Search

CN-115147480-B - Object detection device, object detection method, and storage medium

CN115147480BCN 115147480 BCN115147480 BCN 115147480BCN-115147480-B

Abstract

Provided are an object detection device, an object detection method, and a storage medium, which can reduce the processing load while maintaining high detection accuracy. The object detection device is provided with an acquisition unit that acquires a captured image obtained on a captured road, a low-resolution image generation unit that generates a low-resolution image that reduces the image quality of the captured image, a definition unit that defines one or more partial region groups each of which is defined by cutting out a plurality of partial regions from the low-resolution image, and an extraction unit that derives a summary value obtained by summing up differences in feature amounts between the partial regions in the one or more partial region groups and the surrounding partial regions, and extracts a region of interest based on the summary value.

Inventors

  • YASUI YUJI

Assignees

  • 本田技研工业株式会社

Dates

Publication Date
20260505
Application Date
20220215
Priority Date
20210331

Claims (7)

  1. 1. An object detection device, wherein, The object detection device is provided with: an acquisition unit that acquires a captured image obtained on a captured road; a low resolution image generation unit that generates a low resolution image in which the image quality of the captured image is reduced; A definition unit that defines one or more partial region groups each defined by cutting out a plurality of partial regions from the low resolution image, and An extraction unit that derives, for each of the partial regions included in the one or more partial region groups, a summary value obtained by summing up differences in feature amounts between the partial regions and the surrounding partial regions, extracts a region of interest based on the summary value, The definition section defines a plurality of the partial region groups in such a manner that the numbers of pixels in the partial regions are different from each other between the plurality of the partial region groups, The moving body is caused to autonomously travel in accordance with a determination result of an object at the region of interest of the captured image.
  2. 2. The object detection device according to claim 1, wherein, The extraction unit extracts the region of interest by adding the sum values pixel by pixel among the plurality of partial region groups.
  3. 3. The object detection device according to claim 1 or 2, wherein, The extraction unit sums up differences in feature amounts between the partial areas adjacent to each other in the vertical, horizontal, and diagonal directions with respect to the partial areas included in the one or more partial area groups, and derives the sum value.
  4. 4. The object detection device according to claim 3, wherein, The extraction unit further adds, to the sum value, a difference in feature amounts between the partial regions adjacent to each other in the vertical direction, a difference in feature amounts between the partial regions adjacent to each other in the horizontal direction, and a difference in feature amounts between the partial regions adjacent to each other in the diagonal direction, to the partial regions included in the one or more partial region groups, respectively.
  5. 5. The object detection device according to claim 1 or 2, wherein, The object detection device further includes a high-resolution processing unit that performs high-resolution processing on the target portion in the captured image, and determines whether or not an object on the road is an object that the moving object should avoid touching.
  6. 6. An object detection method, which is executed using a computer, wherein, The object detection method comprises the following steps: acquiring a photographed image obtained on a photographing path; generating a low resolution image that reduces the image quality of the captured image; Defining more than one partial region group, and Deriving a summary value obtained by summing up differences in feature amounts between the partial regions included in the one or more partial region groups and the peripheral partial regions, extracting a region of interest based on the summary value, The one or more partial areas are defined by cutting out a plurality of the partial areas from the low resolution image respectively, The number of pixels in the partial areas is different from each other between the plurality of partial area groups, The moving body is caused to autonomously travel in accordance with a determination result of an object at the region of interest of the captured image.
  7. 7. A storage medium, wherein, The storage medium stores a program that causes a computer to execute: acquiring a captured image obtained by capturing at least a road in a traveling direction of a moving object; generating a low resolution image that reduces the image quality of the captured image; Defining more than one partial region group, and Deriving a summary value obtained by summing up differences in feature amounts between the partial regions included in the one or more partial region groups and the peripheral partial regions, extracting a region of interest based on the summary value, The one or more partial areas are defined by cutting out a plurality of the partial areas from the low resolution image respectively, The number of pixels in the partial areas is different from each other between the plurality of partial area groups, The moving body is caused to autonomously travel in accordance with a determination result of an object at the region of interest of the captured image.

Description

Object detection device, object detection method, and storage medium Technical Field The invention relates to an object detection device, an object detection method, and a storage medium. Background Conventionally, an invention of a travel obstacle detection system has been disclosed in which an area of an object in a monitoring area such as a road obtained by imaging is divided into blocks, local feature amounts are extracted for each block, and the presence or absence of an obstacle is determined based on the extracted local feature amounts (patent document 1). Prior art literature Patent literature Patent document 1 Japanese patent application laid-open No. 201 9-124986 Disclosure of Invention Problems to be solved by the invention In the conventional technique, there are cases where the processing load is excessive or the accuracy is insufficient. The present invention has been made in view of such circumstances, and an object thereof is to provide an object detection device, an object detection method, and a storage medium capable of performing object detection while reducing a processing load. Means for solving the problems The object detection device, object detection method, and storage medium of the present invention employ the following configurations. (1) An object detection device according to an aspect of the present invention includes an acquisition unit that acquires a captured image obtained on a captured road, a low-resolution image generation unit that generates a low-resolution image that reduces the image quality of the captured image, a definition unit that defines one or more partial region groups each defined by cutting out a plurality of partial regions from the low-resolution image, and an extraction unit that derives a summary value obtained by summing up differences in feature amounts between the partial regions in the one or more partial region groups and the surrounding partial regions, and extracts a region of interest based on the summary value. (2) In the above (1), the defining unit defines a plurality of the partial region groups so that the number of pixels in the partial region is different from each other among the plurality of the partial region groups, and the extracting unit extracts the region of interest by adding the sum value for each pixel among the plurality of the partial region groups. (3) In the above-described aspect (1) or (2), the extracting unit may be configured to derive the integrated value by integrating differences in feature amounts between the partial areas included in the one or more partial area groups and other partial areas adjacent to each other in the vertical, horizontal, and diagonal directions. (4) In the above-mentioned aspect (3), the extraction unit may extract the partial areas included in the one or more partial area groups, further, the difference in the feature amounts of the partial regions adjacent to each other in the up-down direction, the difference in the feature amounts of the partial regions adjacent to each other in the left-right direction, and the difference in the feature amounts of the partial regions adjacent to each other in the oblique direction are added to the sum value. (5) In any one of the above (1) to (4), the object detection device further includes a high resolution processing unit that performs high resolution processing on the target portion in the captured image, and determines whether or not an object on the road is an object to which a moving object should be prevented from touching. (6) The object detection method according to another aspect of the present invention is performed using a computer, and includes acquiring a captured image obtained on a captured road, generating a low-resolution image that reduces the image quality of the captured image, defining one or more partial region groups, deriving a summary value obtained by summing up differences in feature amounts between the one or more partial region groups and the surrounding partial regions, and extracting a region of interest based on the summary value, wherein the one or more partial region groups are defined by cutting out a plurality of partial regions from the low-resolution image. (7) A storage medium according to still another aspect of the present invention stores a program for causing a computer to execute a process of acquiring a captured image obtained on a captured road, generating a low-resolution image in which image quality of the captured image is reduced, defining one or more partial region groups, and deriving a summary value obtained by summarizing differences in feature amounts between the one or more partial regions and the surrounding partial regions for each partial region included in the one or more partial region groups, wherein a region of interest is extracted based on the summary value, and each of the one or more partial regions is defined by cutting out a plurality of partial regions from the low-resolution image