Vehicle monitoring apparatus

• US 6,122,597 A
• Filed: 03/26/1998
• Issued: 09/19/2000
• Est. Priority Date: 04/04/1997
• Status: Expired due to Term

• Current Assignee: Subaru Corp.
• Original Assignee: Fuji Heavy Industries Limited (Subaru Corp.)
• Inventors: Saneyoshi, Keiji, Hanawa, Keiji
• Primary Examiner(s): NGUYEN, TAN QUANG
• Application Number:
  US09/048,332
• Time in Patent Office: 908 Days
• Field of Search: 701/301, 701/300, 348/51, 348/113, 348/116, 348/118, 348/140, 382/106, 382/104, 382/168, 382/170, 382/171, 382/172, 382/199, 340/435, 340/436, 340/903, 356/12
• US Class Current: 701/301
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/11 Region-based segmentation
• 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: 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 13/194 Transmission of 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

Abstract

A vehicle monitoring apparatus for obtaining a distance image including an image data and three-dimensional distance information and for monitoring surrounding conditions on the basis of the distance image, comprises: means for dividing the distance image into a plurality of blocks composed of picture elements, means for collecting the blocks having a similar distance data and for grouping the blocks into an independent group, means for calculating an area size of the independent group, means for extracting the image data as an object data if the area size of the group is larger than a predetermined value and for discarding the image data as a false data if the area size is smaller than the predetermined value, means for preparing a histogram having a lateral axis representing a deviation amount and a longitudinal axis representing a frequency corresponding to a number of the image data, and means for detecting an object and a distance to the object by deleting the frequency having a smaller number of the image data than a threshold value along the lateral axis on the histogram. Thereby, false data can be removed from the image data and a mismatching can be prevented.

Claims

1. A vehicle monitoring apparatus for obtaining a distance image including an image data and a three-dimensional distance information and for monitoring surrounding conditions on the basis of said distance image, comprising:

means for dividing said distance image into plurality of blocks composed of at least one picture element;

means for grouping said blocks having a similar distance data into an independent group;

means for calculating an area size of said independent group;

means for extracting said image data as an object data of said area size of said independent group is larger than a predetermined value and for discarding said image data as a false data if said area size of said independent group is smaller than said predetermined value;

means for preparing a histogram on the basis of the image data thus extracted by said extracting means said histogram having a lateral axis representing a deviation amount and a longitudinal axis representing a frequency corresponding to a number of said image data; and

means for detecting an object and a distance to said object by deleting said frequency having a smaller number of said image data than a threshold value along said lateral axis on said histogram.

2. The vehicle monitoring apparatus according to claim 1, wherein

when said block has a similar distance to said adjacent blocks whose group number is known, said block is grouped into the same group as said adjacent blocks and when said block-has a similar distance to said adjacent blocks whose group number is unknown, said block is grouped into a group denoted by a new number.

3. The vehicle monitoring apparatus according to claim 1, wherein

said distance image is divided into lattice-like divisions and said histogram is prepared for each of- said divisions.

4. The vehicle monitoring apparatus according to claim 1, further comprising:

a group number memory for memorizing a number of said group to which said image data belongs and a group area memory for memorizing a number of said image data to which each of said groups belong as an area size.

5. A monitoring apparatus mounted on a vehicle for watching an object in a vicinity thereof, having a pair of stereoscopic CCD cameras mounted on a front portion of said vehicle for obtaining a distance image including an image data and a three-dimensional distance information about said object and for producing an image signal, comprising:

stereoscopic image processing means responsive to said image signal for deriving a distance information about said object and for transmitting a distance signal;

means for forming groups based on said distance information;

road detecting means responsive to said distance signal for deriving a road shape by extracting a line painted on a road in front of said vehicle and for outputting a road signal;

group filtering means responsive to said distance signal and said road signal for calculating an area of each group after distinguishing whether a deviation of said distance image is within a predetermined criteria and for producing an area signal;

data extracting means responsive to said area signal for extracting area signals larger than a predetermined threshold value and for outputting a data signal; and

object distance deriving means responsive to said data signal for calculating an exact distance from said vehicle to said object in said each group by making a histogram through eliminating false data so as to be precisely detectable of an unevenness of a surface of said object.

6. The monitoring apparatus according to claim 5, wherein:

said group is registered into the same number as that of an adjacent known group when said group has a similar distance to said adjacent known group and said group is registered into a new number when said group has an approximately similar distance to an unknown group.

7. The monitoring apparatus according to claim 5, wherein:

said distance image is divided into lattice-like divisions and said histogram is prepared for each group.

8. The monitoring apparatus according to claim 5, further comprising:

a group number memory for memorizing a number of said groups to which said image data belongs; and

a group area memory for memorizing a number of said image data to which each of said groups belong as an area size.

9. A vehicle monitoring method for obtaining a distance image including an image data and a three-dimensional distance information and for monitoring surrounding conditions on the basis of said distance image, the method comprising the steps of:

dividing said distance image into a plurality of blocks composed of at least one picture element;

grouping said blocks having a similar distance data into an independent group;

calculating an area size of said independent group;

extracting said image data as an object data if said area size is larger than a predetermined value;

discarding said image data as false data if said area size is smaller than said predetermined value;

preparing a histogram on the basis of the image data thus extracted, said histogram having a lateral axis representing a deviation amount and a longitudinal axis representing a frequency corresponding to a number of said image data; and

detecting an object and a distance to said object by deleting said frequency having a smaller number of said image data than a threshold value along said lateral axis on said histogram.

10. The vehicle monitoring method according to claim 9, wherein said grouping step comprises the step of:

grouping said block into the same group as adjacent blocks when said block has a similar distance to said adjacent blocks whose group number is known, and

grouping said block into a group denoted by a new number when said block has a similar distance to said adjacent blocks whose group number is unknown.

11. The vehicle monitoring method according to claim 9, wherein said histogram preparing step comprises the steps of:

dividing said distance image into lattice-like divisions, and

preparing said histogram for each of said divisions.

12. The vehicle monitoring method according to claim 9, further comprising the steps of:

memorizing a number of said groups to which said image data belongs; and

memorizing a number of said image data to which each of said groups belongs as an area size.

13. A monitoring method of a vehicle for watching an object in a vicinity thereof, having a pair of stereoscopic CCD cameras mounted on a front portion of said vehicle for obtaining a distance image including an image data and a three-dimensional distance information about said object, comprising the steps of:

deriving a distance information about said object from said distance images;

determining a plurality of groups based on said distance information;

calculating an area of each of said groups;

imaging a road shape by extracting a line painted on a road in front of said vehicle;

calculating a three dimensional coordinate value of said object;

determining values which exceed a predetermined threshold value;

deciding an area of corresponding group by referring to a memory;

determining larger values of said area than a predetermined value;

rewriting a histogram data of said larger values by comparing a frequency thereof; and

detecting a distance of said object by counting a number of deviations from said frequency so as to be precisely detectable of an unevenness of a surface of said object.