Obstacle detecting apparatus and method

• US 20030227378A1
• Filed: 03/14/2003
• Published: 12/11/2003
• Est. Priority Date: 03/29/2002
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Nakai, Hiroaki, Hattori, Hiroshi, Onoguchi, Kazunori, Takeda, Nobuyuki
• Granted Patent: US 7,091,837 B2
• Time in Patent Office: Days
• US Class Current: 340/435
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06T 7/77 using statistical methods
• 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 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

Abstract

An obstacle detecting apparatus, comprising: an image input unit for receiving images inputted respectively from a plurality of image pick-up devices and accumulating the input images; a feature calculating unit for calculating predetermined, specific feature quantities in the respective accumulated images; a feature comparing unit for comparing the feature quantities in the respective accumulated images; and a result judging unit for judging the presence or absence of an obstacle on the basis of the comparison result obtained in the feature comparing unit. The obstacle detecting apparatus can thus detect an obstacle present on the road, such as a vehicle running ahead, a parked vehicle, and a pedestrian, by distinguishing the obstacle from a mere object causing no obstruction to driving of the vehicle, such as the texture like the white line or signs on the road surface, and the guardrail along the roadside.

Claims

1. An obstacle detecting apparatus for detecting whether there is an obstacle within a common range shot through the use of a plurality of image pick-up devices, said obstacle detecting apparatus comprising:

image input means for receiving a plurality of images inputted respectively from said plurality of image pick-up devices;

feature calculating means for calculating a predetermined, specific feature quantity in each of said plurality of input images;

feature comparing means for finding a difference in said calculated feature quantity between said plurality of input images; and

result judging means for judging whether there is an obstacle within said range based on a result of comparison of said found difference in said calculated feature quantity with a threshold.

4. The obstacle detecting apparatus according to any of claims 1 through 3, wherein said feature calculating means calculates a luminance gradient at each pixel in each image and uses the luminance gradient as said feature quantity.

2. An obstacle detecting apparatus for detecting whether there is an obstacle within a range shot through the use of at least one image pick-up device, said obstacle detecting apparatus comprising:

image input means for receiving an image inputted from said image pick-up device;

feature calculating means for calculating a predetermined, specific feature quantity in said input image;

indicator calculating means for calculating an indicator indicating one of presence and absence of an obstacle based on a distribution of said calculated feature quantity; and

result judging means for judging one of the presence and absence of an obstacle based on said calculated indicator.

3. An obstacle detecting apparatus for detecting whether there is an obstacle within a common range shot through the use of a plurality of image pick-up devices, said obstacle detecting apparatus comprising:

image input means for receiving a plurality of images inputted respectively from said plurality of image pick-up devices;

feature calculating means for calculating a predetermined, specific feature quantity in each of said plurality of input images;

feature comparing means for finding a difference in said calculated feature quantity between said plurality of input images, and for synthesizing an image by combining said plurality of input images based on a result of comparison of said difference in said calculated feature quantity with a threshold;

indicator calculating means for calculating an indicator indicating one of presence and absence of an obstacle based on a distribution of a feature quantity in said synthesized image; and

result judging means for judging one of the presence and absence of an obstacle based on said calculated indicator.

5. A method of detecting an obstacle for detecting whether there is an obstacle within a common range shot through the use of a plurality of image pick-up devices, said method comprising:

an image inputting step of receiving a plurality of images inputted respectively from said plurality of image pick-up devices;

a feature calculating step of calculating a predetermined, specific feature quantity in each of said plurality of input images;

a feature comparing step of finding a difference in said calculated feature quantity between said plurality of input images; and

a result judging step of judging whether there is an obstacle within said range based on a result of comparison of said found difference in said calculated feature quantity with a threshold.

6. A method of detecting an obstacle for detecting whether there is an obstacle within a range shot through the use of at least one image pick-up device, said method comprising:

an image inputting step of receiving an image inputted from said image pick-up device;

a feature calculating step of calculating a predetermined, specific feature quantity in said input image;

an indicator calculating step of calculating an indicator indicating one of presence and absence of an obstacle based on a distribution of said calculated feature quantity; and

a result judging step of judging one of the presence and absence of an obstacle based on said calculated indicator.

7. A method of detecting an obstacle for detecting whether there is an obstacle within a common range shot through the use of a plurality of image pick-up devices, said method comprising:

an image inputting step of receiving a plurality of images inputted respectively from said plurality of image pick-up devices;

a feature calculating step of calculating a predetermined, specific feature quantity in each of said plurality of input images;

a feature comparing step of finding a difference in said calculated feature quantity between said plurality of input images, and for synthesizing an image by combining said plurality of input images based on a result of comparison of said found difference in said calculated feature quantity with a threshold;

an indicator calculating step of calculating an indicator indicating one of presence and absence of an obstacle based on a distribution of a feature quantity in said synthesized image; and

a result judging step of judging one of the presence and absence of an obstacle based on said calculated indicator.

8. A computer-executable program for a method of detecting an obstacle for detecting whether there is an obstacle within a common range shot through the use of a plurality of image pick-up devices, said program causing a computer to perform:

an image inputting function of receiving a plurality of images inputted respectively from said plurality of image pick-up devices;

a feature calculating function of calculating a predetermined, specific feature quantity in each of said plurality of input images;

a feature comparing function of finding a difference in said calculated feature quantity between said plurality of input images; and

a result judging function of judging whether there is an obstacle within said range based on a result of comparison of said found difference in said calculated feature quantity with a threshold.

9. A computer-executable program for a method of detecting an obstacle for detecting whether there is an obstacle within a range shot through the use of at least one image pick-up device, said program causing a computer to perform:

an image inputting function of receiving an image inputted from said image pick-up device;

a feature calculating function of calculating a predetermined, specific feature quantity in said input image;

an indicator calculating function of calculating an indicator indicating one of presence and absence of an obstacle based on a distribution of said calculated feature quantity; and

a result judging function of judging one of the presence and absence of an obstacle based on said calculated indicator.

10. A computer-executable program for a method of detecting an obstacle for detecting whether there is an obstacle within a common range shot through the use of a plurality of image pick-up devices, said program causing a computer to perform:

an image inputting function of receiving a plurality of images inputted respectively from said plurality of image pick-up devices;

a feature calculating function of calculating a predetermined, specific feature quantity in each of said plurality of input images;

a feature comparing function of finding a difference in said calculated feature quantity between said plurality of input images, and for synthesizing an image by combining said plurality of input images based on a result of comparison of said found difference in said calculated feature quantity with a threshold;

an indicator calculating function of calculating an indicator indicating one of presence and absence of an obstacle based on a distribution of a feature quantity in said synthesized image; and

a result judging function of judging one of the presence and absence of an obstacle based on said calculated indicator.

11. An obstacle detecting apparatus for detecting whether there is an obstacle within a common range shot through the use of a plurality of image pick-up devices, said obstacle detecting apparatus performing of:

receiving a plurality of images inputted respectively from said plurality of image pick-up devices;

calculating a predetermined, specific feature quantity in each of said plurality of input images;

finding a difference in said calculated feature quantity between said plurality of input images; and

judging whether there is an obstacle within said range based on a result of comparison of said found difference in said calculated feature quantity with a threshold.

12. An obstacle detecting apparatus for detecting whether there is an obstacle within a range shot through the use of at least one image pick-up device, said obstacle detecting apparatus performing of:

receiving an image inputted from said image pick-up device;

calculating a predetermined, specific feature quantity in said input image;

calculating an indicator indicating one of presence and absence of an obstacle based on a distribution of said calculated feature quantity; and

judging one of the presence and absence of an obstacle based on said calculated indicator.

13. An obstacle detecting apparatus for detecting whether there is an obstacle within a common range shot through the use of a plurality of image pick-up devices, said obstacle detecting apparatus performing of:

receiving a plurality of images inputted respectively from said plurality of image pick-up devices;

calculating a predetermined, specific feature quantity in each of said plurality of input images;

finding a difference in said calculated feature quantity between said plurality of input images, and for synthesizing an image by combining said plurality of input images based on a result of comparison of said difference in said calculated feature quantity with a threshold;

calculating an indicator indicating one of presence and absence of an obstacle based on a distribution of a feature quantity in said synthesized image; and

judging one of the presence and absence of an obstacle based on said calculated indicator.

14. An obstacle detecting apparatus for detecting an obstacle within a common viewing range through the use of a plurality of image pick-up devices, comprising:

input unit configured to receive a plurality of images respectively from said plurality of image pick-up devices;

first calculating unit configured to calculate a predetermined feature data in each of said plurality of input images;

second calculating unit configured to calculate differences between a pair of the feature data among said plurality of input images; and

comparing unit configured to compare the differences in said calculated feature data with at least one threshold value so as to determine if there is an obstacle in the common viewing range.

15. A method of detecting an obstacle for detecting an obstacle within a common viewing range through the use of a plurality of image pick-up devices, said method comprising:

receiving a plurality of images respectively from said plurality of image pick-up devices;

calculating a predetermined feature data in each of said plurality of input images;

calculating differences between a pair of the feature data among said plurality of input images; and

comparing the differences in said calculated feature data with at least one threshold value so as to determine if there is an obstacle in the common viewing range.