System for monitoring condition outside vehicle using imaged picture by a plurality of television cameras

• US 5,410,346 A
• Filed: 03/15/1993
• Issued: 04/25/1995
• Est. Priority Date: 03/23/1992
• Status: Expired due to Term

• Current Assignee: Fuji Heavy Industries Limited (Subaru Corp.)
• Original Assignee: Fuji Heavy Industries Limited (Subaru Corp.)
• Inventors: Hanawa, Keiji, Saneyoshi, Keiji
• Primary Examiner(s): Chin, Tommy P.
• Assistant Examiner(s): LIN, BRYAN T
• Application Number:
  US08/031,728
• Time in Patent Office: 771 Days
• Field of Search: 348/118, 348/116, 348/113, 348/148, 348/143, 364/424.01, 364/424.02
• US Class Current: 348/116
• 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: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G01S 11/12 using electromagnetic waves other than radio waves
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles
• CPC Class Codes: H04N 13/10 Processing, recording or transmission of stereoscopic or multi-view image signals
• CPC Class Codes: H04N 13/167 Synchronising or controlling image signals
• CPC Class Codes: H04N 13/189 Recording image signals; Reproducing recorded image signals
• 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
• CPC Class Codes: H04N 2013/0092 Image segmentation from stereoscopic image signals
• CPC Class Codes: H04N 2013/0096 Synchronisation or controlling aspects

Abstract

A distance between a running vehicle and an object is determined over an imaged picture with high reliability. Three-dimensional objects or a road shape along with accurate position or dimension are also detected. An object within a set region outside a vehicle is imaged by a stereoscopic optical system to input the imaged picture of the object into a stereoscopic picture processing apparatus. The stereoscopic picture processing apparatus processes the picture imaged by the stereoscopic optical system to calculate a distance distribution over the entire picture. A road/three-dimensional object detecting apparatus calculates three-dimensional positions of respective portions of objects corresponding to information of the distance distribution to detect the shape of the road and a plurality of three-dimensional objects by using information of these three-dimensional positions securely and with high reliability.

Claims

1. A system for monitoring conditions outside a vehicle having at least a pair of cameras mounted on said vehicle for taking pictures of one or more objects outside of said vehicle, comprising:

a picture imaging system for imaging said one or more objects in pictures taken by said cameras in a predetermined region outside said vehicle and for generating a picture signal representative of said pictures;

picture processing means responsive to said picture signal for calculating a distance distribution over an entire picture;

first three dimensional window setting means for setting a first three dimensional window representative of a three dimensional space area including a white line of a road imaged by said picture imaging system, based upon an estimated position of the white line on the road;

linear element detecting means responsive to said distance distribution for detecting three-dimensional linear elements within said first three dimensional window and for producing a road model based upon one or more detected linear elements;

road shape judgment means responsive to said road model for judging a reasonableness of said three-dimensional linear elements and for modifying said road model based upon said judging;

road shape estimation means for estimating a position of the white line on the road on a basis of said distance distribution;

object detection means responsive to said distance distribution and said road model for detecting a presence of an object within said entire picture by dividing said picture into a plurality of picture information portions;

second three-dimensional window setting means responsive to a detected object for setting a second three-dimensional window representative of a second three-dimensional space area including an object imaged by said picture imaging system;

object contour image extraction means responsive to said distance distribution and said second three dimensional window for extracting only data within said second three-dimensional window from said plurality of picture information portions in order to derive a contour and a position of a detected object so as to precisely predict a sudden movement of a detected object.

2. The system for monitoring condition outside a vehicle according to claim 1, further comprising:

collision judgment means connected to said object contour image extraction means for judging a possibility of collision between said vehicle and a detected object by referring to a relationship between the detected object and said vehicle from said plurality of picture information portions in view of an obtained running route of said vehicle.

3. The system for monitoring condition outside a vehicle according to claim 2, wherein

said linear element detecting means extracts only the data within said first three-dimensional window to multiply the data by a weighting coefficient in order to derive a three-dimensional linear expression with respect to at least one of said three-dimensional linear element by a method of least squares.

4. The system for monitoring condition outside a vehicle according to claim 2, wherein

said linear element detecting means extracts only the data within said first three-dimensional window to multiply the data by a weighting coefficient in order to derive a three-dimensional linear expression with respect to at least one of said three-dimensional linear element by a Hough transformation.

5. The system for monitoring condition outside a vehicle according to claim 2, further comprising

object discrimination means for discriminating a kind of object from a dimension and the position of the contour image of a detected object.

6. The system for monitoring condition outside a vehicle according to claim 1, wherein

said linear element detecting means extracts only the data within said first three-dimensional window to multiply the data by a weighting coefficient in order to derive a three-dimensional linear expression with respect to at least one of said three-dimensional linear elements by a method of least squares.

7. The system for monitoring condition outside a vehicle according to claim 1, wherein

said linear element detecting means extracts only the data within said first three-dimensional window to multiply the data by a weighting coefficient in order to derive a three-dimensional linear expression with respect to at least one of said three-dimensional linear element by a Hough transformation.

8. The system for monitoring a condition outside a vehicle according to claim 1, further comprising

object discrimination means for discriminating a kind of object from a dimension and the position of the contour image of a detected object.