Abstract: A learning method includes acquiring a learning image including an object, and correct information including a correct class a correct box; calculating an evaluation value for a learning model in accordance with a difference between the correct information and an object detection result that includes a detected class and a detected box and that is obtained by inputting the learning image to the learning model; and adjusting parameters of the learning model in accordance with the evaluation value, The calculating of the evaluation value includes performing at least one of processing for varying a weight that is assigned to each of differences of two or more positions or lengths between the correct box and the detected box, or processing for varying a weight that is assigned to a difference between the correct class and the detected class.

Abstract: A video signal shuffling device forms a segment with blocks having a given offset value in horizontal and vertical directions from a given starting point uniquely determined on the screen, the offset value being identical in every region. The segment is formed in a unit of one frame or two frames. The shuffling device divides one frame comprising blocks into a plurality of regions. A coding device determines a final priority as well as a final quantizer thereby quantizing a segment and providing the segment with a variable-length-coding based on a first priority, coding-quantity obtained from a plurality of quantizers, second priority and a quantizer. A coding device and its decoder, the coding device carries out a hierarchical coding by only a motion vector in a compressed stream at a lower resolution side and by agreeing a motion detected and a DCT block size with a size on the screen.

Abstract: A video signal layering-encoding system has at least either a frequency distribution unit to judge a frequency distribution in an input video signal or a motion judgment unit to judge the motion of an input video signal. With this, encoding quantity control according to the characteristics of the input video signal can be performed between layers. Also, with selection of encode modes and sharing of a motion vector, the encoded data of a bidirectionally predicted frame can be reduced and the encoding efficiency of a high resolution signal can be increased.

Abstract: A data editing system has a data transmitting-side unit including a camera shooting a video; a recorder recording the video shot onto a predetermined recording medium; and a transmitter compressing the video shot by the camera and transmitting the compresed video. The system also has a data editing-side unit including a receiver receiving the data transmitted from the data transmitting-side unit; editing instructions for performing the final editing of the video recorded on the recording medium by using the data received by the receiver; and a final editor performing the final editing of the video recorded on the recording medium based on the editing instruction.

Abstract: A data editing system has

Abstract: The present invention includes a motion vector detector for detecting motion vectors using a first image signal of high resolution; a resolution reducer for creating a second image signal of low resolution from the first image signal; an image signal interpolater for interpolating the second image signal so that it has the same number of pixels as the first image signal, thereby creating an interpolated signal; a differentiator for determining a differential between the first image signal and the interpolated signal; and an encoder for using the motion vectors to high-efficiency-encode the differential signal. Thus, by encoding two types of image signals of different resolutions, the present invention improves the accuracy of the motion vectors during the encoding of the high-resolution signal and reduces the rate after encoding due to the encoding of the differential signal.

Abstract: A video signal coding device is provided with unit dividing means (202) for dividing an input picture into units each of which is a coding quantity control unit consisting of one or a plurality of frames to be processed by any one of intra-frame coding, inter-frame forward coding, and inter-frame bidirectional coding; activity calculating means (203) for calculating a frame activity for every frame of the input picture, and calculating a unit activity for every unit from the frame activities of frames belonging to the same unit; target coding quantity deciding means (205) for deciding a target coding quantity of a coding frame on the basis of the frame activity of the coding frame which is a coding object, the unit activity of a coding unit to which the coding unit belongs, and the average unit activity of a unit prior to the coding unit; and coding means (206) for coding the coding frame by the target coding quantity so as to generate coded data.

Abstract: A video signal coding device is provided with unit dividing means (202) for dividing an input picture into units each of which is a coding quantity control unit consisting of one or a plurality of frames to be processed by any one of intra-frame coding, inter-frame forward coding, and inter-frame bi-directional coding; activity calculating means (203) for calculating a frame activity for every frame of the input picture, and calculating a unit activity for every unit from the frame activities of frames belonging to the same unit; target coding quantity deciding means (205) for deciding a target coding quantity of a coding frame on the basis of the fame activity of the coding frame which is a coding object, the unit activity of a coding unit to which the coding unit belongs, and the average unit activity of a unit prior to the coding unit; and coding means (206) for coding the coding frame by the target coding quantity so as to generate coded data.

Abstract: A video signal coding device is provided with unit dividing means (202) for dividing an input picture into units each of which is a coding quantity control unit consisting of one or a plurality of frames to be processed by any one of intra-frame coding, inter-frame forward coding, and inter-frame bidirectional coding; activity calculating means (203) for calculating a frame activity for every frame of the input picture, and calculating a unit activity for every unit from the frame activities of frames belonging to the same unit; target coding quantity deciding means (205) for deciding a target coding quantity of a coding frame on the basis of the frame activity of the coding frame which is a coding object, the unit activity of a coding unit to which the coding unit belongs, and the average unit activity of a unit prior to the coding unit; and coding means (206) for coding the coding frame by the target coding quantity so as to generate coded data.

Abstract: A video signal layering-encoding system according to the present invention has at least either a frequency distribution unit to judge a frequency distribution in an input video signal or a motion judgment unit to judge the motion of an input video signal. With this, encoding quantity control according to the characteristics of the input video signal can be performed between layers. Also, with selection of encode modes and sharing of a motion vector, the encoded data of a bidirectionally predicted frame can be reduced and the encoding efficiency of a high resolution signal can be increased. A digitial broadcast decoding system according to the present invention can readily display a plurality of broadcasting programs on different channels onto a small screen within a main screen when digital broadcasts are received, by a decoding method in which processing is easy, structurally simple circuitry, and software.

Abstract: A video signal coding apparatus comprises a divider 102 that divides an input digital video signal into an effective area and an additional area, an effective-area blocking device 103 for dividing the effective area into effective blocks, an effective-area encoder 104 that hight-efficiency-codes the effective blocks to create effective compressed blocks, an additional-area encoder 105 that hight-efficiency-codes the additional area to create additional compressed data, an additional-area blocking device 106 for dividing the additional compressed data into additional compressed blocks each a luminance signal for a plurality of pixels and at least one color difference signal for pixels arranged at the same position as the plurality of pixels, and a substitution device 107 that substitutes the additional compressed blocks for data in the same effective compressed blocks at predetermined positions.

Abstract: A video signal layering-encoding system according to the present invention has at least either a frequency distribution unit to judge a frequency distribution in an input video signal or a motion judgment unit to judge the motion of an input video signal. With this, encoding quantity control according to the characteristics of the input video signal can be performed between layers. Also, with selection of encode modes and sharing of a motion vector, the encoded data of a bidirectionally predicted frame can be reduced and the encoding efficiency of a high resolution signal can be increased.

Abstract: The ringing detector of the invention receives data representing pixel values of a plurality of pixels including: a remarked pixel; a number L (where L is a natural number) of neighboring pixels which are located in the vicinity of the remarked pixel; and a number M (where M is a natural number) of surrounding pixels which are more distant from the remarked pixel than the neighboring pixels are, thereby generating a ringing constant t indicating whether or not a ringing exists in the vicinity of the remarked pixel. The ringing detector includes: a pixel value variation detector for calculating a value x corresponding to a variation in the pixel values of the neighboring pixels; a distance detector for calculating a value y corresponding to a distance between the pixel values of the surrounding pixels and a barycenter of the pixel values of the remarked pixel and the neighboring pixels; and a ringing constant calculator for calculating the ringing constant t based on the values x and y.