Image processing apparatus, imaging device, moving object device control system, and image processing method

Patent metadata

Field	Value
Publication number	US-10650271-B2
Application number	US-201715453532-A
Country	US
Kind code	B2
Filing date	Mar 8, 2017
Priority date	Mar 8, 2016
Publication date	May 12, 2020
Grant date	May 12, 2020

Abstract

An image processing apparatus includes a processor configured to generate vertical direction distribution data which is a distribution of distance values to a vertical direction of a distance image from the distance image having distance values according to distance of a road surface in captured images. There is an extraction of a pixel having the highest frequency value for each of the distance values from pixels in a search area. There is a detection of the road surface based on each pixel extracted.

First claim

What is claimed is:

1. An image processing apparatus comprising:
a processor configured to:
generate vertical direction distribution data which is a distribution of distance values along a vertical direction to a distance image from the distance image having distance values according to distance of a road surface in captured images obtained by an imaging circuit mounted on a moving object;
select one coordinate on abscissa axis of coordinates of a map represented by the vertical direction distribution data and set the selected one coordinate as an observation point;
select a range on the abscissa axis of the coordinate, the range including the observation point;
set a search area having a width corresponding to the range on the abscissa axis and a height;
extract a pixel having a highest frequency value for each of the distance values from pixels in the search area;
detect the road surface based on each pixel extracted; and
control the moving object based on the detected road surface.

2. The image processing apparatus according to claim 1 , wherein
the height of the search area has a value which is greater than or equal to a predetermined value of each of the distance values and is a predetermined height from the lowest pixel in the vertical direction in the vertical direction distribution data.

3. The image processing apparatus according to claim 1 , wherein the processor is further configured to:
calculate an approximate line based on each pixel extracted;
remove a pixel which is greater than a predetermined distance from the approximate line; and
detect the road surface based on pixels which have not been removed.

4. The image processing apparatus according to claim 3 , wherein the processor is further configured to:
remove the pixel which is greater than the predetermined distance, the predetermined distance corresponding to a distance of the road surface.

5. An imaging device comprising:
a plurality of imaging circuits mounted on a moving object;
circuitry configured to:
generate a distance image having distance values according to a parallax of a road surface in captured images obtained by the plurality of imaging circuits;
generate vertical direction distribution data which is a distribution of distance values along a vertical direction to the distance image;
select one coordinate on abscissa axis of coordinates of a map represented by the vertical direction distribution data and set the selected one coordinate as an observation point;
select a range on the abscissa axis of the coordinate, the range including the observation point;
set a search area having a width corresponding to the range on the abscissa axis and a height;
extract a pixel having a highest frequency value for each of the distance values from pixels in the search area;
detect the road surface based on each pixel which has been extracted; and
control the moving object based on the detected road surface.

6. A moving object device control system comprising:
a plurality of imaging circuits mounted at a moving object which captures images of a forward area of the moving object;
circuitry configured to:
generate a distance image having distance values according to a parallax of a moving surface or a road surface in captured images obtained by the plurality of imaging circuits;
generate vertical direction distribution data which is a distribution of distance values along vertical direction to the distance image;
select one coordinate on abscissa axis of coordinates of a map represented by the vertical direction distribution data and set the selected one coordinate as an observation point;
select a range on the abscissa axis of the coordinate, the range including the observation point;
set a search area having a width corresponding to the range on the abscissa axis and a height;
extract a pixel having a highest frequency value for each of the distance values from pixels in the search area; and
detect the moving surface or the road surface based on each pixel which has been extracted;
detect an object based on the moving surface detected or the distance image; and
control the moving object based on data of the object which has been detected.

7. An image generation method, comprising:
generating vertical direction distribution data which is a distribution of distance values along a vertical direction to a distance image from the distance image having distance values according to distance of a road surface in captured images obtained by an imaging circuit mounted on a moving object;
selecting one coordinate on abscissa axis of coordinates of a map represented by the vertical direction distribution data and setting the selected one coordinate as an observation point;
selecting a range on the abscissa axis of the coordinate, the range including the observation point;
setting a search area having a width corresponding to the range on the abscissa axis and a height;
extracting a pixel having a highest frequency value for each of the distance values from pixels in the search area;
detecting the road surface based on each pixel extracted; and
controlling the moving object based on the detected road surface.

Assignees

• Nakata Otoichi
• Motohashi Naoki
• Sumiyoshi Shinichi
• Ricoh Co Ltd

Inventors

• Nakata Otoichi
• Motohashi Naoki
• Sumiyoshi Shinichi

Classifications

• G06T7/73

  using feature-based methods · CPC title

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• B60R2300/303

  using joined images, e.g. multiple camera images · CPC title

• H04N2013/0092

  Image segmentation from stereoscopic image signals · CPC title

• H04N2013/0081

  Depth or disparity estimation from stereoscopic image signals · CPC title