector map; reconstructing an unpolarized image from the polarized images; and setting an attribute of the subject to each of the pixels in the unpolarized image, wherein the circuitry detects a dominant normal direction on the normal vector map corresponding to a region having those pixels in the unpolarized image of which the attribute is set to the movement-enabling region, the dominant normal direction being the normal direction of the plane constituting the movement-enabling region, and wherein the subject is semantically labelled as a road surface, an obstacle, or sky. 2. The information processing apparatus according to claim 1 , wherein the circuitry sets, through semantic segmentation, the attribute of the subject to each of the pixels in the unpolarized image. 3. The information processing apparatus according to claim 1 , wherein the circuitry is further configured to generate an environmental map on a basis of information regarding the attribute of the subject set to each of the pixels in the unpolarized image and information regarding the plane identified by the plane identification section. 4. The information processing apparatus according to claim 3 , wherein, given the information regarding the attribute of the subject set to each of the pixels in the unpolarized image, the circuitry generates the environmental map on a basis of information regarding the pixels of which the attribute is set to the movement-enabling region and information regarding the pixels of which the attribute is set to an obstacle, the environmental map being indicative of a position of the obstacle on the plane constituting the movement-enabling region. 5. The information processing apparatus according to claim 4 , wherein, given the information regarding the attribute of the subject set to each of the pixels in the unpolarized image, the circuitry generates the environmental map by taking the position on the plane constituting the movement-enabling region and corresponding to a boundary pixel in a vertically downward direction between the region of the pixels of which the attribute is set to the movement-enabling region on one hand and the region of the pixels of which the attribute is set to the obstacle on the other hand, as the position of the obstacle on the plane constituting the movement-enabling region. 6. The information processing apparatus according to claim 3 , wherein the environmental map is an occupancy grid map. 7. The information processing apparatus according to claim 1 , wherein the circuitry is further configured to integrate a coordinate system indicative of the position of the point identified by the circuitry in the movement-enabling region with a coordinate system of the polarized images acquired by the polarization camera. 8. The information processing apparatus according to claim 1 , further comprising: a ranger configured to measure a distance to a point in the movement-enabling region, wherein the circuitry is configured to identify the position of the point in the movement-enabling region on a basis of the distance, measured by the ranger, to the point in the movement-enabling region. 9. The information processing apparatus according to claim 8 , wherein the ranger includes a laser ranging sensor, a stereo camera, or a millimeter-wave radar. 10. The information processing apparatus according to claim 1 , wherein the movement-enabling region includes a road surface. 11. An information processing method comprising the steps of: acquiring polarized images in a plurality of polarizing directions; detecting, on a basis of the polarized images, a normal direction of a plane constituting a movement-enabling region for a mobile object; identifying a position of a point in the movement-enabling region; and recognizing the plane constituting the movement-enabling region on a basis of the normal direction of the movement-enabling region and the position of the point in the movement-enabling region, wherein the detecting the normal direction of the plane constituting the movement-enabling region for the mobile object on the basis of the polarized images comprises: detecting, in units of pixels, a normal direction of a surface of a subject in the polarized images before outputting the detected normal direction as a normal vector map; reconstructing an unpolarized image from the polarized images; and setting an attribute of the subject to each of the pixels in the unpolarized image, wherein a dominant normal direction on the normal vector map corresponding to a region having those pixels in the unpolarized image of which the attribute is set to the movement-enabling region is detected, the dominant normal direction being the normal direction of the plane constituting the movement-enabling region, and wherein the subject is semantically labelled as a road surface, an obstacle, or sky. 12. A non-transitory computer readable memory device that includes instructions that when executed by a processor cause the processor to perform a method, the method comprising: acquiring polarized images in a plurality of polarizing directions; detecting, on a basis of the polarized images, a normal direction of a plane constituting a movement-enabling region for a mobile object; identifying a position of a point on the plane constituting the movement-enabling region; and recognizing the plane constituting the movement-enabling region on a basis of the normal direction of the movement-enabling region and the position of the point in the movement-enabling region, wherein the detecting the normal direction of the plane constituting the movement-enabling region for the mobile object on the basis of the polarized images comprises: detecting, in units of pixels, a normal direction of a surface of a subject in the polarized images before outputting the detected normal direction as a normal vector map; reconstructing an unpolarized image from the polarized images; and setting an attribute of the subject to each of the pixels in the unpolarized image, wherein a dominant normal direction on the normal vector map corresponding to a region having those pixels in the unpolarized image of which the attribute is set to the movement-enabling region is detected, the dominant normal direction being the normal direction of the plane constituting the movement-enabling region, and wherein the subject is semantically labelled as a road surface, an obstacle, or sky. 13. A mobile object comprising the information processing apparatus of claim 1 .
Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera · CPC title
by matching two-dimensional images to three-dimensional objects · CPC title
of input or preprocessed data · CPC title
relating to illumination properties, e.g. using a reflectance or lighting model · CPC title
Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.