6results about How to "Quick and accurate extraction" patented technology

The invention discloses a three-dimensional grid model obtaining method and device and electronic equipment, and relates to the field of three-dimensional reconstruction, modeling is carried out on an acquired image of a to-be-modeled object through a Gaussian splashing algorithm, after an initial Gaussian point cloud model is obtained, requirements are formed on the basis of initial attribute characteristics of each initial Gaussian ellipsoid and a three-dimensional grid model, and a three-dimensional grid model is obtained. And performing point cloud processing on the initial Gaussian point cloud model to obtain a to-be-determined point cloud model with a three-dimensional gridding characteristic, then performing reconstruction through a Gaussian splash algorithm on the basis to obtain a target Gaussian point cloud model meeting a transparency constraint condition, and rapidly and accurately extracting a three-dimensional mesh patch from the target Gaussian point cloud model. Therefore, the three-dimensional grid model which is complete in structure and accurate in surface feature is formed, further manual modification by technicians is not needed, the obtaining efficiency and quality of the three-dimensional grid model are improved, and the requirement of downstream application for a high-quality three-dimensional model is reliably met.

The invention provides a paper quality detection method and system, and relates to the technical field of defect detection, the paper quality detection method is based on a YOLOV8 model, and the method comprises the steps: carrying out the feature extraction operation of a to-be-detected paper image according to a shallow network feature extraction module, and obtaining an initial feature map; when the deep network feature extraction module performs down-sampling operation on the initial feature map, the initial feature map is divided into a plurality of feature regions, and a weight is divided for each feature region through the adaptive weight down-sampling module, so that a weighted feature map is generated; reversely transmitting the weighted feature map to a shallow network feature extraction module through a reversible feature fusion module to obtain a fused weighted feature map; and determining defect information of the to-be-detected paper image through a deep network feature extraction module according to the fused weighted feature map. According to the invention, the defects on the paper can be identified and classified more accurately, and paper defect detection with higher precision and higher efficiency is realized.

The application relates to an orchard robot binocular vision inertial positioning method, device, equipment and medium, which comprises the following steps: screening the line features based on a preset line feature length screening algorithm to determine the line features with a preset length threshold, adopting a preset line feature matching screening algorithm to match the front and rear frames of the orchard images of the left eye or the right eye according to the line features with the preset length threshold to determine the line feature matching pairs, extracting the key frames of the orchard images according to the point feature matching pairs and the line feature matching pairs to determine the key frames in the orchard images, performing triangulation processing on the line features of the key frames to construct line feature re-projection residuals, fusing the line feature re-projection residuals with the cost functions of the prior residuals, IMU residuals and point feature re-projection residuals to minimize the cost functions, and completing the binocular vision inertial positioning of the orchard robot. The application significantly improves the positioning accuracy of the orchard robot.

The invention discloses a method and a device for acquiring secondary technical application data of an electrician. The method comprises the following steps of: extracting cable plate information, cable number head information and graphic information in a CAD drawing through a software library; identifying a target cable plate and a target drawing name corresponding to a target keyword in the cable plate information through the target keyword; obtaining a cable plate document according to the target cable plate and the target drawing name; extracting a table graph in the graph information, and determining coordinates of each data grid in the table graph; matching the coordinate of a target text in the cable head number information with the coordinate of each data grid to obtain the data grid to which each target text belongs; and obtaining a row-column relationship and a column attribute of each target text, and obtaining a secondary cable header document according to the row-column relationship and the column attribute of the target text. The data in the secondary technical application CAD drawing of the electrician can be quickly and accurately obtained, and the corresponding document can be generated.

The invention relates to the technical field of power distribution, in particular to a mountain area power distribution network grid division method considering disaster scene characteristics and a related device, and the method comprises the steps: obtaining map information of a target area; performing preliminary division on the map information of the target area by adopting a U-Net neural network to obtain a plurality of land parcels; obtaining road lattice characteristics of each land parcel, and quantifying the road lattice characteristics; according to the quantized road lattice features, an MST is generated by applying a graph theory; clustering the MST by using a Chameleon clustering method to obtain a refined grid, and completing the grid division of the power distribution network in the mountainous area; according to the method, efficient management of the mountain area power distribution network can be realized, the grid division condition under the extreme weather condition is clear, and disaster risks and power demands of different land parcels can be evaluated more accurately. The problems that in the prior art, due to the fact that influences of power equipment operation information, disaster scene characteristics and the like are not considered in power distribution grid division, grid division is not clear, and a reliable basis cannot be provided for operators are solved.

The invention relates to the technical field of deep learning, and in particular to an AI-based binary homology sample analysis method; the method comprises reading file content, identifying a shell type, and then performing shell removal processing to obtain an original data file; disassembling the shelled original data file; converting assembly instruction codes into intermediate codes, and a natural language large model converting the intermediate codes into high-level languages ​​for malicious code feature marking to produce a malicious sample data set; preprocessing some malicious samples, and then performing label encoding; constructing an LSTM model capable of enhancing malicious sample feature extraction and detection capabilities, and inputting some processed malicious samples into the LSTM model for training; and inputting the preprocessed new malicious samples into the trained LSTM model to obtain a final result; the advantages of the invention are that feature relations in a language can be extracted more quickly, and the effect of performing family classification on malicious samples can be significantly improved.