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: The described techniques relate to predicting object behavior based on top-down representations of an environment comprising top-down representations of image features in the environment. For example, a top-down representation may comprise a multi-channel image that includes semantic map information along with additional information for a target object and/or other objects in an environment. A top-down image feature representation may also be a multi-channel image that incorporates various tensors for different image features with channels of the multi-channel image, and may be generated directly from an input image. A prediction component can generate predictions of object behavior based at least in part on the top-down image feature representation, and in some cases, can generate predictions based on the top-down image feature representation together with the additional top-down representation.

Abstract: The embodiment of the present specification discloses an image synthesis method, apparatus and device for free-viewpoint.

Abstract: The present specification discloses a method, apparatus, and device for video frame interpolation.

Abstract: There is provided a detection panel, including: a substrate, gate lines, signal detection lines and pixels, a thin film transistor and an optical sensor are arranged in each pixel, the thin film transistor has a gate coupled with the corresponding gate line, a first electrode coupled with the corresponding signal detection line, and a second electrode coupled with a third electrode of the optical sensor in the same pixel; the pixels include at least one detecting pixel and at least one marking pixel, a first bias voltage line and a second bias voltage line are arranged on a side of the optical sensor away from the substrate, a fourth electrode of the optical sensor in the detecting pixel is coupled with the corresponding first bias voltage line, and the second electrode of the thin film transistor in the marking pixel is coupled with the corresponding second bias voltage line.

Abstract: A method and a device for MCMC framework-based sub-hypergraph matching are provided. Matching of object features is performed by constructing sub-hypergraphs. In a large number of actual images and videos, objects vary constantly, and contain various noise points as well as other interference factors, which makes image object matching and searching very difficult. Perform object feature matching by representing the appearance and positions of objects by sub-hypergraphs allows for faster and more accurate image matching. Furthermore, a sub-hypergraph has several advantages over a graph or a hypergraph: on one hand, a sub-hypergraph has more geometric information (e.g. angle transformation, rotation, scale, etc.) than a graph, and has a lower degree of difficulty and better extensibility than a hypergraph. On the other hand, the disclosed method and device have stronger capabilities to resist interference and good robustness, and are adaptable to more complex settings, especially with outliers.

Abstract: The present application provides methods, systems, devices and computer-readable mediums for encoding and decoding transform. A method of the present application comprises: performing transform-encoding on a prediction residual block separately using a plurality of transform matrices, to obtain transformed residual blocks; based on the transformed residual block, determining, by a rate-distortion optimization decision, a transform matrix or a combination of transform matrices matching the residual characteristics of the prediction residual block from the plurality of transform matrices, and determining a transformed residual block to be outputted in a bitstream. Compared with the prior art, the method of the embodiments of the present invention performs a residual transform using transform matrices that are more closely matched with the residual characteristic, thereby improving the expression of the residual signal and improving the coding efficiency of the residual block.

Abstract: The present disclosure provides a detection substrate, a manufacturing method thereof and a ray detector. The detection substrate includes: a base substrate; a plurality of independent first electrodes arranged on the base substrate on the same layer; a photoelectric conversion layer arranged on a whole face of sides, facing away from the base substrate, of the plurality of first electrodes; a ray absorption layer arranged on a side, facing away from the plurality of first electrodes, of the photoelectric conversion layer, wherein an orthographic projection of the ray absorption layer on the base substrate is overlapped with an orthographic projection of gaps between the first electrodes on the base substrate; and a second electrode arranged on a whole face of a side, facing away from the plurality of first electrodes, of the photoelectric conversion layer.

Abstract: The present application provides a method and a device of encoding and decoding based on free viewpoint, and relates to the technical field of video encoding. The method includes: generating a planar splicing image and splice information based on multiple single-viewpoint videos at a server side; generating a planar splicing video based on the planar splicing image; generating camera side information of the planar splicing video based on camera side information existing in the multiple single-viewpoint videos; and encoding the planar splicing video, the splice information and the camera side information of the planar splicing video to generate a planar splicing video bit stream, and decoding a planar splicing video bit stream to acquire a virtual viewpoint according to viewpoint information of a viewer at client side.

Abstract: The application discloses a method, system, device and computer-readable storage medium for inverse quantization, wherein, in some embodiments, determining an initial weighted inverse quantization matrix, wherein, the initial weighted inverse quantization matrix is the same as the quantized block in size; setting some matrix elements in the initial weighted inverse quantization matrix to zero to obtain a weighted inverse quantization matrix, wherein, determining the matrix elements that need to be zeroed according to the size of the quantized block; weighted inverse quantizing the quantized coefficients in the quantized block to generate corresponding inverse transform coefficients, wherein, the value of the matrix element corresponding to the position of the quantized coefficient in the weighted inverse quantization matrix is used as a weight coefficient of the weighted inverse quantization.

Abstract: Disclosed are a panoramic video asymmetrical mapping method and a corresponding inverse mapping method that include mapping a spherical surface corresponding to a panoramic image or video A onto a two-dimensional image or video B, projecting the spherical surface onto an isosceles quadrangular pyramid with a square bottom plane, and further projecting the isosceles quadrangular pyramid onto a planar surface, using isometric projection on a main viewpoint region in the projection and using a relatively high sampling density to ensure that the video quality of the region of the main viewpoint is high, while using a relatively low sample density for non-main viewpoint regions so as to reduce bit rate. The panoramic video asymmetrical inverse mapping technique provides a method for mapping from a planar surface to a spherical surface, and a planar surface video may be mapped back to a spherical surface for rendering and viewing.

Abstract: The present disclosure discloses an application method of silicon quantum dots (Si QDs) for controlling corn armyworm, belonging to the technical field of nano-agricultural technology for crop pest control. The method for controlling corn armyworm by using Si QDs of the present disclosure includes the following steps of: preparing the Si QDs into an aqueous solution of the Si QDs, and then applying the aqueous solution on the roots or leaves of plants as plant fertilizer; where the concentration of the aqueous solution of the Si QDs is 10-150 mg/L; the size of the Si QDs is 3-8 nm. The method of the present disclosure not only improves the effect of the conventional silicon fertilizer on the stress resistance of plants, but also directly improves the direct insecticidal effect of the nano-silicon and improves the chemical defense capability of plants; the optimal spraying amount of Si QDs is determined by spraying different concentrations of Si QDs in the growth and development experiment of armyworm.

Abstract: A trajectory estimate of a wheeled vehicle can be determined based at least in part on determining a wheel angle associated with the vehicle. In some examples, at least a portion of the image associated with the wheeled vehicle may be input into a machine-learned model that is trained to classify and/or regress wheel directions of wheeled vehicles. The machine-learned model may output a predicted wheel direction. The wheel direction and/or additional or historical sensor data may be used to estimate a trajectory of the wheeled vehicle. The predicted trajectory of the object can then be used to generate and refine an autonomous vehicle's trajectory as the autonomous vehicle proceeds through the environment.

Abstract: Techniques are discussed for determining prediction probabilities of an object based on a top-down representation of an environment. Data representing objects in an environment can be captured. Aspects of the environment can be represented as map data. A multi-channel image representing a top-down view of object(s) in the environment can be generated based on the data representing the objects and map data. The multi-channel image can be used to train a machine learned model by minimizing an error between predictions from the machine learned model and a captured trajectory associated with the object. Once trained, the machine learned model can be used to generate prediction probabilities of objects in an environment, and the vehicle can be controlled based on such prediction probabilities.

Abstract: Techniques are disclosed for updating map data. The techniques may include detecting a traffic light in a first image, determining, based at least in part on the traffic light detected in the first image, a proposed three-dimensional position of the traffic light in a three-dimensional coordinate system associated with map data. The proposed three-dimensional position may then be projected into a second image to determine a two-dimensional position of the traffic light in the second image and the second image may be annotated, as an annotated image, with a proposed traffic light location indicator associated with the traffic light. The techniques further include causing a display to display the annotated image to a user, receiving user input associated with the annotated images, and updating, as updated map data, the map data to include a position of the traffic light in the map data based at least in part on the user input.

Abstract: Techniques for determining predictions on a top-down representation of an environment based on object movement are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) may capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle, a pedestrian, a bicycle). A multi-channel image representing a top-down view of the object(s) and the environment may be generated based in part on the sensor data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) may also be encoded in the image. Multiple images may be generated representing the environment over time and input into a prediction system configured to output a trajectory template (e.g., general intent for future movement) and a predicted trajectory (e.g., more accurate predicted movement) associated with each object. The prediction system may include a machine learned model configured to output the trajectory template(s) and the predicted trajector(ies).

Abstract: The disclosure discloses an integrated riparian system for river/lake silt on-site treatment and application thereof, belonging to the technical field of silt treatment. The integrated riparian system includes three subsystems, namely a silt ecological treatment subsystem, a siphon drainage subsystem and a silt leachate advanced treatment subsystem. The silt ecological treatment subsystem is provided with plants, fillers, an aeration pipe and a water collection pipe from top to bottom, and a vent pipe is connected to the water collection pipe. A siphon in the siphon drainage subsystem is retractable and hump-shaped. The silt leachate advanced treatment subsystem includes a first-stage ecological treatment unit upflow wetland and a second-stage ecological treatment unit surface flow wetland.

Abstract: Embodiments of the present disclosure provide a method and device for selecting a context model of a quantized coefficient end flag. The method comprises: obtaining a scanning position POS of a non-zero coefficient corresponding to current quantized coefficient end flag in a specific scanning order; wherein the scanning position POS is a subscript of the non-zero coefficient in the scanning order; configuring a first context model array, and using a fixed value as the base to calculate the logarithmic value of the value of the scanning position POS plus 1, and according to the logarithmic value, selecting a first context model from the first context model array; and using the first context model to encode or decode a binary symbol of the current quantized coefficient end flag. According to the technical solution of the present application, it is able to improve encoding and decoding efficiency for a quantized coefficient end flag, thereby further improve the efficiency of video encoding and decoding.