IMAGE PROCESSING DEVICE

• US 20150294163A1
• Filed: 03/16/2015
• Published: 10/15/2015
• Est. Priority Date: 04/15/2014
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: SAKAMOTO, Yosuke
• Granted Patent: US 10,185,879 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

Provided is an image processing device in which a region targeted for edge extraction of a taken image is divided into a plurality of partial regions 11(1) to 11(7) for which threshold values for edge extraction different from each other are set, respectively. An edge extraction unit 5, which extracts edges from the region targeted for edge extraction, performs processing of extracting the edges in the partial regions 11(1) to 11(7) by using the threshold values set so as to correspond to the each of the partial regions 11(1) to 11(7).

Claims

1. An image processing device comprising an edge extraction unit which extracts an edge from a taken image by comparing a pixel value change in the image taken by an imaging device which takes an image of a monitoring region with a given threshold value,

wherein a region targeted for edge extraction, which is a region in the taken image in which the edge extraction unit performs a processing of extracting the edge from the taken image, is divided, into a plurality of partial regions for which the threshold values different from each other are set, respectively, and

wherein the edge extraction unit is configured to perform the processing of extracting the edge in each of the partial regions of the region targeted for edge extraction by using the threshold values set corresponding to the partial regions.

2. The image processing device, according to claim 1, wherein the threshold values are set so that a threshold value in a partial region where an image of a portion which is at a relatively long distance from the imaging device in a real space is projected is smaller than a threshold value in a partial region where an image of a portion which is at a relatively short distance from the imaging device is projected, among the plurality of partial regions.

3. The image processing device according to claim 1, further comprising a threshold updating unit configured to update the threshold values in one or more respective partial regions among the plurality of partial regions according to a number of edges extracted by the edge extraction unit in local regions of the partial regions concerned.

4. The image processing device according to claim 1,

wherein the monitoring region whose image is taken by the imaging device is a region including a vehicle traveling road surface, and

wherein the image processing device further comprises:

a lane mark recognition unit configured to recognize an image of lane marks on the vehicle traveling road surface by using the edges extracted by the edge extraction unit in the region targeted for edge extraction including an image of the vehicle traveling road surface; and

a threshold updating unit configured to update the threshold values in the one or more respective partial regions, in which at least the image of the lane marks is likely to be shown among the plurality of partial regions, according to a number of edges extracted by the edge extraction unit in local regions set in each of the one or more partial regions concerned so as to show an image of a road surface between the right and left lane marks of the vehicle traveling road surface.

5. The image processing device according to claim 1,

wherein the monitoring region whose image is taken by the imaging device is a region including a vehicle traveling road s dace, and

wherein the image processing device further comprises:

a lane mark recognition unit configured to recognize an image of lane marks on the vehicle traveling road surface by using the edges extracted by the edge extraction unit in the region targeted for edge extraction including an image of the vehicle traveling road surface; and

a threshold updating unit configured to update the threshold values in the one or more respective partial regions, in which at least the image of the lane marks is likely to be shown among the plurality of partial regions, according to a number of edges extracted by the edge extraction unit in local regions set in each of the one or more partial regions concerned so as to show the image of the lane marks.

6. The image processing device, according to claim 4, wherein the threshold updating unit is configured to estimate locations of the lane marks in a new taken image based on positions in the taken image of the lane marks ahead y recognized by the lane mark recognition unit before updating the threshold values and to set the local regions based on the estimation result.

7. The image processing device according to claim 5, wherein the threshold updating unit is configured to estimate locations of the lane marks in a new taken image based on positions in the taken image of the lane marks already recognized by the lane mark recognition unit before updating the threshold values and to set the local regions based on the estimation result.