Image generating device, image generating method, and non-transitory computer-readable storage medium
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/36
G06T-005/50
B60R-001/00
G06T-003/40
B60R-011/04
G06T-005/00
G06T-005/40
G06T-011/60
H04N-005/247
H04N-007/18
출원번호
US-0902938
(2014-06-23)
등록번호
US-9691142
(2017-06-27)
우선권정보
JP-2013-142726 (2013-07-08)
국제출원번호
PCT/JP2014/003347
(2014-06-23)
국제공개번호
WO2015/004866
(2015-01-15)
발명자
/ 주소
Shigemura, Shusaku
출원인 / 주소
DENSO CORPORATION
대리인 / 주소
Knobbe, Martens, Olson & Bear, LLP
인용정보
피인용 횟수 :
0인용 특허 :
6
초록▼
An image generating device that generates a composite image based on partial images cut out from captured images having photographic subject regions partially overlapping with each other, includes: a correction device that corrects each target partial image by setting one of first and second adjacen
An image generating device that generates a composite image based on partial images cut out from captured images having photographic subject regions partially overlapping with each other, includes: a correction device that corrects each target partial image by setting one of first and second adjacent partial images as a reference partial image; a generation device that generates first and second conversion tables for approximating a concentration characteristic of each target partial image in overlapping first and second common regions to the first and second adjacent partial images, respectively; and a mixture conversion device that converts a concentration of each target partial image to make an influence of the first conversion table larger as a position of a pixel is closer to the first adjacent partial image, and to make the influence of the second conversion table larger as the position of the pixel is closer to the second adjacent partial image.
대표청구항▼
1. An image generating device that generates a composite image, in which a plurality of partial images respectively cut out from a plurality of captured images are continuously arranged, using the plurality of captured images respectively having photographic subject regions partially overlapping wit
1. An image generating device that generates a composite image, in which a plurality of partial images respectively cut out from a plurality of captured images are continuously arranged, using the plurality of captured images respectively having photographic subject regions partially overlapping with each other, the image generating device comprising: a correction device, using a processor, that corrects each target partial image by setting at least one of a first adjacent partial image and a second adjacent partial image, which are the partial images adjacent to the target partial image on both sides in the composite image, as a reference partial image, when at least one of the plurality of partial images is defined as a reference partial image, and the partial images other than the reference partial image are defined as target partial images, wherein the plurality of partial images are continuously arranged in an annular shape;a generation device, using the processor, that generates a first conversion table as a concentration conversion table for performing a correction to approximate a concentration characteristic of each target partial image to a concentration characteristic of the first adjacent partial image and a second conversion table as a concentration conversion table for performing a correction to approximate the concentration characteristic of each target partial image to a concentration characteristic of the second adjacent partial image; anda mixture conversion device, using the processor, that converts a concentration of each target partial image using each of the first conversion table and the second conversion table, wherein:the generation device generates the concentration conversion table as the first conversion table for performing the correction to approximate a concentration characteristic of each target captured image in a first common region to a concentration characteristic of a first adjacent captured image in the first common region when a photographic subject region of the target captured image, which is a captured image providing an origin of the target partial image, and a photographic subject region of the first adjacent captured image, which is a captured image providing an origin of the first adjacent partial image, are overlapped in the first common region;the generation device generates the concentration conversion table as the second conversion table for performing the correction to approximate a concentration characteristic of each target captured image in a second common region to a concentration characteristic of a second adjacent captured image in the second common region when the photographic subject region of the target captured image and a photographic subject region of the second adjacent captured image, which is a captured image providing an origin of the second adjacent partial image, are overlapped in the second common region; andthe mixture conversion device converts the concentration of the target partial image to make an influence of the first conversion table larger as compared with an influence of the second conversion table as a position of a pixel in the target partial image is closer to the first adjacent partial image, and to make the influence of the second conversion table larger as compared with the influence of the first conversion table as the position of the pixel in the target partial image is closer to the second adjacent partial image. 2. The image generating device according to claim 1, further comprising: a setting device, using the processor, that sets one or more of the plurality of partial images, of which the concentration characteristic satisfies a predetermine condition, to be the reference partial image. 3. The image generating device according to claim 2, wherein: the correction device does not correct the partial image when no partial image for satisfying the predetermined condition is present in the plurality of the partial images. 4. The image generating device according to claim 1, further comprising: a fixation conversion device, using the processor, that converts a concentration of the target partial image using one of the first conversion table and the second conversion table, wherein:the correction device converts the concentration of the target partial image using the fixation conversion device when the first adjacent partial image and the second adjacent partial image are one of the reference partial image and the target partial image after a concentration conversion, and the target partial image before the concentration conversion; andthe correction device converts the concentration of the target partial image using the mixture conversion device when both of the first adjacent partial image and the second adjacent partial image are any one of the reference partial image and the target partial image after the concentration conversion. 5. The image generating device according to claim 1, wherein: the plurality of captured images are captured by a plurality of imaging devices mounted in a vehicle, respectively; andthe composite image is an image of a surrounding of the vehicle viewed from a top. 6. An image generating method used in an image generating device that generates a composite image, in which a plurality of partial images respectively cut out from a plurality of captured images are continuously arranged, using the plurality of captured images respectively having photographic subject regions partially overlapping with each other, the image generating method comprising: correcting each target partial image by setting at least one of a first adjacent partial image and a second adjacent partial image, which are the partial images adjacent to the target partial image on both sides in the composite image, as a reference partial image, when at least one of the plurality of partial images is defined as a reference partial image, and the partial images other than the reference partial image are defined as target partial images, wherein the plurality of partial images are continuously arranged in an annular shape;generating a first conversion table as a concentration conversion table for performing a correction to approximate a concentration characteristic of each target partial image to a concentration characteristic of the first adjacent partial image and a second conversion table as a concentration conversion table for performing a correction to approximate the concentration characteristic of each target partial image to a concentration characteristic of the second adjacent partial image; andconverting a concentration of each target partial image using each of the first conversion table and the second conversion table, wherein:the generating provides to generate the concentration conversion table as the first conversion table for performing the correction to approximate a concentration characteristic of each target captured image in a first common region to a concentration characteristic of a first adjacent captured image in the first common region when a photographic subject region of the target captured image, which is a captured image providing an origin of the target partial image, and a photographic subject region of the first adjacent captured image, which is a captured image providing an origin of the first adjacent partial image, are overlapped in the first common region;the generating provides to generate the concentration conversion table as the second conversion table for performing the correction to approximate a concentration characteristic of each target captured image in a second common region to a concentration characteristic of a second adjacent captured image in the second common region when the photographic subject region of the target captured image and a photographic subject region of the second adjacent captured image, which is a captured image providing an origin of the second adjacent partial image, are overlapped in the second common region; andthe converting provides to convert the concentration of the target partial image to make an influence of the first conversion table larger as compared with an influence of the second conversion table as a position of a pixel in the target partial image is closer to the first adjacent partial image, and to make the influence of the second conversion table larger as compared with the influence of the first conversion table as the position of the pixel in the target partial image is closer to the second adjacent partial image. 7. A non-transitory computer readable storage medium comprising instructions for functioning a computer as an image generating device that generates a composite image, in which a plurality of partial images respectively cut out from a plurality of captured images are continuously arranged, using the plurality of captured images respectively having photographic subject regions partially overlapping with each other, the instruction including: correcting each target partial image by setting at least one of a first adjacent partial image and a second adjacent partial image, which are the partial images adjacent to the target partial image on both sides in the composite image, as a reference partial image, when at least one of the plurality of partial images is defined as a reference partial image, and the partial images other than the reference partial image are defined as target partial images, wherein the plurality of partial images are continuously arranged in an annular shape;generating a first conversion table as a concentration conversion table for performing a correction to approximate a concentration characteristic of each target partial image to a concentration characteristic of the first adjacent partial image and a second conversion table as a concentration conversion table for performing a correction to approximate the concentration characteristic of each target partial image to a concentration characteristic of the second adjacent partial image; andconverting a concentration of each target partial image using each of the first conversion table and the second conversion table, wherein:the generating provides to generate the concentration conversion table as the first conversion table for performing the correction to approximate a concentration characteristic of each target captured image in a first common region to a concentration characteristic of a first adjacent captured image in the first common region when a photographic subject region of the target captured image, which is a captured image providing an origin of the target partial image, and a photographic subject region of the first adjacent captured image, which is a captured image providing an origin of the first adjacent partial image, are overlapped in the first common region;the generating provides to generate the concentration conversion table as the second conversion table for performing the correction to approximate a concentration characteristic of each target captured image in a second common region to a concentration characteristic of a second adjacent captured image in the second common region when the photographic subject region of the target captured image and a photographic subject region of the second adjacent captured image, which is a captured image providing an origin of the second adjacent partial image, are overlapped in the second common region; andthe converting provides to convert the concentration of the target partial image to make an influence of the first conversion table larger as compared with an influence of the second conversion table as a position of a pixel in the target partial image is closer to the first adjacent partial image, and to make the influence of the second conversion table larger as compared with the influence of the first conversion table as the position of the pixel in the target partial image is closer to the second adjacent partial image.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (6)
Katayama Tatsushi,JPX ; Takiguchi Hideo,JPX ; Yano Kotaro,JPX ; Hatori Kenji,JPX, Apparatus and method for combining a plurality of images.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.