JP2017120672A5 - Image processing apparatus, image processing system, and image processing method - Google Patents

Description

The present invention relates to an image processing apparatus , an image processing system, and an image processing method for generating a learning image for generating a dictionary used for image recognition processing for detecting an image of a target object from an input image.

In view of the above problems, the present invention provides an image processing apparatus and an image processing system that easily generate a learning image that approximates the surface luminance of a target object by reflecting environmental conditions based on information obtained by photographing the target object in a real environment. And an image processing method.

As a means for achieving the above object, an image processing apparatus of the present invention comprises the following arrangement. That is, an image processing apparatus for generating a learning image used for generation of the dictionary referenced in the recognition of an object,
A brightness value of the surface of the object in each of a plurality of areas is acquired from a brightness image including the plurality of objects having different postures, and information relating to the orientation of the surface of the object in each of the plurality of areas is acquired. Acquisition means of
Second acquisition means for acquiring a relationship between information relating to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition means and a luminance value corresponding to each area;
And generating means for generating the learning image based on the relationship acquired by the second acquiring means and the model information of the object .

Claims (23)

An image processing apparatus for generating a learning image used for generation of the dictionary referenced in the recognition of an object,
A brightness value of the surface of the object in each of a plurality of areas is acquired from a brightness image including the plurality of objects having different postures, and information relating to the orientation of the surface of the object in each of the plurality of areas is acquired. Acquisition means of
Second acquisition means for acquiring a relationship between information relating to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition means and a luminance value corresponding to each area;
An image processing apparatus comprising: a generation unit configured to generate the learning image based on the relationship acquired by the second acquisition unit and the model information of the object . The first acquisition means acquires a plurality of luminance images including a plurality of the objects having different postures, acquires a luminance value of the surface of the object in a plurality of regions from each luminance image, and for each luminance image Obtaining information related to the orientation of the surface of the object in the plurality of regions,
The second acquisition means, for each of the luminance images, a relationship between information relating to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition means and a luminance value corresponding to each area The image processing apparatus according to claim 1, further comprising: The first acquisition means acquires distance information of each pixel of the luminance image, and acquires information related to the orientation of the surface of the object in the plurality of regions based on the acquired distance information. The image processing apparatus according to claim 1 or 2. 4. The image according to claim 1, wherein the luminance image including the plurality of objects having different postures is an image taken in a state where the plurality of objects are randomly arranged. 5. Processing equipment. 5. The image processing apparatus according to claim 1, wherein the luminance image including the plurality of objects having different postures is an image captured in a state where the plurality of objects are piled up. 6. . Based on the relationship acquired by the second acquisition means, further comprising an estimation means for estimating a luminance distribution on the surface of the object;
The generation unit, based on the model information of the object and luminance distribution estimated by the estimating means, the image processing according to any one of claims 1 to 5, characterized in that to generate the learning image apparatus. The image processing apparatus according to claim 6 , wherein the generation unit determines a luminance value corresponding to information related to a direction of the surface of the object from a distribution of the luminance distribution. The image processing apparatus according to claim 6 , wherein the estimation unit estimates the luminance distribution based on a relationship acquired by the second acquisition unit and a predetermined luminance distribution model. Said estimating means, means and, said plurality of the means for assigning the acquired relationship by the second acquisition unit to the luminance distribution model, the luminance distribution model said plurality of luminance distribution models for obtaining a plurality of intensity distribution model The image processing apparatus according to claim 8 , further comprising an update unit configured to update based on a relationship assigned to the image processing apparatus. The assigning means is configured to input the information related to the orientation of the surface of the object indicated by the relationship acquired by the second acquiring means to the brightness distribution model closest to the brightness value obtained by the relationship. The image processing apparatus according to claim 9 , wherein the relationship is assigned to the image processing apparatus. 10. The apparatus according to claim 9 , further comprising : a unit that causes the allocation unit and the update unit to repeatedly perform processing until the allocation destinations of the relationship acquired by the second acquisition unit before and after the update match. Image processing apparatus. The generating means performs projective transformation corresponding to a plurality of postures of the object on the model information of the object, and in the orientation of the surface of the object indicated by the model information after the projective transformation , giving a brightness value corresponding to the orientation of the surface, the image processing apparatus according to any one of claims 1 to 11, characterized in that to generate the learning images for each of the posture. The model information is CAD data, the learning image is an image processing apparatus according to any one of claims 1 to 12, characterized in that a CG image. The image processing according to any one of claims 1 to 13, wherein the information related to the orientation of the surface of the object acquired by the first acquisition means is information on a normal of the surface of the object. apparatus. The image processing apparatus according to any one of claims 1 to 14, further comprising a distance image generating means for generating a distance image from the model information of the said luminance image object. The image processing apparatus according to claim 15 , wherein the distance image represents a position of a surface of the object. Based on the generated training image by the generation unit, an image processing apparatus according to any one of claims 1 to 16, further comprising means for generating a classifier for recognizing said object . It means for obtaining an image including the object,
Recognition means for recognizing the object from an image including the object based on the classifier ;
The image processing apparatus according to claim 17 , further comprising: The image processing apparatus according to claim 1, wherein the luminance image including a plurality of objects having different postures is an image photographed under the same illumination condition as the recognition of the object. An image processing method for generating a learning image used for generation of the dictionary referenced in the recognition of an object,
A brightness value of the surface of the object in each of a plurality of areas is acquired from a brightness image including the plurality of objects having different postures, and information relating to the orientation of the surface of the object in each of the plurality of areas is acquired. The acquisition step of
A second acquisition step of acquiring a relationship between the luminance value corresponding to the information and each region according to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition step,
An image processing method comprising: a generation step of generating the learning image based on the relationship acquired in the second acquisition step and the model information of the object . Further comprising the step of inputting the luminance image;
In the first acquisition step, the luminance value of the surface of the object in each of the plurality of regions of the input luminance image is acquired, and information relating to the orientation of the surface of the object in each of the plurality of regions is acquired. The image processing method according to claim 20, wherein: An image processing system for generating a learning image used for generating a dictionary referred to in object recognition,
Photographing means for photographing a luminance image including a plurality of the objects having different postures;
First acquisition means for acquiring a luminance value of the surface of the object in each of a plurality of areas from the captured luminance image, and acquiring information relating to the orientation of the surface of the object in each of the plurality of areas;
Second acquisition means for acquiring a relationship between information relating to the orientation of the surface of the object in the plurality of areas acquired by the first acquisition means and a luminance value corresponding to each area;
Generating means for generating the learning image based on the relationship acquired by the second acquiring means and the model information of the object;
An image processing system comprising: A program for causing a computer device to function as each unit of the image processing device according to any one of claims 1 to 19 when executed by the computer device.