Abstract: An image processing apparatus has a processing circuit. The processing circuit functions as a three-dimensional data generation unit, a two-dimensional data generation unit, and a recognition image generation unit. The three-dimensional data generation unit generates three-dimensional data of an object ton the basis of an image of the object on which object information represented by a character or a symbol is attached, and a distance image indicating a distance between a reference position and the object for each pixel. The two-dimensional data generation unit flattens the three-dimensional data generated by the three-dimensional data generation unit to generate two-dimensional data. The recognition image generation unit generates a recognition image which is used to recognize the object information, on the basis of the two-dimensional data generated by two-dimensional data generation unit.

Abstract: An image processing apparatus has a processing circuit. The processing circuit functions as a three-dimensional data generation unit, a two-dimensional data generation unit, and a recognition image generation unit. The three-dimensional data generation unit generates three-dimensional data of an object ton the basis of an image of the object on which object information represented by a character or a symbol is attached, and a distance image indicating a distance between a reference position and the object for each pixel. The two-dimensional data generation unit flattens the three-dimensional data generated by the three-dimensional data generation unit to generate two-dimensional data. The recognition image generation unit generates a recognition image which is used to recognize the object information, on the basis of the two-dimensional data generated by two-dimensional data generation unit.

Abstract: According to an embodiment, an information processing device includes an input, a first storage, an acquirer, and a second storage. The input receives image data from an imager that captures, from a vehicle, an image of surroundings of the vehicle. The first storage stores, in correlation with each other, identification information for identifying a road structure contained in the image data for guiding the vehicle, and category information indicating a category of the road structure. The acquirer acquires location information representing a spot at which the vehicle is traveling. The second storage stores, in correlation with one another, the image data from which the road structure is detected based on the identification information stored in the first storage, the category information, and the location information indicating a spot at which the vehicle is traveling at the time of capturing the image data containing the road structure.

Abstract: An embodiment of a vehicle monitoring apparatus has a determiner and a reader. The determiner determines whether or not a specific site of a vehicle exists at least in an area of an image, the image imaged by an imager, the area being one of multiple areas into which the image is divided by dividing line that are substantially orthogonal to a direction of travel of the vehicle. The reader reads information on a license plate mounted to the vehicle from the area in case that the determiner determines the specific site of the vehicle is determined to exist in the area.

Abstract: An image processing system of an embodiment includes a first analyzer, an image processor, and a first scaler. The first analyzer is configured to analyze image data to generate an analysis result. The image processor is configured to perform image processing of the image data in accordance with the analysis result, to generate processed image data. The image processor includes a first image processor and a second image processor. The second image processor is configured to receive an output from the first image processor. The first scaler configured to determine whether the analysis result is usable with respect to the image data to be used by the second image processor after the first image processor performs the image processing, and to scale the analysis result to be used by the second image processor when the analysis result is not usable with respect to the image data to be used by the second image processor.

Abstract: An image processing apparatus is provided, which performs alignment of pixels on a reference frame and on a standard frame, executes an image reconfiguration based on an alignment result, and generates a high resolution image of a frame from low resolution images of the reference and the standard frames, the apparatus including a memory configured to store an input video and to output an image processed video; and a plurality of arithmetic processors configured to perform in parallel, at the time of the alignment, a first alignment processing in a first direction from the reference to the standard frame by a first arithmetic processor, and a second alignment processing in a second direction from the standard to the reference frame by a second arithmetic processor, the second direction being opposite to the first direction, processing results of the first and the second alignment processings being shared among the processors.

Abstract: An embodiment of a vehicle monitoring apparatus has a determiner and a reader. The determiner determines whether or not a specific site of a vehicle exists at least in an area of an image, the image imaged by an imager, the area being one of multiple areas into which the image is divided by dividing line that are substantially orthogonal to a direction of travel of the vehicle. The reader reads information on a license plate mounted to the vehicle from the area in case that the determiner determines the specific site of the vehicle is determined to exist in the area.

Abstract: A vehicle discrimination apparatus specifies a vehicle area in which a vehicle is photographed from an image including the vehicle and discriminates a vehicle passing through a road based on an image which a photographing device such as a camera installed at a side of the road or above the road photographs. The vehicle discrimination apparatus includes an image acquisition section, a first search window setting section, a feature amount calculation section, a likelihood calculation section, a vehicle area determination section, a template creation section, a template storage section, a tracking area setting section, a second search window setting section, a candidate area determination section, a selection section, and a detection section.

Abstract: According to one embodiment, an information processor divides input image data for a plurality of information processors so as to perform a super resolution process as a distributed processing. The super resolution process generates a high resolution image based on a plurality of low resolution input images. The information processor includes a division point determining unit, a division processor, and a combination processor. The division point determining unit determines a division point for an input image of a sequence of image frames. The division processor divides, for each of the information processors, the input image at the division point, and allocates each divided input image to each corresponding one of the information processors.

Abstract: An image processing apparatus of one embodiment executes a super-resolution processing which generate a high resolution image of a frame from low resolution images of a plurality of frames by performing alignment of pixels on a reference frame on a standard frame which is made to have high resolution and executing reconfiguration of an image based on a result of the aligning. The image processing apparatus includes a plurality of arithmetic processing units which can operate in parallel. When executing alignment between the standard frame and the reference frame, the plurality of arithmetic processing units operate in parallel a first alignment processing and a second alignment processing which are in the reverse relation to each other in terms of the relation of the standard and the reference, and the first alignment processing and the second alignment processing share their processing results mutually.

Abstract: A video data processing apparatus includes a reading unit reading video data from a video data file recorded on a randomly accessible storage medium in response to a first control signal, and reading position data indicating a frame position of the video data in the video data file from the video data file recorded on the storage medium in response to a second control signal, a memory storing the position data read by the reading unit, and a controller controlling the reading unit by outputting the second control signal before the outputting of the first control signal, and controlling the reading unit by outputting the first control signal with a designation of particular video data to be read indicated by the position data stored in the memory, in response to a request to execute a process to the video data file.

Abstract: According to one embodiment, an information processor divides input image data for a plurality of information processors so as to perform a super resolution process as a distributed processing. The super resolution process generates a high resolution image based on a plurality of low resolution input images. The information processor includes a division point determining unit, a division processor, and a combination processor. The division point determining unit determines a division point for an input image of a sequence of image frames. The division processor divides, for each of the information processors, the input image at the division point, and allocates each divided input image to each corresponding one of the information processors.

Abstract: An image processing apparatus of one embodiment executes a super-resolution processing which generate a high resolution image of a frame from low resolution images of a plurality of frames by performing alignment of pixels on a reference frame on a standard frame which is made to have high resolution and executing reconfiguration of an image based on a result of the aligning. The image processing apparatus includes a plurality of arithmetic processing units which can operate in parallel. When executing alignment between the standard frame and the reference frame, the plurality of arithmetic processing units operate in parallel a first alignment processing and a second alignment processing which are in the reverse relation to each other in terms of the relation of the standard and the reference, and the first alignment processing and the second alignment processing share their processing results mutually.

Abstract: According to one embodiment, an IP broadcast system includes a transmitting side and a receiving side connected to the transmitting side through a broadcast network on an IP network. The transmitting side includes a multiplexer which generates a standardized multiplex frame including at least a header field and an information field by multiplexing a plurality of RTP packets. The receiving side includes a buffer which temporarily holds the multiplex frame from the broadcast network and a program reproducer which retrieves and analyzes the multiplex frame from the buffer, extracts a reproduction clock shared by a plurality of programs, demultiplexes a plurality of TSs for each program from the multiplex frame, and based on the reproduction clock, reproduces the programs from each TS.

Abstract: A first prediction unit performs intra-prediction of an original image corresponding to an inter-frame coded frame to produce a first prediction residual and a prediction parameter. A second prediction unit performs intra-prediction of local decode data corresponding to the inter-frame coded data with the prediction parameter to produce a second prediction residual. A subtractor calculates difference data between the first prediction residual and the second prediction residual. A third prediction unit performs intra-prediction of data corresponding to a decoded frame with the prediction parameter to produce a third prediction residual, when the inter-frame coded data is decoded and transformed into the intra-frame coded data. An adder calculates addition data of the third prediction residual and the differential data. An intra-frame coding unit performs intra-frame coding to the addition data.

Abstract: A video data processor and a video data processing method which uses hardware resources efficiently even when a plurality of processing occurs to video data are performed in parallel is provided. The video data read from a recording medium in playback processing, editing processing, duplication processing, and other process that may be accomplished upon video is outputted to either of two lines by distributor 171. The video data that is outputted is temporarily held by input buffer 172-1, and decoded by decoder 173-1, and outputted to frame buffer 174-1. Frame buffer 174-1 and 174-2 are divided into a plurality of holding areas and these holding areas are dynamically assigned according to processing of playback processing, editing processing, or other processing that may be accomplished upon video. Thereby, the holding areas in frame buffer 174-1 and 174-2 can be used efficiently.

Abstract: A video data processing apparatus includes a reading unit reading video data from a video data file recorded on a randomly accessible storage medium in response to a first control signal, and reading position data indicating a frame position of the video data in the video data file from the video data file recorded on the storage medium in response to a second control signal, a memory storing the position data read by the reading unit, and a controller controlling the reading unit by outputting the second control signal before the outputting of the first control signal, and controlling the reading unit by outputting the first control signal with a designation of particular video data to be read indicated by the position data stored in the memory, in response to a request to execute a process to the video data file.

Abstract: A first prediction unit performs intra-prediction of an original image corresponding to an inter-frame coded frame to produce a first prediction residual and a prediction parameter. A second prediction unit performs intra-prediction of local decode data corresponding to the inter-frame coded data with the prediction parameter to produce a second prediction residual. A subtractor calculates difference data between the first prediction residual and the second prediction residual. A third prediction unit performs intra-prediction of data corresponding to a decoded frame with the prediction parameter to produce a third prediction residual, when the inter-frame coded data is decoded and transformed into the intra-frame coded data. An adder calculates addition data of the third prediction residual and the differential data. An intra-frame coding unit performs intra-frame coding to the addition data.

Abstract: According to one embodiment, an IP broadcast system includes a transmitting side and a receiving side connected to the transmitting side through a broadcast network on an IP network. The transmitting side includes a multiplexer which generates a standardized multiplex frame including at least a header field and an information field by multiplexing a plurality of RTP packets. The receiving side includes a buffer which temporarily holds the multiplex frame from the broadcast network and a program reproducer which retrieves and analyzes the multiplex frame from the buffer, extracts a reproduction clock shared by a plurality of programs, demultiplexes a plurality of TSs for each program from the multiplex frame, and based on the reproduction clock, reproduces the programs from each TS.