Abstract: A video processing device includes a foreground region estimation unit that determines whether a pixel of an input image is a foreground or a background, and a blinking correction unit that determines, for a target pixel on which a foreground and a background have been switched, whether switching between the foreground and the background is a color change in the foreground or in the background by using a lookup table capable of determining whether switching is in the foreground or in the background from a temporal change of a pixel value, and corrects a result of determination as to whether it is the foreground or the background that has been performed for the target pixel in a case where the switching between the foreground and the background is the color change in the foreground or in the background.

Abstract: A settlement system includes a service provider device 2 which transmits a template information transaction including a template of a transaction to a network 4 of a first blockchain, a user device which transmits, to the network 4 of the first blockchain, a payment information transaction that includes an electronic signature generated by using the template of the transaction and a payment amount, and a smart contract 41, wherein the smart contract 41 verifies the electronic signature by using the payment amount and the template of the transaction, the service provider device 2 generates a settlement transaction by using the template of the transaction, the electronic signature and the payment amount, and transmits the settlement transaction to a network 3 of a second blockchain, a plurality of output conditions are set to the template of the transaction, and the settlement transaction becomes usable when any one of the plurality of output conditions is satisfied.

Abstract: It is possible to inhibit deterioration of extraction precision of a subject and reliably extract the subject even when colors of the subject and a background are the same or similar. An image processing device 1 includes an input unit 11 configured to input a first invisible light image of only a background in which a subject is not included and a second invisible light image in which the subject and the background are included and a subject region extraction unit 15 configured to calculate a difference between a pixel value of each pixel of the second invisible light image and a pixel value of a corresponding pixel of the first invisible light image, determine whether the pixel is in a subject region or a background region in accordance with whether the difference is equal to or greater than a predetermined threshold, and extract the subject region from the second invisible light image.

Abstract: Accurate and rapid identification can be performed even when feature vectors of input pixels and background pixels are close.

Abstract: To identify and track a plurality of objects. An object tracking device 1 includes a frame acquisition unit 31 for acquiring one set of frame data 11 included in moving image data that captures a space where a plurality of objects are present; a distance acquisition unit 32 for acquiring measurement data 12 from measurement of three-dimensional coordinates of points configuring the objects in the space where the objects are present; an object position detection unit 33 for detecting a two-dimensional position of each of the objects from the frame data 11 on the basis of comparison with template data of each of the objects; an object distance detection unit 34 for detecting a plurality of three-dimensional positions of the objects from the measurement data 12; and an associating unit 35 for associating each two-dimensional position from the object position detection unit 33 with the nearest three-dimensional position among the three-dimensional positions from the object distance detection unit 34.

Abstract: A video generation device includes: an object extraction unit 11 that extracts an object area from a captured video in a space; a spatial position tracking unit 12 that detects an article from three-dimensional position measurement data in the space, applies identification information to the article, and calculates a three-dimensional spatial position of the article using the three-dimensional position measurement data; a position information merging unit 13 that links the object area to the identification information of the article to associate the three-dimensional spatial position with the object area; a depth expression unit 14 that generates a depth expression video of only the object area with which the three-dimensional spatial position has been associated, a depth of the video being able to be adjusted in the depth expression video; and a feedback unit 15 that transmits information indicating a method for reducing blurring generated in the object area of the depth expression video to any one or more o

Abstract: There is provided an object tracking apparatus that realizes robust object detection and tracking even for movement fluctuation and observation noise, an object tracking method and a computer program. An object cracking apparatus 1 is an apparatus tracking an object in video, the object tracking apparatus 1 including: a deep learning discriminator 2 which is a discriminator by deep learning; and a particle filter function unit 3 tracking an object by applying a multi-channel feature value of video including feature values by the deep learning discriminator 2 to likelihood evaluation by a particle filter, according to a distance between position information about the multi-channel feature value and position information about each particle.

Abstract: A settlement system includes a service provider device 2 which transmits a template information transaction including a template of a transaction to a network 4 of a first blockchain, a user device which transmits, to the network 4 of the first blockchain, a payment information transaction that includes an electronic signature generated by using the template of the transaction and a payment amount, and a smart contract 41, wherein the smart contract 41 verifies the electronic signature by using the payment amount and the template of the transaction, the service provider device 2 generates a settlement transaction by using the template of the transaction, the electronic signature and the payment amount, and transmits the settlement transaction to a network 3 of a second blockchain, a plurality of output conditions are set to the template of the transaction, and the settlement transaction becomes usable when any one of the plurality of output conditions is satisfied.

Abstract: A blockchain is used to distribute a right to content data. A right holder terminal, an assignee terminal, and a blockchain control terminal stores a blockchain that is synchronized among the right holder terminal, the assignee terminal, and the blockchain control terminal. The blockchain includes a transaction set with a smart contract program for distributing the right. The blockchain control terminal includes a token issuance unit generating token data that includes match information for the content data and a type of right to be distributed, is set with an address of a right holder as owner information, and is identified by a token identifier, and registering the token data corresponding to the token identifier with the blockchain.

Abstract: A digital watermark is applied to a video to be distributed without re-encoding. A content distribution device 1 receives a content acquisition request to request video content, distributes the video content based on the content acquisition request, generates and distributes a watermark video with a watermark ID embedded, and causes watermark-video-related information including the watermark ID to be recorded, and a content playback device 2 transmits the content acquisition request, receives the video content and the watermark video, plays back and displays the video content, and superimposes the watermark video on the video content for playback and display.

Abstract: It is possible to inhibit deterioration of extraction precision of a subject and reliably extract the subject even when colors of the subject and a background are the same or similar. An image processing device 1 includes an input unit 11 configured to input a first invisible light image of only a background in which a subject is not included and a second invisible light image in which the subject and the background are included and a subject region extraction unit 15 configured to calculate a difference between a pixel value of each pixel of the second invisible light image and a pixel value of a corresponding pixel of the first invisible light image, determine whether the pixel is in a subject region or a background region in accordance with whether the difference is equal to or greater than a predetermined threshold, and extract the subject region from the second invisible light image.

Abstract: The present invention efficiently coordinates a plurality of blockchains. A settlement system, including: a service provider device 2 that transmits a template information transaction including a template of a transaction to a network 4 of a first blockchain; a user device that transmits a payment information transaction including a payment amount and an electronic signature which is generated by using the template of the transaction registered in the first blockchain; and a smart contract 41 included in the first blockchain, in which the smart contract 41 uses the payment amount and the template of the transaction to verify the electronic signature included in the payment information transaction, and the service provider device 2 uses the template of the transaction, the electronic signature, and the payment amount registered in the first blockchain to generate a settlement transaction and transmits the settlement transaction to a network 3 of a second blockchain.

Abstract: To identify and track a plurality of objects. An object tracking device 1 includes a frame acquisition unit 31 for acquiring one set of frame data 11 included in moving image data that captures a space where a plurality of objects are present; a distance acquisition unit 32 for acquiring measurement data 12 from measurement of three-dimensional coordinates of points configuring the objects in the space where the objects are present; an object position detection unit 33 for detecting a two-dimensional position of each of the objects from the frame data 11 on the basis of comparison with template data of each of the objects; an object distance detection unit 34 for detecting a plurality of three-dimensional positions of the objects from the measurement data 12; and an associating unit 35 for associating each two-dimensional position from the object position detection unit 33 with the nearest three-dimensional position among the three-dimensional positions from the object distance detection unit 34.

Abstract: Accurate and rapid identification can be performed even when feature vectors of input pixels and background pixels are close.

Abstract: There is provided an object tracking apparatus that realizes robust object detection and tracking even for movement fluctuation and observation noise, an object tracking method and a computer program. An object cracking apparatus 1 is an apparatus tracking an object in video, the object tracking apparatus 1 including: a deep learning discriminator 2 which is a discriminator by deep learning; and a particle filter function unit 3 tracking an object by applying a multi-channel feature value of video including feature values by the deep learning discriminator 2 to likelihood evaluation by a particle filter, according to a distance between position information about the multi-channel feature value and position information about each particle.

Abstract: An aerial image display device is capable of changing a depth of a virtual image viewed by an observer without changing a distance between at least one display device and an optical element forming the virtual image. The aerial image display device includes a display device, optical elements, and a reflecting member. The optical elements are installed corresponding to different display regions of a display surface of the display device and sequentially arranged along the display surface in an observation direction of an observer. The optical element is installed obliquely with an angle of about 45° in a ?X direction when viewed from the display surface of the display device. The optical element is installed obliquely with an angle of about 45° in an X direction when viewed from the display surface of the display device.

Abstract: An aerial image display device is capable of changing a depth of a virtual image viewed by an observer without changing a distance between at least one display device and an optical element forming the virtual image. The aerial image display device includes a display device, optical elements, and a reflecting member. The optical elements are installed corresponding to different display regions of a display surface of the display device and sequentially arranged along the display surface in an observation direction of an observer. The optical element is installed obliquely with an angle of about 45° in a ?X direction when viewed from the display surface of the display device. The optical element is installed obliquely with an angle of about 45° in an X direction when viewed from the display surface of the display device.

Abstract: A scheme to judge emphasized speech portions, wherein the judgment is executed by a statistical processing in terms of a set of speech parameters including a fundamental frequency, power and a temporal variation of a dynamic measure and/or their derivatives. The emphasized speech portions are used for clues to summarize an audio content or a video content with a speech.

Abstract: An audio feature is extracted from audio signal data for each analysis frame and stored in a storage part. Then, the audio feature is read from the storage part, and an emotional state probability of the audio feature corresponding to an emotional state is calculated using one or more statistical models constructed based on previously input learning audio signal data. Then, based on the calculated emotional state probability, the emotional state of a section including the analysis frame is determined.

Abstract: A scheme to judge emphasized speech portions, wherein the judgment is executed by a statistical processing in terms of a set of speech parameters including a fundamental frequency, power and a temporal variation of a dynamic measure and/or their derivatives. The emphasized speech portions are used for clues to summarize an audio content or a video content with a speech.