Three-Dimensional Object Detecting Device

• US 20090226035A1
• Filed: 02/07/2007
• Published: 09/10/2009
• Est. Priority Date: 02/09/2006
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company), Kumamoto University
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company), Kumamoto University
• Inventors: Ueda, Yasushi, Kourogi, Naoki, Furuki, Satoko, Iihoshi, Akira, Uchimura, Keiichi, Hu, Zhencheng
• Granted Patent: US 8,396,283 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30268 Vehicle interior
• CPC Class Codes: G06T 7/521 from laser ranging, e.g. using interferometry; from the projection of structured light
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching
• CPC Class Codes: G06V 40/166 using acquisition arrangements

Abstract

A three-dimensional-object can be effectively detected. A pair of image capture devices capture a three-dimensional-object and calculate disparity component data of subdivided-image regions, respectively. On a basis of the disparity component data, gray scale values indicative of distances from the image capture device are calculated and a gray scale image in which each region has its corresponding gray scale value is generated. A model of the three-dimensional-object is defined and correlation values is calculated to show the degree of a similarity between the model and the image subdivided regions in the gray scale image. The model is a two-dimensional image with a shaping characteristic when the three-dimensional object is viewed from positions of the image capture devices while each subdivided region of the two-dimensional image has a gray scale value indicative of a distance from the image capture device at a portion corresponding to the three-dimensional object. The correlation values are calculated on a basis of gray scale values of the model and those of the image region in the gray scale image. The model and an image region with the highest correlation value are detected in the gray scale image, so that a three-dimensional image is detected.

Claims

1. An object detecting device comprising:

a pair of imaging means for taking an image of a three-dimensional object;

disparity data computing means for computing disparity data for each region based on the images obtained by the pair of imaging means, each region being obtained by dividing the image;

gray-scale image generating means for computing a gray-scale value indicating a distance to the imaging means based on the disparity data computed for each region and generating a gray-scale image having the gray-scale value corresponding to each region;

model storage means in which a model modeling the three-dimensional object is stored;

correlation value computing means for computing a correlation value indicating a similarity between the model and an image region in the gray-scale image, the model being a two-dimensional image having a geometric feature when the three-dimensional object is viewed from a direction in which the imaging means are located, each region obtained by dividing the two-dimensional image having a gray-scale value indicating a distance to the imaging means, of a corresponding portion of the three-dimensional object, the correlation value being computed based on gray-scale values of the model and gray-scale values of the image region in the gray-scale image; and

object detecting means for detecting the three-dimensional object by detecting an image region in the gray-scale image, having a highest correlation value with the model.

3. The object detecting device according to claim 1, wherein a plurality of models are stored in the model storage means according to a size and an attitude of the three-dimensional object,

the correlation value computing means computes the correlation value for each of the plurality of models, and

the object detecting means determines a size and an attitude of the three-dimensional object based on the model correlated with an image region having the highest correlation value, in the plurality of models.

4. The object detecting device according to claim 1, wherein the three-dimensional object is a human head, and

the model is a two-dimensional image having an elliptic shape.

5. The object detecting device according to claim 4, wherein the detected human head is a head of a human riding on a vehicle.

6. The object detecting device according to claim 1, wherein the object detecting device is one which detects an occupant in a vehicle,

the object detecting device comprises occupant region detecting means for detecting an occupant region, where the occupant exists, in the image obtained by the imaging means, based on the disparity data when the occupant sits on a seat and the disparity data at a vacant seat, and

the gray-scale image generating means generates the gray-scale image based on the occupant region.

8. The object detecting device according to claim 1, comprising pattern light illuminating means for illuminating the object with pattern light having a predetermined pattern.

2. An object detecting device comprising:

distance measuring means for measuring a distance to each region, each region being obtained by dividing a predetermined range including a three-dimensional object;

gray-scale image generating means for computing a gray-scale value indicating a distance measured by the distance measuring means and generating a gray-scale image having the gray-scale value corresponding to each region;

model storage means in which a model is stored, the model being formed by modeling the three-dimensional object;

correlation value computing means for computing a correlation value indicating a similarity between the model and an image region in the gray-scale image, the model being a two-dimensional image having a geometric feature when the three-dimensional object is viewed from a direction in which the distance measuring means is located, each region obtained by dividing the two-dimensional image having a gray-scale value indicating a distance to the distance measuring means, of a corresponding portion of the three-dimensional object, the correlation value being computed based on gray-scale values of the model and gray-scale values of the image region in the gray-scale image; and

object detecting means for detecting the three-dimensional object by detecting an image region in the gray-scale image, having a highest correlation value with the model.

7. The object detecting device according to claim 2, wherein the object detecting device is one which detects an occupant in a vehicle,

the object detecting device comprises occupant region detecting means for detecting an occupant region, where the occupant exists, in a predetermined range measured by the distance measuring means, based on the distance measured by the distance measuring means when the occupant sits on a seat and the distance measured by the distance measuring means at a vacant seat, and

the gray-scale image generating means generates the gray-scale image based on the occupant region.

9. The object detecting device according to claim 2, wherein a plurality of models are stored in the model storage means according to a size and an attitude of the three-dimensional object,

the correlation value computing means computes the correlation value for each of the plurality of models, and

the object detecting means determines a size and an attitude of the three-dimensional object based on the model correlated with an image region having the highest correlation value, in the plurality of models.

10. The object detecting device according to claim 2, wherein the three-dimensional object is a human head, and

the model is a two-dimensional image having an elliptic shape.

11. The object detecting device according to claim 10, wherein the detected human head is a head of a human riding on a vehicle.

12. An object detecting device comprising:

a pair of imaging capturing devices which capture an image of a three-dimensional object;

a disparity data computing device which computes disparity data for each region based on the images obtained by the pair of imaging capturing devices, each region being obtained by dividing the image;

a gray-scale image generating device which calculates a gray-scale value indicating a distance to the imaging capturing devices based on the disparity data computed for each region and generates a gray-scale image having the gray-scale value corresponding to each region;

a model storage device in which a model modeling the three-dimensional object is stored;

a correlation value computing device which computes a correlation value indicating a similarity between the model and an image region in the gray-scale image, the model being a two-dimensional image having a geometric feature when the three-dimensional object is viewed from a direction in which the imaging capturing devices are located, each region obtained by dividing the two-dimensional image having a gray-scale value indicating a distance to the imaging capturing devices, of a corresponding portion of the three-dimensional object, the correlation value being computed based on gray-scale values of the model and gray-scale values of the image region in the gray-scale image; and

an object detector which detects the three-dimensional object by detecting an image region in the gray-scale image, having a highest correlation value with the model.

13. The object detecting device according to claim 12, wherein a plurality of models are stored in the model storage device according to a size and an attitude of the three-dimensional object,

the correlation value computing device computes the correlation value for each of the plurality of models, and

the object detector determines a size and an attitude of the three-dimensional object based on the model correlated with an image region having the highest correlation value, in the plurality of models.

14. The object detecting device according to claim 12, wherein the three-dimensional object is a human head, and

the model is a two-dimensional image having an elliptic shape.

15. The object detecting device according to claim 14, wherein the detected human head is a head of a human riding on a vehicle.

16. The object detecting device according to claim 12, wherein the object detecting device is one which detects an occupant in a vehicle,

the object detecting device comprises occupant region detecting device which detects an occupant region, where the occupant exists, in the image obtained by the imaging devices, based on the disparity data when the occupant sits on a seat and the disparity data at a vacant seat, and

the gray-scale image generating device generates the gray-scale image based on the occupant region.