Object identifier

• US 9,292,751 B2
• Filed: 06/20/2013
• Issued: 03/22/2016
• Est. Priority Date: 09/14/2012
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Miyagawa, Keisuke
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US14/428,035
• Publication Number:
  US 20150242694A1
• Time in Patent Office: 1,006 Days
• Field of Search: 382/100, 382103-107, 382/162, 382/166, 382/168, 382/173, 382/181, 382/194, 382/199, 382/209, 382/219, 382/222, 382/232, 382/243, 382/254, 382/274, 382/276, 382286-291, 382/305, 382/312, 382/317, 340/435, 250/208.1, 701/36, 348/222.1, 348/114
• US Class Current: 1/1
• CPC Class Codes: B60R 1/00 Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
• CPC Class Codes: B60R 1/24 in front of the vehicle
• CPC Class Codes: B60R 2300/307 virtually distinguishing relevant parts of a scene from the background of the scene
• CPC Class Codes: B60R 2300/8033 for pedestrian protection
• CPC Class Codes: G06V 10/446 using Haar-like filters, e.g. using integral image techniques
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

An object identifier is provided with a data-forming unit and a data-retrieving unit. The data-forming unit forms an integral image having an image region of the same size as an original image and an image to be integrated. The data-retrieving unit obtains compressed data derived by extracting, from a plurality of pixels constituting the integral image, at least every other pixel in at least one direction.

Claims

1. An object identifying apparatus comprising:

an image capturing unit that is mounted on a vehicle for acquiring an original image by capturing the original image while the vehicle is traveling;

a data generator for successively integrating pixel values of integration object images representing feature quantities at respective pixels that make up the original image, from a starting point at either one of angular positions of the integration object images, thereby generating integral images, each including an image area having a size in common with the original image and the integration object images;

a data acquirer for acquiring compressed data by extracting at least every other pixel along at least one direction from a plurality of pixels that make up the integral images generated by the data generator;

an identification object region determiner for determining an identification object region from within an original image area represented by the original image; and

an object identifier for calculating a total of the pixel values of the integration object images within the identification object region that was determined by the identification object region determiner, as an image feature quantity using the compressed data acquired by the data acquirer, and on the basis of the image feature quantity, identifying whether or not an object exists within the identification object region in the original image,

wherein the image feature quantity is represented by a histogram.

2. The object identifying apparatus according to claim 1, wherein the identification object region determiner determines the identification object region, which includes at least four pixels at vertices thereof, selected respectively from pixel groups extracted as the compressed data.

3. The object identifying apparatus according to claim 1, wherein the data acquirer acquires the compressed data by reducing the amount of data of each of the pixels of the integral images by at least one bit.

4. The object identifying apparatus according to claim 1, wherein if the identification object region determiner determines the identification object region, and the object identifier identifies the object (66) while a position of the identification object region is changed sequentially along a scanning direction at a scanning interval, thereby identifying whether or not the object (66) exists within the original image, the identification object region determiner determines the identification object region at a different scanning interval depending on a position in the original image area.

5. The object identifying apparatus according to claim 4, further comprising:

an image capturing unit mounted on a vehicle for acquiring an image in a vicinity of the vehicle by capturing the image while the vehicle is traveling,

wherein the scanning interval in a lower position in the original image area, which is represented by the captured image acquired as the original image by the image capturing unit, is greater than the scanning interval in an upper position in the original image area.

6. The object identifying apparatus according to claim 1, wherein

the integration object images are represented by binary voting data, which-indicate whether each pixel of the original image belongs to any one of ranges of the histogram.

7. An object identifying apparatus comprising:

an image capturing unit that is mounted on a vehicle for acquiring an original image by capturing the original image while the vehicle is traveling;

a data generator for successively integrating pixel values of integration object images representing feature quantities at respective pixels that make up the original image, from a starting point at either one of angular positions of the integration object images, thereby generating integral images, each including an image area having a size in common with the original image and the integration object images;

a data acquirer for acquiring compressed data by extracting at least every other pixel along at least one direction from a plurality of pixels that make up the integral images generated by the data generator;

an identification object region determiner for determining an identification object region from within an original image area represented by the original image; and

an object identifier for calculating a total of the pixel values of the integration object images within the identification object region that was determined by the identification object region determiner, as an image feature quantity using the compressed data acquired by the data acquirer, and on the basis of the image feature quantity, identifying whether or not an object exists within the identification object region in the original image,

wherein the integration object images are represented by binary voting data.