Vehicle surroundings monitoring apparatus

• US 6,888,953 B2
• Filed: 12/20/2001
• Issued: 05/03/2005
• Est. Priority Date: 01/30/1998
• Status: Expired due to Term

• Current Assignee: Subaru Corp.
• Original Assignee: Fuji Jukogyo KK (Subaru Corp.)
• Inventors: Hanawa, Keiji
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): Choobin, Barry
• Application Number:
  US10/028,882
• Publication Number:
  US 20030099377A1
• Time in Patent Office: 1,230 Days
• Field of Search: 382/104, 382/154, 382/106, 382/103, 382/288, 382/295, 382/291, 382/293, 340/907, 340/905, 340/933, 348/113, 348/116, 701/23, 701/301, 356/3.14
• US Class Current: 382/104
• CPC Class Codes: G01S 11/12 using electromagnetic waves other than radio waves
• CPC Class Codes: G01S 13/726 Multiple target tracking
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 2013/932 using own vehicle data, e.g. ground speed, steering wheel direction
• CPC Class Codes: G06T 17/10 Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/74 involving reference images or patches
• 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 20/64 Three-dimensional objects
• CPC Class Codes: H04N 13/239 using two 2D image sensors having a relative position equal to or related to the interocular distance H04N13/243 takes precedence
• CPC Class Codes: H04N 2013/0081 Depth or disparity estimation from stereoscopic image signals

Abstract

Distance image outputted from an image processor is read by a recognition/judgment computer, in which the distance image is divided into strips having a specified interval and a histogram is prepared for each strip. Based on the histogram, the position of solid objects and the distance thereto are obtained and these positional data of the solid objects are classified into groups of solid object and groups of side wall. Further, the position of a wall surface forming a boundary of a road is detected from the data of the groups of side wall. On the other hand, assuming a wall surface model composed of a series of nodes, respective nodes are determined and corrected by the data of side wall. Thus obtained nodes form a successive wall surface along a curved road.

Claims

1. A vehicle surroundings monitoring apparatus having a stereoscopic image detecting unit for detecting a stereoscopic image around a self vehicle, an image processor for processing said image into a distance image and a recognition computer for recognizing objects based on said distance image, comprising:

classifying means for classifying positional data representing a side wall of a particular one of said objects arranged along a boundary of a road on which said self vehicle is running and positional data of other ones of said objects; and

wall surface detecting means for detecting an outline of said side wall by performing a pattern matching of a side wall surface pattern to said positional data of said side wall, said side wall surface pattern being suitable for said particular object.

2. A vehicle surroundings monitoring apparatus having a stereoscopic image detecting unit for detecting a stereoscopic image around a self vehicle, an image processor for processing said image into a distance image and a recognition computer for recognizing objects based on said distance image, comprising:

grouping means for grouping positional data representing a side wall of a particular object arranged along a boundary of a road on which said self vehicle is running; and

wall surface detecting means for detecting an outline of said side wall by performing a pattern matching of a side wall surface pattern to said positional data of said side wall, said side wall surface pattern being suitable for said particular object, wherein said wall surface detecting means is adopted to perform the pattern matching successively along a wall surface model represented by a combination of a plurality of nodes arranged at a predetermined interval ahead of said self vehicle.

3. The apparatus according to claim 2, wherein said wall surface detecting means is adopted to apply said side wall surface pattern to said positional data of said side wall within a searching area provided around each node of said wall surface model.

4. The apparatus according to claim 3, wherein said side wall surface pattern is represented by a weight coefficient being variable depending on a distance from a central point of said pattern.

5. The apparatus according to claim 4, wherein said wall surface detecting means is adopted to recognize a position of the central point of said side wall surface pattern as a node of said wall surface model when the degree of coincidence of the pattern matching becomes maximum while said side wall surface pattern is shifted towards a lateral direction.

6. The apparatus according to claim 5, further comprising correcting means for correcting coordinates of each node of said wall surface model set by said wall surface detecting means in the direction of bringing said each node close to a straight line connecting two adjacent nodes.

7. A vehicle surroundings monitoring apparatus having a stereoscopic image detecting unit for detecting a stereoscopic image around a self vehicle, an image processor for processing said image into a distance image and a recognition computer for recognizing objects based on said distance image, comprising:

classifying means for classifying positional data representing a sidewall of a particular one of said objects arranged along a boundary of a road on which said self vehicle is running and positional data of other ones of said objects; and

wall surface detecting means for detecting a curved outline of said aide wall by performing a pattern matching of a side wall surface pattern to said positional data of said side wall, said side wall surface pattern being suitable for said particular object.