4results about How to "High false positive rate" patented technology

The invention discloses an AI substitute inspection method and system based on multi-modal perception, and relates to the technical field of intelligent detection. According to the method, images, audios, environmental parameters and equipment state data of an inspection area are synchronously collected through a multi-modal sensor array, and after space-time alignment preprocessing, multi-modal features are extracted and input into a pre-trained fusion model to generate unified feature representation. The fusion model adopts a Transform architecture to realize cross-modal feature interaction, an anomaly detection algorithm is used to identify and classify anomalies, a confidence coefficient is calculated in combination with an evidence theory, and finally an inspection report containing anomaly positions, types and processing suggestions is generated. According to the invention, the information limitation of single-mode inspection is solved, the detection accuracy and robustness in a complex environment are improved, unmanned inspection in a high-risk scene is realized, the labor cost is reduced, the safety is guaranteed, and the method is suitable for automatic inspection in the fields of industrial equipment, public facilities and the like.

This invention belongs to the field of computer vision and image processing technology, and particularly relates to a query key-guided asymmetric feature enhancement system and method. The system includes: Q-ASFE modules embedded in the backbone network, specifically in the link where features are transmitted from the C3K2 module to the CBS module. The P2 and P3 layer feature maps output by the backbone network are processed by the neck network to output three feature fusion maps at different scales. These three feature fusion maps are then processed by a detection head to obtain the final detection result. This invention achieves efficient enhancement of image features through the organic integration of spatial detail awareness and global semantic guidance.

The application relates to a water conservancy embankment safety hidden danger digital management method, system, device and medium. The method comprises the following steps: reconstructing and expanding a space-time temperature field data matrix according to a natural day cycle through a sliding time window to obtain a third-order space-time temperature tensor; performing blind source separation iteration solving on the third-order space-time temperature tensor through adaptive robust tensor principal component analysis to obtain a low-rank environmental temperature field and an original sparse leakage temperature field; performing connected domain clustering and space-time consistency feature extraction on the sparse leakage temperature field to obtain candidate leakage events corresponding to each connected domain; performing spatial Gaussian fitting verification and time series autocorrelation verification screening on each candidate leakage event to obtain suspected leakage events, and performing leakage parameter quantitative estimation on each suspected leakage event to obtain safety hidden danger digital information. The method can adaptively match the embankment monitoring environment without external reference sensors, and can complete accurate identification and quantitative evaluation of leakage hidden dangers.

The application provides a kind of based on deep learning's marine converter station warm air professional three-way identification method, comprising the following steps: obtaining the dwg file of target warm air professional CAD drawing, constructs graph structure: graph data annotation based on prior knowledge: model training and topological feature learning based on graph neural network;To the graph structure that is well constructed, all subgraphs containing 3 lines are intercepted by sliding window, as the input of the trained graph neural network, the subgraph with confidence degree greater than or equal to threshold is screened and classified, and is determined as three-way, and the three-way area boundary box and the three interface center point coordinates are output.The application constructs graph structure with lines as nodes, directly models the core topological relationship of three-way, avoids the dependence of prior art on form details and pixel noise;By adjusting the angle range, distance threshold and other parameters, the warm air three-way of different specifications can be adapted, or migrated to other industrial pipeline components (such as four-way, elbow) identification scene, without reconstructing network architecture, reducing technical iteration cost.