Image processing apparatus, image processing method, and image processing program

Patent metadata

Field	Value
Publication number	US-10713530-B2
Application number	US-201815902332-A
Country	US
Kind code	B2
Filing date	Feb 22, 2018
Priority date	Mar 13, 2017
Publication date	Jul 14, 2020
Grant date	Jul 14, 2020

Abstract

An image processing apparatus includes a scale-down factor determination unit that generates two-dimensional images of an object viewed from a plurality of viewpoints using three-dimensional data representing a three-dimensional shape of the object and determines a scale-down factor for each viewpoint, a template generation unit that scales down the generated two-dimensional image from each viewpoint using the scale-down factor determined for the viewpoint and calculates a feature quantity from a scaled-down image to generate a template, and a template information output unit that outputs, for each viewpoint, the template and the scale-down factor used for generating the template in a manner associated with each other.

First claim

The invention claimed is:

1. An image processing apparatus, comprising a processor configured with a program to perform operations comprising:
operation as a scale-down factor determination unit configured to generate two-dimensional images of an object viewed from a plurality of viewpoints using three-dimensional data representing a three-dimensional shape of the object and determine a scale-down factor for each viewpoint;
operation as a template generation unit configured to generate, for each of the two-dimensional images from each viewpoint, a scaled-down image, using the scale-down factor determined for the viewpoint and calculate, for each viewpoint, a feature quantity from the scaled-down image to generate a template; and
operation as a template information output unit configured to output, for each viewpoint, the template and the scale-down factor used for generating the template in a manner associated with each other.

2. The image processing apparatus according to claim 1 , wherein
the processor is configured with the program such that operation as the scale-down factor determination unit comprises operation as the scale-down factor determination unit that determines the scale-down factor based on the number of feature points included in the template for each viewpoint or an area of the object to be included in the scaled-down image from each viewpoint.

3. The image processing apparatus according to claim 1 , wherein
the processor is configured with the program such that operation as the scale-down factor determination unit comprises operation as the scale-down factor determination unit that integrates the scale-down factors determined for the plurality of viewpoints.

4. The image processing apparatus according to claim 3 , wherein
the processor is configured with the program such that operation as the scale-down factor determination unit comprises operation as the scale-down factor determination unit that selects a reference viewpoint, classifies viewpoints satisfying a predetermined condition defining a positional relationship with the reference viewpoint into the same group as for the reference viewpoint, and integrates the scale-down factors by assigning the same scale-down factor to the viewpoints included in the same group.

5. The image processing apparatus according to claim 1 , wherein the processor is configured with the program to perform operations further comprising:
operation as an image obtaining unit configured to obtain an input image;
operation as an image scale-down unit configured to scale down the obtained input image using the plurality of scale-down factors output by the template information output unit to generate a plurality of scaled-down input images;
operation as a feature quantity calculation unit configured to calculate a feature quantity from each of the generated scaled-down input images, the feature quantity being the same item as the feature quantity calculated by the template generation unit;
operation as a template matching unit configured to search for a position of the object in the scaled-down input image using the template and the feature quantity calculated by the feature quantity calculation unit from the scaled-down input image having the scale-down factor associated with the template, and obtain a plurality of comparison results; and
operation as a recognition output unit configured to output a recognition result obtained by integrating the plurality of comparison results.

6. The image processing apparatus according to claim 5 , wherein
the comparison results comprise coordinates of the object recognized in each scaled-down input image and a comparison score representing a degree of image feature matching between the scaled-down input image and the template on the coordinates, and
the processor is configured with the program such that, for different comparison results output on the same coordinates, the recognition output unit determines a template having the highest comparison score being recognized on the coordinates, and outputs the recognition result.

7. An image processing method that is implemented by a computer, the method comprising:
generating two-dimensional images of an object viewed from a plurality of viewpoints using three-dimensional data representing a three-dimensional shape of the object;
determining a scale-down factor for each viewpoint;
generating, for each of the two-dimensional images from each viewpoint, a scaled-down image using the scale-down factor determined for the viewpoint;
calculating, for each viewpoint, a feature quantity from the scaled-down image to generate a template; and
outputting, for each viewpoint, the template and the scale-down factor used for generating the template in a manner associated with each other.

8. The image processing method according to claim 7 , further comprising:
obtaining an input image;
scaling down the obtained input image using a plurality of the output scale-down factors to generate a plurality of scaled-down input images;
calculating a feature quantity from each of the plurality of scaled-down images, the feature quantity being the same item as the feature quantity used to generate the template;
searching for a position of the object in the scaled-down input image using the template and the feature quantity calculated from the scaled-down input image having the scale-down factor associated with the template, and obtaining a plurality of comparison results; and
outputting a recognition result obtained by integrating the plurality of comparison results.

9. A non-transitory computer-readable recording medium storing a program causing a computer to perform operations comprising:
generating two-dimensional images of an object viewed from a plurality of viewpoints using three-dimensional data representing a three-dimensional shape of the object;
determining a scale-down factor for each viewpoint;
generating, for each of the two-dimensional image images from each viewpoint, a scaled-down image using the scale-down factor determined for the viewpoint;
calculating, for each viewpoint, a feature quantity from the scaled-down image to generate a template; and
outputting, for each viewpoint, the template and the scale-down factor used for generating the template in a manner associated with each other.

10. The non-transitory computer-readable recording medium according to claim 9 , storing the program causing the computer to perform operations further comprising:
obtaining an input image;
scaling down the obtained input image using a plurality of the output scale-down factors to generate a plurality of scaled-down input images;
calculating a feature quantity from each of the plurality of scaled-down images, the feature quantity being the same item as the feature quantity used to generate the template;
searching for a position of the object in the scaled-down input image using the template and the feature quantity calculated from the scaled-down input image having the scale-down factor associated with the template, and obtaining a plurality of comparison results; and
outputting a recognition result obtained by integrating the plurality of comparison results.

11. The image processing apparatus according to claim 2 , wherein
the processor is configured with the program such that operation as the scale-down factor determination unit comprises operation as the scale-down factor determination unit that integrates the scale-down factors determined for the plurality of viewpoints.

12. The image processing apparatus according to claim 11 , wherein
the processor is configured with the program such that operation as the scale-down factor

Assignees

• Omron Tateisi Electronics Co

Inventors

• Konishi Yoshinori

Classifications

• G06V10/52

  Scale-space analysis, e.g. wavelet analysis (multi-scale boundary representations G06V10/42) · CPC title

• G06F18/28

  Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries · CPC title

• G06V20/647 Primary

  by matching two-dimensional images to three-dimensional objects · CPC title

• G06F18/2137

  based on criteria of topology preservation, e.g. multidimensional scaling or self-organising maps · CPC title

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title