42results about How to "Reduce computational redundancy" patented technology

The invention discloses an improved Multi-RRT path planning method and an AGV trolley based on fusion prediction. The invention generates a real-time optimal path instruction by improving the multi-objective path planning algorithm of Multi-RRT and sparse matrix, and at the same time sends the operation instruction to Intelligent logistics vehicles are executed by intelligent logistics vehicles. The present invention can be applied to multi-robot multi-object point collaborative work path planning scenarios such as intelligent logistics storage or intelligent factories. While retaining the randomness of path selection, it can speed up the convergence of the algorithm, especially suitable for scenarios with multiple sensor nodes in large open environments.

The embodiment of the present application discloses a video processing method, device, equipment, and storage medium. The video processing method involves technologies such as artificial intelligence, cloud computing, computer vision, and machine learning. The video processing method includes: acquiring the target video to be processed ; Extract a frame sequence from the target video, the frame sequence includes N tested video frames, and N is an integer greater than 1; call the watermark detection model to perform watermark detection on the frame sequence, and obtain the watermark indication of each tested video frame; from N M watermark indications are selected from the watermark indications for time-domain joint discrimination processing to obtain watermark data of the target video, where M is an integer greater than 1 and M≤N. By adopting the embodiment of the present application, the time-domain multi-frame joint detection can be performed on the frame sequence of the target video, effectively reducing calculation redundancy, improving the efficiency of video watermark detection, and improving the accuracy of video watermark detection results.

The invention discloses a SAR echo fast time-domain generation method. By merging all point targets included in the area target step by step, each group of point targets combined is replaced by a virtual point target at each level, and time-domain superposition is used. The method generates the first level of echoes. As the point targets are merged step by step, the sub-echoes generated by each level gradually become finer and denser. Finally, when the number of echo data azimuth sampling points reaches the same number as the number of azimuth sampling points, the combination is terminated. , superimposing the last level of sub-echoes to obtain a complete echo. Compared with the existing time-domain superposition method, the method of the present invention does not need to traverse azimuth-by-azimuth sampling points and point-by-point targets, reduces the calculation redundancy of echo generation, greatly reduces the amount of calculation, and is suitable for any mode of SAR system, especially for The echo generation of the target in a large scene is easy to introduce platform motion error.

The invention discloses a coding distributed computation method, a coding distributed computation apparatus, a coding distributed computation device based on edge computation environment, and a computer readable storage medium. The method comprises the following steps: acquiring network parameters of an edge computation network; obtaining a computation task arrangement scheme based on the networkparameter; performing coding distributed computation to obtain a coding scheme of data migration in the edge computation network; determining any one participated node as a target node, determining acomputation task of a corresponding median of any one output function as a special computation task when the any one output function on the target node and corresponding input data both are located onthe target node, and the other participated nodes, except for the target node, do not have such any output function, determining the special computation task of the other participated nodes, except for the target node, as an abnormal computation task, and deleting the abnormal computation task in the computation task arrangement scheme; and realizing edge computation based on the coding scheme and the computation task arrangement scheme. With the method, the apparatus and the device provided by the invention, computation redundancy is reduced greatly, and network computation resource is saved.

The invention relates to a system and a method for supporting the computation migration of multiple embedded devices. The system comprises a computer, a coding machine and the embedded devices, wherein virtual machines corresponding to the embedded devices are arranged in the computer; the coding machine is connected with the computer and is used for receiving video images and audio data from the computer, performing concurrent compression coding and sending the video images and audio data subjected to the concurrent compression coding to the embedded devices; and the embedded devices are used for receiving the data sent by the coding machine and transmitting an interactive service instruction to the computer. The method comprises the following steps that: the embedded devices request for a service; the computer provides an interactive service; the coding machine performs concurrent compression coding on the video images and audio data sent from the computer and distributes the video images and audio data subjected to the concurrent compression coding to the embedded devices; and the embedded devices receive the data subjected to the compression coding by the coding machine and acquire the video images and sound of the requested service. The system and the method have the advantages of simple and compact structure, low cost, simple and convenient operation, simple principle, high processing capacity, small delay, high concurrent access capacity, low requirement on network bandwidth in the transmission process, and the like.

The invention relates to a texture generation method based on a streamline growth method, which belongs to the field of scientific computing visualization. This method first uses the scanning line point positioning method to perform point positioning and interpolation on each pixel in the vector field; then uses the streamline growth method to generate the static streamline texture of each frame; and then uses the particle trajectory method to generate the current frame trace. Line texture: Finally, the streamline texture of each frame obtained by the streamline growth method and the trace texture generated by the particle trajectory method are synthesized to obtain the output texture of each frame, and each frame is played in a loop to obtain the final dynamic texture animation. The method of the invention can greatly improve the calculation efficiency and precision, has excellent vector field expression ability and strong flexibility, and is suitable for popularization and application.

The invention discloses an image processing method, device, equipment and a readable storage medium. The image processing method includes: receiving an image to be processed, and performing region division processing on the image to be processed to obtain each region of interest; calling a pre-stored full convolutional network structure model to detect each region of interest to obtain each region of interest. A probabilistic image segment, wherein the pre-stored fully convolutional network structure model includes a fully convolutional structure that replaces a linear regression layer with an equivalent convolutional layer, and the pre-stored fully convolutional network structure model removes the full-volume The blank filling operation layer and the up-sampling layer in the product structure; performing synthesis processing on each probability image segment to obtain the target probability image. The invention solves the technical problem of high calculation redundancy in the high-density prediction process of the existing pathological images, resulting in low processing efficiency of the pathological images.