Three-dimensional model generation method, three-dimensional model generation device, and non-transitory computer readable medium
AssigneePanasonic Intellectual Property Management Co., Ltd.
InventorsToru Matsunobu, Satoshi Yoshikawa, Kensho Teranishi, Masaki Fukuda, Ukyou Katsura
Life of this patent
Estimating the term…
Abstract
A three-dimensional model generation method executed by a computer includes: obtaining a first image generated by shooting a subject from a first viewpoint and a second image generated by shooting the subject from a second viewpoint; detecting, in at least the first image, a first line composed of a series of edges and corresponding to a contour of the subject; and generating first three-dimensional points representing the contour, in a three-dimensional space in the computer, based on the first image, the second image, and the first line.
Claims10
A three-dimensional model generation method executed by a computer, the three-dimensional model generation method comprising:
- obtaining a first image generated by shooting a subject from a first viewpoint and a second image generated by shooting the subject from a second viewpoint;
- detecting, in at least the first image, a first line composed of a series of edges and corresponding to a contour of the subject;
- and
- generating first three-dimensional points representing the contour, in a three-dimensional space in the computer, based on the first image, the second image, and the first line,
- wherein the generating the first three-dimensional points includes:
- (i)(a) correcting, based on the first line, positions of third three-dimensional points that correspond to the contour, the third three-dimensional points being among second three-dimensional points generated by performing matching by searching for similar points between the first image and the second image, the second three-dimensional points representing the subject, and (b) not correcting positions of one or more other three-dimensional points obtained by excluding the third three-dimensional points from the second three-dimensional points;
- or
- (ii)(a) generating a corrected first image by correcting pixel values of respective first pixels of a plurality of first pixels in the first image through which the first line passes, using the pixel values of the respective first pixels of the plurality of first pixels, (b) generating a corrected second image by correcting pixel values of respective second pixels of a plurality of second pixels in the second image through which a second line corresponding to the contour in the second image passes, using the pixel values of the respective second pixels of the plurality of second pixels, and (c) performing matching by searching for similar points between the corrected first image and the corrected second image.
A three-dimensional model generation device comprising:
- a processor;
- and
- a memory storing a program executable by the processor to cause the three-dimensional model generation device to:
- obtain a first image generated by shooting a subject from a first viewpoint and a second image generated by shooting the subject from a second viewpoint;
- detect, in at least the first image, a first line composed of a series of edges and corresponding to a contour of the subject;
- and
- generate first three-dimensional points representing the contour, in a three-dimensional space in a computer, based on the first image, the second image, and the first line,
- wherein in the generating the first three-dimensional points, the three-dimensional model generation device:
- (i)(a) corrects, based on the first line, positions of third three-dimensional points that correspond to the contour, the third three-dimensional points being among second three-dimensional points generated by performing matching by searching for similar points between the first image and the second image, the second three-dimensional points representing the subject, and (b) does not correct positions of one or more other three-dimensional points obtained by excluding the third three-dimensional points from the second three-dimensional points;
- or
- (ii)(a) generates a corrected first image by correcting pixel values of respective first pixels of a plurality of first pixels in the first image through which the first line passes, using the pixel values of the respective first pixels of the plurality of first pixels, (b) generates a corrected second image by correcting pixel values of respective second pixels of a plurality of second pixels in the second image through which a second line corresponding to the contour in the second image passes, using the pixel values of the respective second pixels of the plurality of second pixels, and (c) performs matching by searching for similar points between the corrected first image and the corrected second image.
A non-transitory computer readable medium storing a program executable by a processor to cause an information processing apparatus to:
- obtain a first image generated by shooting a subject from a first viewpoint and a second image generated by shooting the subject from a second viewpoint;
- detect, in at least the first image, a first line composed of a series of edges and corresponding to a contour of the subject;
- and
- generate first three-dimensional points representing the contour, in a three-dimensional space in a computer, based on the first image, the second image, and the first line,
- wherein in the generating the first three-dimensional points, the information processing apparatus:
- (i)(a) corrects, based on the first line, positions of third three-dimensional points that correspond to the contour, the third three-dimensional points being among second three-dimensional points generated by performing matching by searching for similar points between the first image and the second image, the second three-dimensional points representing the subject, and (b) does not correct positions of one or more other three-dimensional points obtained by excluding the third three-dimensional points from the second three-dimensional points;
- or
- (ii)(a) generates a corrected first image by correcting pixel values of respective first pixels of a plurality of first pixels in the first image through which the first line passes, using the pixel values of the respective first pixels of the plurality of first pixels, (b) generates a corrected second image by correcting pixel values of respective second pixels of a plurality of second pixels in the second image through which a second line corresponding to the contour in the second image passes, using the pixel values of the respective second pixels of the plurality of second pixels, and (c) performs matching by searching for similar points between the corrected first image and the corrected second image.
Dependencies are inferred from the claim text.