Ranging device utilizing image processing

• US 7,729,516 B2
• Filed: 08/16/2007
• Issued: 06/01/2010
• Est. Priority Date: 09/25/2001
• Status: Expired due to Fees

• Current Assignee: Fujitsu Ten Limited (DENSO Corporation)
• Original Assignee: Fujitsu Ten Limited (DENSO Corporation)
• Inventors: Oka, Kenji, Oota, Akihiro, Shima, Nobukazu
• Primary Examiner(s): Bella; Matthew C
• Assistant Examiner(s): Mackowey; Anthony
• Application Number:
  US11/839,701
• Publication Number:
  US 20070291992A1
• Time in Patent Office: 1,020 Days
• Field of Search: 382/103, 382/104, 382/106, 382/154, 382/199, 382/266, 382/105, 382/204, 382/259, 382/294, 382/298, 348/47, 348/115, 348/116, 348/139, 348/148
• US Class Current: 382/106
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• 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 2201/08 Detecting or categorising vehicles

Abstract

An image size changing section obtains a size changed image by changing the size of one of two original images captured by a pair of cameras. If an edge of an object has many oblique components, the edge is difficult to detect as a vertical edge but, when the image is horizontally reduced, an oblique edge becomes close to a vertical edge. For this reason, feature end points are extracted with reliability by a feature extracting section and, thereby, an object is recognized and the distance to the object is determined reliably.

Claims

1. A ranging device utilizing image processing, comprising:

an image size changing section for obtaining a size-reduced image by reducing the size in only a horizontal direction of one of two original images captured by a pair of cameras facing a direction of motion;

a feature extracting section for extracting feature end points which are continuously detected in a vertical direction from said size-reduced image;

a pattern extracting section for extracting a pattern of a prescribed size including said feature end points, and the coordinate of said pattern, from said one of two original images; and

a ranging section for searching for the coordinates in the other one of said two images, on the axis on which the coordinate of said pattern exists, to detect the coordinate of a position most correlating with said pattern, and recognizing an object in front of said ranging device to determine the distance to said object based on the difference between the coordinates of the positions in said two original images where said pattern is extracted.