NTT COMMUNICATIONS CORPORATION

An estimating device includes processing circuitry configured to acquire image data lacking part of a body of a person, restore a defective part of the body of the person in the image data by using the image data acquired as an input, and using a whole body restoration model for restoring the defective part of the body of the person in the image data, and estimate skeleton data by using the image data restored as an input, and using a skeleton estimation model for estimating the skeleton data related to a skeleton of the person.

An estimating device includes processing circuitry configured to acquire image data lacking part of a body of a person, restore a defective part of the body of the person in the image data by using the image data acquired as an input, and using a whole body restoration model for restoring the defective part of the body of the person in the image data, and estimate skeleton data by using the image data restored as an input, and using a skeleton estimation model for estimating the skeleton data related to a skeleton of the person.

A learning device includes a convolutional neural network configured to output action, re-identification, size, and position feature maps in response to respective image frames constituting a video sequence being input; a processor; and a memory storing program instructions that cause the processor to: receive the action feature map, the re-identification feature map, and the size feature map to output an action feature, a re-identification feature, and a size feature; receive the action feature and the re-identification feature to output a feature obtained by considering an interaction between features; output a group activity classification result based on the output feature; output an action classification result based on the output feature; and update model parameters of the convolutional neural network so as to minimize an error between the position feature map, the size feature, the re-identification feature, the group activity classification result, and the action classification result; and correct data.

In accordance with the present invention, an object recognition device includes: a memory; and a processor coupled to the memory and configured to: track one or more objects that are detected from a video; and determine whether or not an attribute of an undetermined object can be determined, based on appearance information of the undetermined object in the video, the undetermined object being an object whose attribute is not yet determined among the one or more objects that are tracked, and determine the attribute of the undetermined object when the attribute of the undetermined object can be determined.

Even an attribute of a target object can be clearly confirmed while looking at a photographed image. According to one embodiment, where the user sets additional information for a 3D display image, a user terminal MT first displays first guide pattern in the process of specifying a setting target of the additional information, and then displays second guide information in the process of specifying the display position of the additional information. After the display position is determined, the additional information input by the user is registered in a server device SV in association with the setting target and the coordinates of the display position.

A technique for enabling accurate management of photography positions is provided. According to the first embodiment, a server device SV generates plan view data in which position coordinates of a photography point are plotted and transmits the plan view data to a user terminal MT, each time a photography operation is performed for a photography point. The plot position of the photography spot in the plan view data is corrected in accordance with a plot position correction request made by a user, and the corrected plan view data is stored as photography position management information.

Optimization of a photography position is intended. According to one embodiment, photography recommended positions are sequentially set based on reference points set on a two-dimensional coordinate plane of a plan view of a floor to be photographed, a graphic pattern representing a set photography recommended position is combined with a finder display image output from a camera CM to thereby generate photography guide information composed of an AR image, and the generated photography guide information is transmitted to the user terminal MT and displayed. In addition, it is determined whether or not the movement position of the user is within a predetermined range including the photography recommended position. If the photography is performed outside the predetermined range, a message is displayed to that effect or notification is given by vibrating a vibrator, and the image data photographed at this time is discarded.

An object tracking device according to an embodiment obtains trajectories that indicate tracks of target objects in an input video. The object tracking device has parallel processing hardware, and this parallel processing hardware: extracts primary points and secondary information for restoring a field of a target object captured in an image frame at a time t included in the video; selects, from among the extracted primary points, a primary point having the closest distance to a predicted primary point of the target object predicted from the trajectories obtained by a time t−1; and, when the distance is smaller than a first threshold determined from secondary information corresponding to the selected primary point, associates the selected primary point and the secondary information corresponding to the selected primary point, with a trajectory corresponding to the predicted primary point of the target object.

A learning device estimates skeleton data by using the acquired image data as an input, and using a skeleton estimation model for estimating the skeleton data related to a skeleton of the person. The learning device also uses the acquired image data as an input, and divides a region of the image data per classification of the clothing by using a clothing form region division model for dividing regions of respective pieces of the clothing of the person included in the image data per classification of the clothing. Subsequently, the learning device uses an estimation result and a division result as inputs, estimates the skeleton data by using an improved skeleton estimation model, and outputs a discrimination result of the skeleton input to a discrimination model by using the discrimination model that is learned to discriminate the estimated skeleton data from skeleton data as a correct answer.

A computing device uses image data as an input, and estimates skeleton data by using a skeleton estimation model for estimating the skeleton data related to a skeleton of a person. The computing device then calculates weight values of respective articulations based on reliability of estimation results of the respective articulations, and computes a similarity between pieces of the skeleton data by using the calculated weight values of the respective articulations. The computing device then determines whether the similarity is equal to or larger than a predetermined threshold. If the similarity is equal to or larger than the predetermined threshold, the computing device determines that authentication has succeeded, and if the similarity is smaller than the predetermined threshold, the computing device determines that authentication has failed.