Abstract: An image processing device according to an embodiment includes: a depth estimation unit that, when a size of a differential region between a first frame and a second frame at a timing later than a timing of the first frame in chronological order in a moving image satisfies a predetermined condition and is large, estimates a depth of at least a region corresponding to the differential region in the second frame; and a depth estimation result update unit that updates an estimation result of the depth of the first frame by using the region corresponding to the differential region to output the updated estimation result as a new estimation result of the depth of the second frame.

Abstract: An image processing device according to an embodiment includes: a frame determination unit that, when a size of a differential region between one frame and a frame after the frame in chronological order in a moving image satisfies a predetermined condition and is large, determines the one frame and the frame at a later timing as first and second frames serving as generation sources of functions used for mapping depths of the frames; a depth estimation unit that estimates a depth of each frame between the first and second frames; and a function generation unit that generates the function used for mapping the depth of the first frame as a function usable for mapping the depth of the each frame and generates the function used for mapping the depth of the second frame.

Abstract: A synchronous shift of video/audio data between a plurality of display system devices is suppressed. A synchronous control device includes a coded-data adjustment unit 312 or a video and audio data adjustment unit 314 configured to perform frame adjustment based on a predetermined frame adjustment instruction by inserting predetermined frame data into a plurality of pieces of frame data in a chronological order or deleting a piece of frame data from the plurality of pieces of frame data, a video and audio data output unit 315 configured to sequentially output each piece of frame data subjected to the frame adjustment, and a video and audio data output time-point adjustment unit 316 configured to compare a reference time point for outputting each piece of the frame data with an output time point at which each piece of the frame data is output.

Abstract: A control unit controls an image processing unit that executes different types of processing. The control unit includes: a monitoring unit that monitors buffers used by each of the different types of processing executed by the image processing unit in order to transfer a task and estimates a load on the image processing unit; and a change unit that changes a processing content of processing with a lower priority among the different types of processing executed by the image processing unit to processing with a smaller load in a case where the load on the image processing unit is larger than a first threshold.

Abstract: A processing apparatus 1 includes: an acquisition unit 21 that acquires a plurality of pieces of frame data captured simultaneously from a plurality of pieces of video data captured while parts of capturing regions are superimposed; a specification unit 22 that specifies a blend region which includes a pixel forming a seam line connecting the plurality of pieces of frame data and is provided in a direction in which the plurality of pieces of frame data overlap; and an output unit that outputs connected frame data FO in which each pixel of the blend region has a pixel value obtained by blending pixel values of the plurality of pieces of frame data, and the plurality of pieces of frame data are connected by the seam line. The specification unit 22 specifies, as the blend region, consecutive pixels that include a pixel forming a seam line and in which a luminance difference between corresponding pixels of the plurality of pieces of frame data is within a predetermined value.

Abstract: An accuracy improvement device 1 of the present embodiment includes: a painting processing unit 13 that generates a segmentation image obtained by painting each of a plurality of regions in an RGB image to be processed, with a designated color, on the basis of a segmentation result obtained by dividing the RGB image to be processed into the plurality of regions, and a smoothing processing unit 15 that uses the segmentation image as a guide image to execute edge retention smoothing processing on a depth map estimated from the RGB image to be processed.

Abstract: A synchronous control system is provided. A transmission device 1 includes a reception unit 11 that receives a control signal for a lighting device in a live event site and a transmission unit 13 that transmits, to a reception device in a live viewing site, the control signal to which an output time is appended. The output time is obtained by adding a predetermined period of time to a receipt time at which the control signal is received. A reception device 2 includes a reception unit 21 that receives the control signal to which the output time is appended, and an output control unit 13 that outputs the control signal to a lighting device 6 in the live viewing site at the output time, and allows the control of the lighting device 6 to synchronize with at least one of video and audio to be played in the live viewing site.

Abstract: A synchronous shift of video/audio data between a plurality of display system devices is suppressed. A synchronous control device includes a coded-data adjustment unit 312 or a video and audio data adjustment unit 314 configured to perform frame adjustment based on a predetermined frame adjustment instruction by inserting predetermined frame data into a plurality of pieces of frame data in a chronological order or deleting a piece of frame data from the plurality of pieces of frame data, a video and audio data output unit 315 configured to sequentially output each piece of frame data subjected to the frame adjustment, and a video and audio data output time-point adjustment unit 316 configured to compare a reference time point for outputting each piece of the frame data with an output time point at which each piece of the frame data is output.

Abstract: To more reliably control synchronous between pieces of video/audio data from a plurality of imaging system devices. A synchronous control unit 15 that synchronizes a plurality of pieces of video/audio data transmitted individually from a plurality of imaging system devices 2 includes a frame acquisition unit 151 configured to acquire a plurality of pieces of frame data from the pieces of video/audio data and assign a frame timestamp based on an acquisition time to each of the plurality of pieces of frame data, for each of the pieces of the video/audio data, and a frame shaping unit 152 configured to assign a new frame timestamp to the plurality of pieces of frame data based on a value of the frame timestamp so that start times of the plurality of pieces of frame data that are close in time among the plurality of pieces of video/audio data are equal to each other, and time intervals between the plurality of pieces of frame data are equal to each other.

Abstract: To suppress an unnatural movement of a moving object at a connection point when a plurality of pieces of video data are connected to each other. A frame acquisition unit 22 acquires pieces of frame data captured at the same time, from the pieces of video data input from cameras C1 and C2. A prohibited-region setting unit 24 sets a prohibited region that is not set as a calculation target when a seam is calculated, based on a position of an object detected in an overlap region between adjacent pieces of frame data and a movement direction of the object. A seam calculation unit 25 calculates a seam between pieces of frame data adjacent to each other, without setting a pixel included in the prohibited region as the calculation target of seam calculation. A connection-frame output unit 26 connects pieces of frame data in accordance with the seam and outputs connection frame data 15.

Abstract: Objects are tracked in real time in a composed video acquired by joining a plurality of videos. A grouping candidate determining unit 12 extracts objects present within an overlapping area, in which pieces of frame data are overlapped, among objects that have been detected and tracked in each of a plurality of pieces of frame data that were captured at the same time as candidate objects. A grouping unit 13 arranges a plurality of candidate objects of which a degree of overlapping is equal to or larger than a predetermined threshold as a group, and an integration unit 14 assigns integration object IDs to groups and objects that have not been grouped.

Abstract: Pop-up display information is created and displayed in a dynamic manner even without establishing settings in advance related to pop-up display for an anchor or an icon or the like, and implementing simple and efficient browsing by a user of linked contents by varying the display size in accordance with the display region. Mouse events of a mouse cursor upon a screen of an information device by the user are observed, and the fact that the mouse cursor has entered into a region of an object which has a linked destination is detected from the mouse events; a new window is displayed upon the screen; linked contents which are connected to the object are acquired; contents for presentation are created based upon the linked contents which have been acquired; and they are displayed within the new window which has been displayed upon the screen.

Abstract: Pop-up display information is created and displayed in a dynamic manner even without establishing settings in advance related to pop-up display for an anchor or an icon or the like, and implementing simple and efficient browsing by a user of linked contents by varying the display size in accordance with the display region. Mouse events of a mouse cursor upon a screen of an information device by the user are observed, and the fact that the mouse cursor has entered into a region of an object which has a linked destination is detected from the mouse events; a new window is displayed upon the screen; linked contents which are connected to the object are acquired; contents for presentation are created based upon the linked contents which have been acquired; and they are displayed within the new window which has been displayed upon the screen.