Abstract: A method for image matching includes acquiring a template image and a target image; acquiring a group of template features according to the template image; extracting a group of target features according to the target image; and according to template features and target features, calculating an degree of image similarity between the template image and each frame of target images, and using a target image with the maximum degree of image similarity as a matched image to the template image. In the image-matching method, image matching is performed by calculating an degree of image similarity between a template image and each target image according to a degree of image similarity between template features and target features, so that non-redundancy of features in an image matching process and correct image matching can be guaranteed, and the image matching accuracy can be improved.

Abstract: Disclosed are a describing method and a coding method of panoramic video ROIs based on multiple layers of spherical circumferences. The describing method comprises: first setting a center of the panoramic video ROIs; then setting the number of layers of ROIs as N; obtaining the size Rn of the current layer ROI based on a radius or angle; obtaining the sizes of all of the N layers of ROIs, and writing information such as the center of the ROIs, the number of layers, and the size of each layer into a sequence header of a code stream. The coding method comprises adjusting or filtering an initial QP based on a QP adjusted value and then coding an image. By flexibly assigning code rates to multiple layers of panoramic video ROIs, while guaranteeing a relatively high image quality of ROIs, the code rate needed for coding and transmission is greatly reduced.

Abstract: Disclosed is a panoramic image mapping method, wherein mapping regions and a non-mapping region are partitioned for an equirectangular panoramic image with a resolution of 2M×M, where only the partitioned mapping regions are mapped as square regions; the method comprises:, computing a vertical distance and a horizontal distance from a point on the square region to a center of the square region, a larger one of which being denoted as m; computing a distance n from the point to a zeroth (0th) point on a concentric square region; computing a longitude and a latitude corresponding to the point; computing a corresponding position (X, Y) in the equirectangular panoramic image to which the point is mapped; and then assigning a value to the point. The method may effectively reduce oversampling, thereby effectively reducing the number of pixels of the panoramic image and the code rate required for coding with little distortion.

Abstract: Disclosed is a method for detecting pedestrians in an image by using Gaussian penalty. Initial pedestrian boundary box is screened using a Gaussian penalty, to improve the pedestrian detection performance, especially sheltered pedestrians in an image. The method includes acquiring a training data set, a test data set and pedestrian labels of a pedestrian detection image; using the training data set for training to obtain a detection model by using a pedestrian detection method, and acquiring initial pedestrian boundary box and confidence degrees and coordinates thereof; performing Gaussian penalty on the confidence degrees of the pedestrian boundary box, to obtain confidence degree of the pedestrian boundary box after the penalty; and obtaining final pedestrian boundary boxes by screening the pedestrian boundary boxes. Thus, repeated boundary boxes of a single pedestrian are removed while reserving boundary boxes of sheltered pedestrians, thereby realizing the detection of the pedestrians in an image.

Abstract: The present disclosure provides an encoding method, a decoding method, an encoder, and a decoder, the encoding method comprises: performing interframe prediction to each interframe coded block to obtain corresponding interframe predicted blocks; writing information of each of the interframe predicted blocks into a code stream; if the interframe coded block exists at an adjacent position to the right or beneath or to the lower right of the intraframe coded block, performing intraframe prediction to the intraframe coded block based on at least one reconstructed coded blocks at adjacent positions to the left and/or above and/or to the upper left of the intraframe coded block and at least one of the interframe coded blocks at adjacent positions to the right and/or beneath and/or to the lower right of the intraframe coded block to obtain intraframe predicted blocks; writing information of each of the intraframe predicted blocks into the code stream.

Abstract: Disclosed is a hierarchical division-based point cloud attribute compression method. For point cloud attribute information, a new hierarchical division based coding scheme is proposed, wherein a frame of point cloud is adaptively divided into a “stripe-macroblock-block” hierarchical structure according to the spatial position and color distribution of the point cloud, and stripes are coded independently from one another, increasing the coding efficiency, enhancing the fault tolerance of a system and improving the performance of point cloud attribute compression. The method comprises: (1) inputting a point cloud; (2) division of a k-dimension (KD) tree structure of the point cloud; (3) continuity analysis of point cloud attribute information; (4) stripe division of the point cloud; (5) division of macroblocks and coding blocks of the point cloud; and (6) intra-frame prediction, transformation, quantification and entropy coding based on a block structure.

Abstract: Disclosed are a panoramic video forward mapping method and a panoramic video inverse mapping method, which relates to the field of virtual reality (VR) videos. In the present disclosure, the forward mapping method comprises: mapping, based on a main viewpoint, the Areas I, II, and III on the sphere onto corresponding areas on the plane, wherein Area I corresponds to the area with the included angle 0°˜Z1, the Area II corresponds to the area with the included angle Z1˜Z2, and the Area III corresponds to the area with the included angle Z2˜180°. The panoramic video forward mapping method refers to mapping a spherical source corresponding to the panoramic image A onto a plane square image B; the panoramic video inverse mapping method refers to mapping the plane square image B back to the sphere for being rendered and viewed.

Abstract: Embodiments of the present disclosure provide a method for accelerating CDVS extraction process based on a GPGPU platform, wherein for the stages of feature detection and local descriptor computation of the CDVS extraction process, operation logics and parallelism strategies of respective inter-pixel parallelism sub-procedures and respective inter-feature point parallelism sub-procedures are implemented by leveraging an OpenCL general-purpose parallelism programming framework, and acceleration is achieved by leveraging a GPU's parallelism computation capability; including: partitioning computing tasks for a GPU and a CPU; reconstructing an image scale pyramid storage model; assigning parallelism strategies to respective sub-procedures for the GPU; and applying local memory to mitigate the access bottleneck. The technical solution of the present disclosure may accelerate the CDVS extraction process and significantly enhances the extraction performance.

Abstract: Disclosed is a multi-angle adaptive intra-frame prediction-based point cloud attribute compression method. A novel block structure-based intra-frame prediction scheme is provided for point cloud attribute information, where six prediction modes are provided to reduce information redundancy among different coding blocks and improve the point cloud attribute compression performance. The method comprises: (1) inputting a point cloud; (2) performing point cloud attribute color space conversion; (3) dividing a point cloud by using a K-dimensional (KD) tree to obtain coding blocks; (4) performing block structure-based multi-angle adaptive intra-frame prediction; (5) performing intra-frame prediction mode decision; and (6) performing conversion, uniform quantization, and entropy encoding.

Abstract: Method and device for deblurring an out-of-focus blurred image: first, a preset blur kernel is used to carry out blurring processing on an original image to obtain a re-blurred image. Blur amounts of pixels in an edge area of the original image are estimated according to the change of the image edge information in the blurring processing to obtain a sparse blur amount diagram. Blur amounts of pixels in a non-edge area of the original image are estimated according to the sparse blur amount diagram to obtain a complete blur amount diagram. Deblurring processing is carried out according to the complete blur amount diagram to obtain a deblurred image. In the method and device provided, since a blur amount diagram is obtained based on the change of edge information after image blurring, the blur amount diagram can be more accurate, so that the quality of a deblurred image is improved.

Abstract: Disclosed is a virtual viewpoint synthesis method based on image local segmentation, which relates to the digital image processing technology.

Abstract: Disclosed is a panoramic image mapping method and a corresponding reversely mapping method. Particularly, the mapping process includes mapping a panoramic image or a spherical surface corresponding to Video A: first, dividing the spherical surface into three areas based on the latitudes of the spherical surface, denoted as Area I, Area II, and Area III, respectively; mapping the three areas to a square plane I?, a rectangular plane II?, and a square plane III?, respectively; then, splicing the planes I?, II? and III? into a plane, wherein the resulting plane is the two-dimensional image or video B. Compared with the equirectangular mapping method, the method according to the present disclosure may effectively ameliorate oversampling in high-latitude areas and effectively lower the bit rate needed by coding and the complexity of decoding. The present disclosure relates to the field of virtual reality, which may be applied to panoramic images and videos.

Abstract: A Collaborative Deep Network model method for pedestrian detection includes constructing a new collaborative multi-model learning framework to complete a classification process during pedestrian detection; and using an artificial neuron network to integrate judgment results of sub-classifiers in a collaborative model, and training the network by means of the method for machine learning, so that information fed back by sub-classifiers can be more effectively synthesized. A re-sampling method based on a K-means clustering algorithm can enhance the classification effect of each classifier in the collaborative model, and thus improves the overall classification effect.

Abstract: Disclosed are a panoramic image mapping method, apparatus, and device. The method comprises: obtaining a to-be-mapped panoramic image; splitting the to-be-mapped panoramic image into three areas according to a first latitude and a second latitude, wherein the area corresponding to a latitude range from ?90° to the first latitude is referred to as a first area, the area corresponding to a latitude range from the first latitude to the second latitude is referred to as a second area, and the area corresponding to a latitude range from the second latitude to 90° is referred to as a third area; mapping the first area to a first target image according to a first mapping method; mapping the second area to the second target image according to a second mapping method; mapping the third area to a third target image according to a third mapping method, and splicing the first target image, the second target image, and the third target image to obtain a two-dimensional plane image.

Abstract: A video action detection method based on a convolutional neural network (CNN) is disclosed in the field of computer vision recognition technologies. A temporal-spatial pyramid pooling layer is added to a network structure, which eliminates limitations on input by a network, speeds up training and detection, and improves performance of video action classification and time location. The disclosed convolutional neural network includes a convolutional layer, a common pooling layer, a temporal-spatial pyramid pooling layer and a full connection layer. The outputs of the convolutional neural network include a category classification output layer and a time localization calculation result output layer. The disclosed method does not require down-sampling to obtain video clips of different durations, but instead utilizes direct input of the whole video at once, improving efficiency.

Abstract: A method and system for video frame interpolation based on an optical flow method is disclosed. The process includes calculating bidirectional motion vectors between two adjacent frames in a frame sequence of input video by using the optical flow method, judging reliabilities of the bidirectional motion vectors between the two adjacent frames, and processing a jagged problem and a noise problem in the optical flow method; marking “shielding” and “exposure” regions in the two adjacent frames, and updating an unreliable motion vector; with regard to the two adjacent frames, according to marking information about the “shielding” and “exposure” regions and the bidirectional motion vector field, mapping front and back frames to an interpolated frame to obtain a forward interpolated frame and a backward interpolated frame; synthesizing the forward interpolated frame and the backward interpolated frame into the interpolated frame; repairing a hole point in the interpolated frame to obtain a final interpolated frame.

Abstract: A system for controlling configuration settings for mobile data communication devices and services includes a redirection server and a policy generation system. The redirection server detects a triggering event in a host system and in response to the triggering event continuously redirects data items from the host system to a wireless network. Each mobile data communication device receives data items from the wireless network and includes a device configuration stored in a memory location on the mobile data communication device. The device configuration of each mobile data communication device controls one or more functions of the mobile data communication device. The policy generation system receives a policy setting from a user interface and stores the policy setting in a user information record associated with a mobile data communication device.

Abstract: The present disclosure provides an encoding method, a decoding method, an encoder, and a decoder, the encoding method comprises: performing interframe prediction to each interframe coded block to obtain corresponding interframe predicted blocks; writing information of each of the interframe predicted blocks into a code stream; if the interframe coded block exists at an adjacent position to the right or beneath or to the lower right of the intraframe coded block, performing intraframe prediction to the intraframe coded block based on at least one reconstructed coded blocks at adjacent positions to the left and/or above and/or to the upper left of the intraframe coded block and at least one of the interframe coded blocks at adjacent positions to the right and/or beneath and/or to the lower right of the intraframe coded block to obtain intraframe predicted blocks; writing information of each of the intraframe predicted blocks into the code stream.

Abstract: Disclosed are a method, apparatus, and device for synthesizing virtual viewpoint images.

Abstract: The present disclosure provides an encoding method, a decoding method, an encoder, and a decoder, the encoding method comprises: performing interframe prediction to each interframe coded block to obtain corresponding interframe predicted blocks; writing information of each of the interframe predicted blocks into a code stream; if the interframe coded block exists at an adjacent position to the right or beneath or to the lower right of the intraframe coded block, performing intraframe prediction to the intraframe coded block based on at least one reconstructed coded blocks at adjacent positions to the left and/or above and/or to the upper left of the intraframe coded block and at least one of the interframe coded blocks at adjacent positions to the right and/or beneath and/or to the lower right of the intraframe coded block to obtain intraframe predicted blocks; writing information of each of the intraframe predicted blocks into the code stream.