Abstract: An object detecting device includes: an overall processing unit configured to perform object detection processing on an input image; an allocation processing unit configured to determine a segmented image for each frame which is subject to object detection among the plurality of segmented images in advance in a cycle of N frames, and reserve the determined segmented image; a selection processing unit configured to select and output, for each frame, some of the segmented images that are subject to object detection among the plurality of segmented images based on a reservation result from the allocation processing unit; a division processing unit configured to perform object detection processing on each of the segmented images output from the selection processing unit; and a synthesizing processing unit configured to synthesize an object detection result from the overall processing unit and an object detection result from the division processing unit.

Abstract: A first aspect of the present disclosure is a convolutional neural network inference processing device that performs processing in a convolutional neural network including a plurality of convolution layers and a residual layer that adds intermediate data related to the plurality of convolution layers as an addition target to a processing result by the plurality of convolution layers for each tile that is data obtained by dividing input data into a predetermined size, the convolutional neural network inference processing device including an inconsistency data storage unit that stores inconsistency data that is data at a portion where there is inconsistency between the processing result and the intermediate data, a past layer data storage unit that stores past layer data that is an addition target in a residual layer generated using inconsistency data related to the tile for which processing has been performed in a past and the intermediate data, and a processing unit that performs processing by the plurality o

Abstract: When an output feature map to be an output of convolution processing is output, the output feature map is output to a storage unit for each of divided small regions. When each small region is output to the storage unit, in a case where a feature included in the small region is the same as a predetermined feature or a feature of a small region output in the past, the predetermined feature or the feature of a small region output in the past is compressed and output to the storage unit.

Abstract: A coding method encodes an image by dividing the image into blocks, and comprises: dividing a coding target image into a plurality of coding unit blocks; determining whether or not to encode by dividing the coding unit block into a plurality of sub-coding unit blocks, on a basis of an edge direction and an edge strength of an edge obtained for each pixel in the coding unit block; and encoding, in a case of determining to divide the coding unit block into a plurality of sub-coding unit blocks in the determining step, a first sub-coding unit block by referencing a second sub-coding unit block inside the same coding unit block as the first sub-coding unit block.

Abstract: In a data processing device, a fixed-point position control unit determines, as first control. The fixed-point position control unit causes a detection calculation unit to perform calculation processing on processing target data at a processing point in time. The saturation rate control unit instructs, as second control to be repeated by the fixed-point position control unit, the fixed-point position control unit to move at least the fixed-point position as control to increase a lower limit saturation rate proportional to a magnitude of a counted lower limit counter value with respect to a result of the first control. The fixed-point position control unit performs, as the second control, a predetermined determination on the basis of the instruction from the saturation rate control unit and the metadata, determines the fixed-point position moved for each layer, and causes calculation processing to be performed.

Abstract: In a data processing device, a fixed-point position control unit determines, as first control. The fixed-point position control unit causes a detection calculation unit to perform calculation processing on processing target data at a processing point in time. The saturation rate control unit instructs, as second control to be repeated by the fixed-point position control unit, the fixed-point position control unit to move at least the fixed-point position as control to increase a lower limit saturation rate proportional to a magnitude of a counted lower limit counter value with respect to a result of the first control. The fixed-point position control unit performs, as the second control, a predetermined determination on the basis of the instruction from the saturation rate control unit and the metadata, determines the fixed-point position moved for each layer, and causes calculation processing to be performed.

Abstract: A calculation unit (22) sets each frame, of a moving image including a plurality of frames, as a target frame, calculates a motion vector with reference to a reference frame over an entirety of the target frames, and calculates an index indicating a magnitude of change between a key frame and the target frame, which is represented by using the motion vector, a judgement unit (25) judges whether or not the calculated index is equal to or greater than a predetermined threshold value, a first detection unit (27) detects a region indicating an object from the target frame by using an object detection model in a case in which the index is equal to greater than the threshold value, a second detection unit (28) detects a region on the target frame, which is obtained by correcting a position of a region detected in the reference frame by using the motion vector in a case in which the index is less than the threshold value, and an output unit (30) outputs information of the region detected by the first detection unit

Abstract: A video coding method is a video coding method for coding an image in units of blocks obtained by dividing an image, and in the method a computer performs processing for dividing the image into blocks, acquiring an intra-image prediction mode predicted for each block, and generating, by using a combination pattern based on the intra-image prediction mode of a plurality of blocks adjacent to at least any one block, determining whether or not the plurality of blocks are to be combined, and performing prediction for each combined block when it is determined that the plurality of blocks are to be combined.

Abstract: A reference region determination device is for determining a reference region to be stored in a reference image buffer, and includes: a motion vector acquisition portion configured to acquire a motion vector for each one of already encoded blocks; a position change amount derivation portion configured to derive a position change amount for the reference region based on the acquired motion vectors; and a reference region determination portion configured to determine a position of the reference region to be used in encoding of a next block for encoding after the already encoded blocks based on the position change amount.

Abstract: An object detection device 10 includes an entire processing unit 110 that obtains first metadata for the entire input image by scaling the input image and performing object detection processing, a divided image narrowing unit 120 that narrows down the input image into a predetermined number of selected divided images from a group of divided images obtained by dividing the input image, a division processing unit 130 that obtains second metadata by performing object detection processing for each of the selected divided images, and a synthesis processing unit 140 that removes the second metadata obtained by the division processing unit 130 that overlaps the first metadata obtained by the entire processing unit 110, and synthesizes the first metadata not removed and the first meta data obtained by the entire processing unit 110 to output the meta data.

Abstract: One aspect of the present invention is an operation circuit for performing a convolution operation of input feature map information supplied as a plurality of channels and coefficient information supplied as a plurality of channels, the operation circuit including a set including at least two channels of an output feature map based on output channels and at least three sub-operation circuits, wherein at least two sub-operation circuits are allocated for each set, the sub-operation circuits included in the set execute processing of a convolution operation of the coefficient information and the input feature map information included in the set, when a specific channel of the output feature map is a zero matrix, a sub-operation circuit that performs a convolution operation of the zero matrix executes processing of a convolution operation of the coefficient information and the input feature map information to be supplied next from a channel of the output feature map and a channel of the input feature map included

Abstract: The integration unit 26, using configuration information of the convolutional neural network model and each filter used in each convolutional layer of the convolutional neural network model as inputs, deletes one or more pieces of activation function processing performed between the plurality of convolutional layers and integrates a plurality of filters used in the plurality of convolutional layers.

Abstract: A coding method is a coding method executed by a coding apparatus. The coding method includes partitioning a first block having a predetermined size in an original image into a group of second blocks each being a block serving as a unit for coding, by quad tree, ternary tree, or binary tree, and predicting movement for each of the second blocks. The partitioning includes first sub-partitioning and second sub-partitioning, the first sub-partitioning includes partitioning the first block into blocks each having a size selected from sizes determined according to the quad tree, the ternary tree, or the binary tree, and the second sub-partitioning includes further partitioning the blocks each having the selected size to generate the second blocks.

Abstract: A coding method encodes an image by dividing the image into blocks, and comprises: dividing a coding target image into a plurality of coding unit blocks; determining whether or not to encode by dividing the coding unit block into a plurality of sub-coding unit blocks, on a basis of an edge direction and an edge strength of an edge obtained for each pixel in the coding unit block; and encoding, in a case of determining to divide the coding unit block into a plurality of sub-coding unit blocks in the determining step, a first sub-coding unit block by referencing a second sub-coding unit block inside the same coding unit block as the first sub-coding unit block.

Abstract: A coding device executes coding having divided an image into blocks, and includes: a candidate obtainment unit that obtains a plurality of provisional motion vector candidates in a coding target block; an evaluation information obtainment unit that obtains a correspondence vector that is a vector having a same direction and a same magnitude as a direction and a magnitude of the obtained provisional motion vector candidates, and evaluation information of a search center indicated by the correspondence vector in a coded block; and a selection unit that, on the basis of the evaluation information, selects, from the plurality of provisional motion vector candidates, a number of motion vector candidates that is lower than the number of the plurality of provisional motion vector candidates.

Abstract: A buffer device stores, in relation to a first area and a second area, which are partial areas respectively located on an identical line of an encoding target frame, and a third area, which is a partial area on the line below the identical line, reference image data for each search range of a reference frame that is referred to during motion search processing executed in order of the first area, the second area, and the third area, the buffer device including a memory for storing the reference image data, and a buffer control unit which, when the motion search processing is executed on the second area, executes control so that among the reference image data included in a first search range that is referred to during the motion search processing of the first area, the reference image data included in a third search range that is referred to during the motion search processing of the third area are left in the memory without being deleted.

Abstract: A reference region determination device is for determining a reference region to be stored in a reference image buffer, and includes: a motion vector acquisition portion configured to acquire a motion vector for each one of already encoded blocks; a position change amount derivation portion configured to derive a position change amount for the reference region based on the acquired motion vectors; and a reference region determination portion configured to determine a position of the reference region to be used in encoding of a next block for encoding after the already encoded blocks based on the position change amount.

Abstract: A coding device executes coding having divided an image into blocks, and includes: a candidate obtainment unit that obtains a plurality of provisional motion vector candidates in a coding target block; an evaluation information obtainment unit that obtains a correspondence vector that is a vector having a same direction and a same magnitude as a direction and a magnitude of the obtained provisional motion vector candidates, and evaluation information of a search center indicated by the correspondence vector in a coded block; and a selection unit that, on the basis of the evaluation information, selects, from the plurality of provisional motion vector candidates, a number of motion vector candidates that is lower than the number of the plurality of provisional motion vector candidates.

Abstract: A buffer device stores, in relation to a first area and a second area, which are partial areas respectively located on an identical line of an encoding target frame, and a third area, which is a partial area on the line below the identical line, reference image data for each search range of a reference frame that is referred to during motion search processing executed in order of the first area, the second area, and the third area, the buffer device including a memory for storing the reference image data, and a buffer control unit which, when the motion search processing is executed on the second area, executes control so that among the reference image data included in a first search range that is referred to during the motion search processing of the first area, the reference image data included in a third search range that is referred to during the motion search processing of the third area are left in the memory without being deleted.