Image capturing apparatus, image processing method, and recording medium
An image capturing apparatus: calculates, for each of pairs of images, based on the pairs of images and camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels respectively included in the pair of images, and information specifying a position of each of the pair of pixels; performs, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle, with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and outputs position information of the measurement point to which a weighted addition value is applied.
1. An image capturing apparatus comprising:
at least three cameras each of which captures an image;
a memory storing a camera parameter of each camera; and
a processing circuit, wherein
the processing circuit:
acquires the images and the camera parameters;
extracts pairs of images from the images;
calculates, for each of the pairs of images, based on the pairs of images and the camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
performs, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
outputs position information of the measurement point to which a weighted addition value is applied, and
wherein the processing circuit determines a weight applied to the information specifying the three-dimensional position of the measurement point in each of the pair of images, so that variance of the weighted addition value is minimized.
2. An image capturing apparatus comprising:
at least three cameras each of which captures an image;
a memory storing a camera parameter of each camera; and
a processing circuit, wherein
the processing circuit:
acquires the images and the camera parameters;
extracts pairs of images from the images;
calculates, for each of the pairs of images, based on the pairs of images and the camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
performs, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
outputs position information of the measurement point to which a weighted addition value is applied, and
wherein in the weighted addition, the processing circuit uses a value obtained by normalizing the effective baseline length to the power of two by the sum of effective baseline lengths to the power of two.
3. An image capturing apparatus comprising:
at least three cameras each of which captures an image;
a memory storing a camera parameter of each camera; and
a processing circuit, wherein
the processing circuit:
acquires the images and the camera parameters;
extracts pairs of images from the images;
calculates, for each of the pairs of images, based on the pairs of images and the camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
performs, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
outputs position information of the measurement point to which a weighted addition value is applied, and
wherein, in the weighted addition, the processing circuit uses a value obtained by normalizing the viewing angle to the power of two by the sum of viewing angles to the power of two.
4. An image processing method comprising:
(a1) acquiring an image captured by each of at least three cameras;
(a2) acquiring a camera parameter of each camera;
(a3) extracting pairs of images from the images;
(a4) calculating, for each of the pairs of images, based on the pairs of images and camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
(a5) performing, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
(a6) outputting position information of the measurement point to which a weighted addition value is applied,
wherein at least one of the processes (a1) to (a6) is executed by a processor, and
wherein a weight applied to the information specifying the three-dimensional position of the measurement point in each of the pair of images is determined so that variance of the weighted addition value is minimized.
5. An image processing method comprising:
(a1) acquiring an image captured by each of at least three cameras;
(a2) acquiring a camera parameter of each camera;
(a3) extracting pairs of images from the images;
(a4) calculating, for each of the pairs of images, based on the pairs of images and camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
(a5) performing, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
(a6) outputting position information of the measurement point to which a weighted addition value is applied,
wherein at least one of the processes (a1) to (a6) is executed by a processor, and
wherein the weighted addition uses a value obtained by normalizing the effective baseline length to the power of two by the sum of effective baseline lengths to the power of two.
6. An image processing method comprising:
(a1) acquiring an image captured by each of at least three cameras;
(a2) acquiring a camera parameter of each camera;
(a3) extracting pairs of images from the images;
(a4) calculating, for each of the pairs of images, based on the pairs of images and camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
(a5) performing, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
(a6) outputting position information of the measurement point to which a weighted addition value is applied,
wherein at least one of the processes (a1) to (a6) is executed by a processor, and
wherein the weighted addition uses a value obtained by normalizing the viewing angle to the power of two by the sum of viewing angles to the power of two.
7. A non-transitory computer-readable recording medium storing a control program that causes an instrument including a processor to execute processing comprising:
(a1) acquiring an image captured by each of at least three cameras;
(a2) acquiring a camera parameter of each camera;
(a3) extracting pairs of images from the images;
(a4) calculating, for each of the pairs of images, based on the pairs of images and camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
(a5) performing, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
(a6) outputting position information of the measurement point to which a weighted addition value is applied,
wherein a weight applied to the information specifying the three-dimensional position of the measurement point in each of the pair of images is determined so that variance of the weighted addition value is minimized.
8. A non-transitory computer-readable recording medium storing a control program that causes an instrument including a processor to execute processing comprising:
(a1) acquiring an image captured by each of at least three cameras;
(a2) acquiring a camera parameter of each camera;
(a3) extracting pairs of images from the images;
(a4) calculating, for each of the pairs of images, based on the pairs of images and camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
(a5) performing, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
(a6) outputting position information of the measurement point to which a weighted addition value is applied,
wherein the weighted addition uses a value obtained by normalizing the effective baseline length to the power of two by the sum of effective baseline lengths to the power of two.
9. A non-transitory computer-readable recording medium storing a control program that causes an instrument including a processor to execute processing comprising:
(a1) acquiring an image captured by each of at least three cameras;
(a2) acquiring a camera parameter of each camera;
(a3) extracting pairs of images from the images;
(a4) calculating, for each of the pairs of images, based on the pairs of images and camera parameters, position information including information specifying a three-dimensional position of a measurement point with respect to a pair of pixels, one of the pixels being included in one of the pair of images and the other of the pixels being included in the other of the pair of images, and information specifying a position of the one of the pixels in one of the pair of images and a position of the other of the pixels in the other of the pair of images;
(a5) performing, based on the position information and the camera parameters, weighted addition on the information specifying the three-dimensional position of the measurement point in each of the pair of images, with information using an effective baseline length or a viewing angle with respect to the three-dimensional position, of a pair of the cameras corresponding to the pair of images; and
(a6) outputting position information of the measurement point to which a weighted addition value is applied,
wherein the weighted addition uses a value obtained by normalizing the viewing angle to the power of two by the sum of viewing angles to the power of two.