Abstract: A method for video processing, comprising: parsing a first bitstream to determine a first quantized motion feature, wherein the first quantized motion feature is formed from first motion information of a luma current picture, wherein the first motion information is determined based on the luma current picture and first bi-directional predictive (B/P) pictures in a first group of pictures (GOP) based on first sets of reference pictures of the luma current picture; and decoding the first quantized motion feature to form a luma motion information by an MV decoder.

Abstract: A method for decoding is disclosed. A first image and a second image of a scene are received by a processor. The first image is downsampled and is different from the second image. A residual map is obtained according to the second image and the downsampled first image by the processor. The downsampled first image is upsampled by the processor. The first image is reconstructed based on the upsampled first image and the residual map by the processor.

Abstract: Methods and a decoder for video processing are provided. The method includes: a current picture is received; and a group of pictures associated with the current picture is determined. The group of pictures includes a first key picture at a first time prior to the current picture and a second key picture at a second time later than the current picture. The method includes: first and second reference pictures are generated based on the first and second key pictures. Based on the first and second reference pictures bi-directional predictive pictures in the group of pictures are determined. A motion estimation process based on the current picture and the bi-directional predictive pictures is then performed to generate motion information of the current picture.

Abstract: Provided in embodiments of the present disclosure are a media data processing method, an apparatus and a system. The method comprises: obtaining an optical signal of a sampling point by a collection device at the source end in an acquisition of media data; acquiring an optical signal intensity of the optical signal of the sampling point and a display brightness of a display device at destination end; determining an opto-electronic transfer control parameter according to the optical signal intensity of the optical signal of the sampling point and the display brightness; performing opto-electronic transfer on the optical signal of the sampling point according to the opto-electronic transfer control parameter to obtain a transferred electrical signal; and encoding the electrical signal and the opto-electronic transfer control parameter to obtain a bitstream.

Abstract: Several embodiments of the present invention are described for a media data processing method, apparatus and system. An example method comprises: obtaining an optical signal of a sampling point by a collection device at the source end in an acquisition of media data; according to an opto-electronic transfer control parameter, performing opto-electronic transfer for the optical signal of the sampling point to obtain a transferred electrical signal, wherein the opto-electronic transfer control parameter is determined on the basis of an optical signal intensity of the optical signal of the sampling point; and encoding the electrical signal and opto-electronic transfer control parameter to obtain a bitstream. According to the embodiment of the present invention, the problem of the lower accuracy in the media data processing is solved, thereby obtaining the effect of improving the accuracy in the media data processing.

Abstract: Several embodiments of the present invention are described for a media data processing method, apparatus and system. An example method comprises: obtaining an optical signal of a sampling point by a collection device at the source end in an acquisition of media data; according to an opto-electronic transfer control parameter, performing opto-electronic transfer for the optical signal of the sampling point to obtain a transferred electrical signal, wherein the opto-electronic transfer control parameter is determined on the basis of an optical signal intensity of the optical signal of the sampling point; and encoding the electrical signal and opto-electronic transfer control parameter to obtain a bitstream. According to the embodiment of the present invention, the problem of the lower accuracy in the media data processing is solved, thereby obtaining the effect of improving the accuracy in the media data processing.

Abstract: Provided are picture encoding and decoding methods and apparatuses, and a picture encoding and decoding system. The picture encoding method includes: determining an adjustment factor according to pixel sampling values of a video picture; converting the video picture according to the adjustment factor, and encoding the converted video picture; and writing the adjustment factor into a bitstream obtained by encoding the converted video picture.

Abstract: Provided are picture encoding and decoding methods and apparatuses, and a picture encoding and decoding system. The picture encoding method includes: determining an adjustment factor according to pixel sampling values of a video picture; converting the video picture according to the adjustment factor, and encoding the converted video picture; and writing the adjustment factor into a bitstream obtained by encoding the converted video picture.

Abstract: An image frame conversion method and a video frame conversion method and apparatus are provided. The video frame conversion method includes: extracting a longest line segment of a 2D video frame; determining a first depth image of the 2D video frame according to a direction of the longest line segment; determining motion information of the 2D video frame according to a video frame adjacent to the 2D video frame; determining a second depth image of the 2D video frame according to the motion information; and generating, according to the first depth image, the second depth image, and the 2D video frame, a 3D video frame corresponding to the 2D video frame.

Abstract: A virtual view generating method and apparatus are provided that are used to resolve a technical problem existing in the prior art that there are holes in a virtual view, so as to improve quality of the virtual view. The method includes obtaining an original image and an original depth map of the original image; preprocessing the original depth map based on an adaptive filtering algorithm to obtain a processed depth map; generating a basic virtual view based on the original image and the processed depth map; and performing hierarchical hole filling on the basic virtual view based on a deconvolution algorithm to generate a virtual view.

Abstract: An image frame conversion method and a video frame conversion method and apparatus are provided. The video frame conversion method includes: extracting a longest line segment of a 2D video frame; determining a first depth image of the 2D video frame according to a direction of the longest line segment; determining motion information of the 2D video frame according to a video frame adjacent to the 2D video frame; determining a second depth image of the 2D video frame according to the motion information; and generating, according to the first depth image, the second depth image, and the 2D video frame, a 3D video frame corresponding to the 2D video frame.

Abstract: A virtual view generating method and apparatus are provided that are used to resolve a technical problem existing in the prior art that there are holes in a virtual view, so as to improve quality of the virtual view. The method includes obtaining an original image and an original depth map of the original image; preprocessing the original depth map based on an adaptive filtering algorithm to obtain a processed depth map; generating a basic virtual view based on the original image and the processed depth map; and performing hierarchical hole filling on the basic virtual view based on a deconvolution algorithm to generate a virtual view.

Abstract: A method and apparatus for detecting text associated with video are provided. The method of detecting the text of the video includes reading a t-th frame (where t is a positive integer) among frames forming the video as a current frame, determining whether there is a text area detected from a previous frame which is a (t?N)-th (where N is a positive integer) frame among the frames forming the video, in the current frame, and upon determining that there is no text area detected from the previous frame in the current frame, detecting the text area in the entire current frame. Upon determining that there is the text area detected from the previous frame in the current frame, the text area is detected from a remaining area obtained by excluding from the current frame an area corresponding to the text area detected from the previous frame. Whether there is a text area in a next frame which is a (t+N)-th frame among the frames forming the video is verified.

Abstract: An apparatus and method for detecting a character region in an image. The apparatus includes a character candidate region detecting unit which detects a character candidate region from the image by detecting character strokes; and a character region checking unit which checks whether the detected character candidate region is the character region in response to the detected result of the character candidate region detecting unit.

Abstract: An apparatus for recognizing characters contained in an image includes: a character string segmentation unit segmenting character strings of the characters contained in the image into a variety of combinations; a character string determination unit determining the character string having a highest geometrical character goodness of fit and a highest character recognition grade among the character strings segmented into a variety of combinations; and a character string correction unit correcting the determined character string based on a language model. It is possible to effectively recognize characters even for character strings having a relatively thick font or a relatively narrow spacing between characters or containing special characters.

Abstract: A method and apparatus for summarizing a sports moving picture based on audio and image data contained in the moving picture of sports such as a football game are provided. The method includes: segmenting the sports moving picture into shots and extracting audio and image data of the segmented shots; calculating a level of importance for each of the shots based on the extracted audio and image data; and selecting important shots of the shots based on the calculated levels of importance of the shots and summarizing the moving picture based on the selected important shots. Accordingly, the sports moving picture are summarized by calculating levels of importance of shots in the sports moving picture based on extracted audio and image data and selecting important shots based on the calculated levels of importance, so that reliability of the summarized sports moving picture can increase and a user can generate a desired length of summarized sports moving picture.

Abstract: A method and apparatus for summarizing a moving picture of a sports game, such as a basketball game, based on scores. The method includes detecting score information of each shot of a moving picture of a sports game, calculating a degree of importance of each shot using the detected score information of each shot, and summarizing the moving picture using the calculated degree of importance of each shot. In the method, a moving picture of a sports game is summarized using degrees of importance of shots selected based on scores having important information regarding the sports game. Therefore, the reliability of summarization of the moving picture can be enhanced. Further, the amount of data calculation required for summarizing the moving picture can be reduced since the moving picture is summarized using changes in score information that has a small amount of data.

Abstract: An apparatus, medium, and method for extracting character(s) from an image. The apparatus includes a mask detector detecting a height of a mask indicating a character(s) region from spatial information of the image created when detecting a caption region including the character(s) region and a background region from the image and a character(s) extractor extracting character(s) from the character(s) region corresponding to the height of the mask. The spatial information includes an edge gradient of the image. Therefore, the apparatus extracts important information from an image and can recognize small character(s) that are not recognizable using conventional methods. In addition, an image can be more accurately identified, summarized, searched, and indexed according to its contents by recognizing extracted character(s). Further, the apparatus enables faster character(s) extraction.

Abstract: A method and apparatus for detecting text associated with video are provided. The method of detecting the text of the video includes reading a t-th frame (where t is a positive integer) among frames forming the video as a current frame, determining whether there is a text area detected from a previous frame which is a (t?N)-th (where N is a positive integer) frame among the frames forming the video, in the current frame, and upon determining that there is no text area detected from the previous frame in the current frame, detecting the text area in the entire current frame. Upon determining that there is the text area detected from the previous frame in the current frame, the text area is detected from a remaining area obtained by excluding from the current frame an area corresponding to the text area detected from the previous frame. Whether there is a text area in a next frame which is a (t+N)-th frame among the frames forming the video is verified.