Abstract: A learning device, an image generating device, a learning method, an image generating method, and a program are provided which can improve accuracy of estimation of an environment outside an angle of view of an image input to an image generating section. A second learning data obtaining section (64) obtains an input image. A second learning section (66) obtains result data indicating a result of execution of semantic segmentation on the input image. An input data generating section (38) generates input data obtained by coupling the input image and the result data to each other. By using the input data as input, the second learning section (66) performs learning of a wide view angle image generating section (28) that generates, in response to input of data obtained by coupling an image to a result of execution of semantic segmentation on the image, an image having a wider angle of view than the image.

Abstract: Provided are a training apparatus, a recognition apparatus, a training method, a recognition method, and a program that can accurately recognize what an object represented in an image associated with depth information is. An object data acquiring section acquires three-dimensional data representing an object. A training data generating section generates a plurality of training data each representing a mutually different part of the object on the basis of the three-dimensional data. A training section trains a machine learning model using the generated training data as the training data for the object.

Abstract: Provided are an image processing device, an image processing method, and a program capable of forming an accurate three-dimensional map even in a case where a moving object is included in an input image. The image processing device includes an image acquiring section that sequentially acquires two-dimensional captured images, an object type recognition executing section that attaches, to each pixel in the sequentially acquired captured images, a label indicating the type of an object represented by the pixel, and a three-dimensional map creating section that executes three-dimensional position recognition of each pixel of the captured images to create a three-dimensional map, on the basis of the sequentially acquired captured images, and the three-dimensional map creating section restricts the three-dimensional position recognition of each pixel of the captured images according to the label attached to the pixel.

Abstract: Provided are an image processing device, an image processing method, and a program for recognizing an object in a three-dimensional map, which do not require collecting learning data of the three-dimensional map and can perform high-speed processing with a small load. The image processing device includes an image acquiring section that sequentially acquires a two-dimensional input image for each frame; an object type recognition executing section that attaches, to each of pixels of the input image acquired for each frame, a label indicating a type of an object represented by the pixels; and a labeling section that executes three-dimensional position recognition of a subject represented in the input image to create a three-dimensional map, based on the input image sequentially input, and attaches, to each voxel included in the three-dimensional map, the label of the pixel corresponding to the voxel.

Abstract: Provided are a training apparatus, an image recognition apparatus, a training method, and a program capable of improving the accuracy of image recognition of a photographic image using classifiers that have been trained using CG images. An intermediate feature identifying section identifies an intermediate feature. An offset feature identifying section identifies an offset feature on the basis of a CG intermediate feature and a photographic intermediate feature. A post-offset intermediate feature identifying section identifies a post-offset intermediate feature associated with a CG image on the basis of the intermediate feature associated with the CG image and the offset feature.

Abstract: A classification learning section executes training of a feature quantity extraction section and training of a classification section resulting from a comparison between an output generated when feature quantity data is inputted to the classification section and training data regarding a plurality of classes associated with a source domain training image. A dividing section divides feature quantity data outputted from the feature quantity extraction section in accordance with input of an image into a plurality of pieces of partial feature quantity data corresponding to the image including a feature map of one or more of the classes. A domain identification learning section executes training of the feature quantity extraction section resulting from a comparison between an output generated when partial feature quantity data corresponding to the image is inputted to a domain identification section and data indicating whether the image belongs to a source domain or to the target domain.

Abstract: A learning input image acquisition section acquires a plurality of input images individually depicting a state imaged at a predetermined angle of view in a predetermined relative imaging direction. A learning wide angle-of-view image acquisition section acquires a wide angle-of-view image having an angle of view including all the angles of view of the plurality of input images. A learning section performs learning of a wide angle-of-view image generation section based on a learning wide angle-of-view image and an output that is generated when the plurality of input images are inputted to the wide angle-of-view image generation section, which generates and outputs an image having an angle of view including all the angles of view of a plurality of images in response to the input of the plurality of images.

Abstract: Provided are a recognition processing device, a recognition processing method, and a program capable of efficiently narrowing down a three-dimensional region on which recognition processing using a three-dimensional convolutional neural network is to be executed. A first recognition process executing section executes a first recognition process on a captured image obtained by capturing an image of a real space and used to generate voxel data. A target two-dimensional region determining section determines a two-dimensional region occupying part of the captured image on the basis of a result of the first recognition process. A target three-dimensional region determining section determines a three-dimensional region in the real space on the basis of the two-dimensional region and a position of a camera when the camera obtains the captured image.

Abstract: Provided are an image recognition apparatus, an image recognition method, and a program for enabling recognition of many kinds of objects with high precision. An overall recognition unit executes, for at least one given object, a process of recognizing the position of the object in an image. A partial image extraction unit extracts, from the image, a partial image which is a part of the image associated with the recognized position. A partial recognition unit executes a process of recognizing what is one or more objects represented by the partial image, the one or more objects including an object other than the given object the position of which is recognized.

Abstract: A learning input image acquisition section acquires a plurality of input images individually depicting a state imaged at a predetermined angle of view in a predetermined relative imaging direction. A learning wide angle-of-view image acquisition section acquires a wide angle-of-view image having an angle of view including all the angles of view of the plurality of input images. A learning section performs learning of a wide angle-of-view image generation section based on a learning wide angle-of-view image and an output that is generated when the plurality of input images are inputted to the wide angle-of-view image generation section, which generates and outputs an image having an angle of view including all the angles of view of a plurality of images in response to the input of the plurality of images.

Abstract: A learning device, an image generating device, a learning method, an image generating method, and a program are provided which can improve accuracy of estimation of an environment outside an angle of view of an image input to an image generating section. A second learning data obtaining section (64) obtains an input image. A second learning section (66) obtains result data indicating a result of execution of semantic segmentation on the input image. An input data generating section (38) generates input data obtained by coupling the input image and the result data to each other. By using the input data as input, the second learning section (66) performs learning of a wide view angle image generating section (28) that generates, in response to input of data obtained by coupling an image to a result of execution of semantic segmentation on the image, an image having a wider angle of view than the image.

Abstract: A classification learning section executes training of a feature quantity extraction section and training of a classification section resulting from a comparison between an output generated when feature quantity data is inputted to the classification section and training data regarding a plurality of classes associated with a source domain training image. A dividing section divides feature quantity data outputted from the feature quantity extraction section in accordance with input of an image into a plurality of pieces of partial feature quantity data corresponding to the image including a feature map of one or more of the classes. A domain identification learning section executes training of the feature quantity extraction section resulting from a comparison between an output generated when partial feature quantity data corresponding to the image is inputted to a domain identification section and data indicating whether the image belongs to a source domain or to the target domain.

Abstract: Provided are a training apparatus, an image recognition apparatus, a training method, and a program capable of improving the accuracy of image recognition of a photographic image using classifiers that have been trained using CG images. An intermediate feature identifying section identifies an intermediate feature. An offset feature identifying section identifies an offset feature on the basis of a CG intermediate feature and a photographic intermediate feature. A post-offset intermediate feature identifying section identifies a post-offset intermediate feature associated with a CG image on the basis of the intermediate feature associated with the CG image and the offset feature.

Abstract: Provided are a recognition processing device, a recognition processing method, and a program capable of efficiently narrowing down a three-dimensional region on which recognition processing using a three-dimensional convolutional neural network is to be executed. A first recognition process executing section executes a first recognition process on a captured image obtained by capturing an image of a real space and used to generate voxel data. A target two-dimensional region determining section determines a two-dimensional region occupying part of the captured image on the basis of a result of the first recognition process. A target three-dimensional region determining section determines a three-dimensional region in the real space on the basis of the two-dimensional region and a position of a camera when the camera obtains the captured image.

Abstract: Provided are a training apparatus, a recognition apparatus, a training method, a recognition method, and a program that can accurately recognize what an object represented in an image associated with depth information is. An object data acquiring section acquires three-dimensional data representing an object. A training data generating section generates a plurality of training data each representing a mutually different part of the object on the basis of the three-dimensional data. A training section trains a machine learning model using the generated training data as the training data for the object.

Abstract: Provided are an image recognition apparatus, an image recognition method, and a program for enabling recognition of many kinds of objects with high precision. An overall recognition unit executes, for at least one given object, a process of recognizing the position of the object in an image. A partial image extraction unit extracts, from the image, a partial image which is a part of the image associated with the recognized position. A partial recognition unit executes a process of recognizing what is one or more objects represented by the partial image, the one or more objects including an object other than the given object the position of which is recognized.