Method and device for recognizing situation based on image using template

• US 9,323,986 B2
• Filed: 06/24/2014
• Issued: 04/26/2016
• Est. Priority Date: 12/27/2011
• Status: Active Grant

• Current Assignee: Korea Electronics Technology Institute (Government of South Korea)
• Original Assignee: Korea Electronics Technology Institute (Government of South Korea)
• Inventors: Kim, Seunghun, Jung, Ilkyun
• Primary Examiner(s): GORADIA, SHEFALI DINESH
• Application Number:
  US14/313,662
• Publication Number:
  US 20140307922A1
• Time in Patent Office: 672 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

The present invention relates to a method and device for recognizing a situation based on an image using a template. The present invention provides the device for recognizing a situation based on an image. The device includes a camera unit capturing an image which is divided into a plurality of regions and having a template for each of the regions, the template defining characteristics of each of the regions, and a control unit detecting an object in the image and determining the situation surrounding the object according to the template mapped to the region to which the detected object belongs. In addition, the present invention provides the method of operating the device for recognizing a situation.

Claims

1. An image-based situation recognition device, comprising:

a camera that captures an image,

wherein the entire captured image is divided into a plurality of regions, and

wherein each of the divided regions is mapped to a template defining a characteristic of the each of the divided regions; and

a control unit that

detects an object in the captured image, and

determines a situation of the object according to the template mapped to the region including the detected object;

wherein the template defines a behavioral characteristic of the object detected in the region,

wherein the control unit compares a behavior of the object detected in the region with the behavioral characteristic of the object defined in the template to determine the situation of the object,

wherein, among the divided regions, regions having the same characteristic are grouped, and then mapped to the same template, and

wherein the characteristic includes at least one selected from the group consisting of a sidewalk, a vacant lot, a drivable way and a drive direction.

2. The image-based situation recognition device of claim 1, wherein the template defines a type of the object detected in the region.

3. The image-based situation recognition device of claim 2, wherein the control unit detects the object in the region with reference to the type of the object defined in the template.

4. An image-based situation recognition method of an image-based situation recognition device, the method comprising:

capturing, by a camera of the image-based situation recognition device, an image,

wherein the entire captured image is divided into a plurality of regions, and

wherein each of the divided regions is mapped to a template defining a characteristic of the each of the divided regions;

detecting, by a processor of the image-based situation recognition device, an object in the captured image; and

determining, by the processor of the image-based situation recognition device, a situation of the object according to the template mapped to the region including the detected object

wherein the template defines a behavioral characteristic of the object detected in the region,

wherein the determining comprises comparing a behavior of the object detected in the region with the behavioral characteristic of the object defined in the template to determine the situation of the object,

wherein, among the divided regions, regions having the same characteristic are grouped, and then mapped to the same template, and

wherein the characteristic includes at least one selected from the group consisting of a sidewalk, a vacant lot, a drivable way and a drive direction.

5. The image-based situation recognition method of claim 4,

wherein the template defines a type of the object detected in the region, and

wherein the detecting comprises detecting the object in the region with reference to the type of the object defined in the template.