Image processing device and image capture apparatus

Patent metadata

Field	Value
Publication number	US-11069076-B2
Application number	US-201916298039-A
Country	US
Kind code	B2
Filing date	Mar 11, 2019
Priority date	Aug 7, 2018
Publication date	Jul 20, 2021
Grant date	Jul 20, 2021

Abstract

According to one embodiment, an image processing device includes a hardware processor implemented by one or more processors. The hardware processor is configured to acquire an image captured by a monocular camera. The hardware processor is configured to estimate a distance to an object based on the acquired image. The hardware processor is configured to calculate the distance to the object by considering an atmosphere failure influencing the acquired image and executing a statistical process on the estimated distance.

First claim

What is claimed is:

1. An image processing device comprising:
a hardware processor implemented by one or more processors; wherein
the hardware processor is configured to:
acquire an image captured by a monocular camera;
estimate a distance to an object based on the acquired image;
calculate the distance to the object by considering an atmosphere failure influencing the acquired image and executing a statistical process on the estimated distance;
estimate a degree of the atmosphere failure based on the estimated distance,
calculate a strength of the statistical process based on the estimated degree of the atmosphere failure, and
calculate the distance to the object by executing the statistical process on the estimated distance based on the calculated strength of the statistical process.

2. The image processing device of claim 1 , wherein
the hardware processor is configured to calculate the distance to the object by executing the statistical process on the estimated distance based on the strength of the statistical process specified by a user's operation.

3. The image processing device of claim 1 , wherein
the hardware processor is configured to:
calculate the strength of the statistical process based on weather information acquired from an external device, and
calculate the distance to the object by executing the statistical process on the estimated distance based on the calculated strength of the statistical process.

4. The image processing device of claim 1 , wherein
the hardware processor is configured to:
measure an air temperature,
calculate the strength of the statistical process based on the measured air temperature, and
calculate the distance to the object by executing the statistical process on the estimated distance based on the calculated strength of the statistical process.

5. The image processing device of claim 1 , wherein
the hardware processor is configured to:
estimate the degree of the atmosphere failure based on a result of comparison of a prepared image under no influence of the atmosphere failure with the acquired image,
calculate the strength of the statistical process based on the estimated degree of the atmosphere failure, and
calculate the distance to the object by executing the statistical process on the estimated distance based on the calculated strength of the statistical process.

6. The image processing device of claim 5 , wherein
the hardware processor is configured to, when the estimated degree of the atmosphere failure is equal to or larger than a threshold, notify a user to stop measurement of the distance to the object.

7. The image processing device of claim 1 , wherein
the hardware processor is configured to estimate the distance to the object by using a first image with a first color component and a second image with a second color component that is different from the first color component and has a blur function expressed in point asymmetry.

8. The image processing device of claim 1 , wherein
the hardware processor is configured to:
acquire a first image that has a blur function indicating a non-slanted blur shape and a second image that has the blur function indicating a slanted blur shape,
generate a plurality of third images by adding a plurality of different blurs to the acquired second image, and
estimate the distance to the object according to a correlation between the acquired first image and the generated plurality of third images.

9. The image processing device of claim 1 , wherein
the hardware processor is configured to:
acquire a first image that has a blur function indicating a non-slanted blur shape and a second image that has the blur function indicating a slanted blur shape,
extract edges from the acquired first image and second image,
calculate amounts of color deviation in the images based on the distances between the extracted edges of the images, and
estimate the distance to the object based on the calculated amounts of color deviation.

10. An imaging capture apparatus comprising:
an image processing device comprising a hardware processor implemented by one or more processors; and
a monocular camera, wherein
the hardware processor is configured to:
acquire an image captured by the monocular camera;
estimate a distance to an object based on the acquired image;
calculate the distance to the object by considering an atmosphere failure influencing the acquired image and executing a statistical process on the estimated distance;
estimate a degree of the atmosphere failure based on the estimated distance,
calculate a strength of the statistical process based on the estimated degree of the atmosphere failure, and
calculate the distance to the object by executing the statistical process on the estimated distance based on the calculated strength of the statistical process.

Assignees

• Toshiba Kk

Inventors

• Tsuruyama Tomoya
• Mishima Nao
• Kozakaya Tatsuo
• Moriya Akihisa
• Yamaguchi Jun
• Sasaki Takayuki

Classifications

• G06T7/50 Primary

  Depth or shape recovery · CPC title

• G01B11/026 Primary

  by measuring distance between sensor and object (G01B11/0608 takes precedence) · CPC title