1759 results about "Region detection" patented technology

The invention discloses a flight path planning method and system for multi-unmanned aerial vehicle cooperative routing inspection of a distribution network line, and relates to the technical field of unmanned aerial vehicle flight path planning, and the method comprises the steps: carrying out the point cloud data collection based on an unmanned aerial vehicle, and carrying out the data denoising sampling; adaptive clustering is carried out according to the reflection intensity of the sampling data, position codes are introduced to describe point coordinate information, point cloud vectors are constructed, and label classification is carried out on point clouds; and fitting the quadratic curve equation based on the power line label point cloud to obtain a power line model. According to the method, through combination of an adaptive clustering method and a mean shift algorithm, interval division of point cloud reflection intensity is more adaptive, initialization of a clustering center is ensured to be based on data distribution characteristics, through combination of RANSAC fitting, power line point cloud classification and cross region detection, modeling of the power line point cloud is more accurate, and the accuracy of power line point cloud modeling is improved. Meanwhile, tracks of different power lines are clear and separable, and misjudgment of line intersection areas is reduced.

The invention discloses a bridge disease detection method and system based on an improved multi-mode visual language model, and the method comprises the steps: obtaining a historical bridge original image which comprises a bridge cantilever casting section, a cast-in-place section, a web, a diaphragm plate, a closure section and a concrete box girder; constructing an improved multi-modal visual language target detection model; based on the bridge original image, training the improved multi-modal visual language target detection model to obtain a trained improved multi-modal visual language target detection model as a bridge disease detection model; obtaining a to-be-detected bridge image, and dividing the to-be-detected bridge image into a plurality of overlapped image blocks based on an SAHI sliding window mechanism; detecting each image block in a local region based on the bridge disease detection model to obtain a region detection result; and on the basis of the detection result of each region, generating a global detection result in a splicing and fusion mode.

The invention discloses a power transmission line unmanned aerial vehicle intelligent inspection system and method based on deep learning, and relates to the technical field of power transmission line inspection. Electromagnetic environment modeling and path optimization are carried out, a high-interference section is identified, the flight path and height are correspondingly adjusted, the influence of strong electromagnetic interference on a sensor and a communication system is reduced, and the inspection efficiency is improved. When the temperature abnormal area is detected, the resolution and focusing parameters of the image are automatically optimized, a clearer high-resolution image is obtained, meanwhile, the temperature abnormal area is focused, after the temperature abnormal area is detected, the shooting distance and angle are automatically adjusted, close-range and multi-angle shooting is carried out on a key component, and tiny abnormity on the surface of the component can be captured. The detection precision of early faults is improved, after the inspection task is finished, the multi-modal data are uploaded to the work platform, the data are analyzed and filed, and the inspection report containing temperature abnormity, fault positions and electromagnetic environment characteristics is generated, so that the manual analysis time is saved.

The invention provides a distribution network line fault positioning method based on edge calculation and multi-region cooperation, and relates to the technical field of fault positioning methods, and the method comprises the steps: deploying an edge sensing node based on a distribution network line, collecting distribution network data through the edge sensing node, and carrying out the preprocessing of the distribution network data at the edge sensing node, a decision tree model is embedded in an edge sensing node, an edge calculation function is realized based on the decision tree model, acquired distribution network data are analyzed in real time, and potential faults are detected. According to the method, edge sensing nodes are deployed in each region of a distribution network line, a decision tree model is introduced to realize fault detection, so that fault information can be analyzed and processed in real time at the edge nodes, multi-region cooperative processing is carried out by using a weighted voting algorithm, and when a fault is detected in a certain region, the fault detection efficiency is improved. And the edge sensing nodes and the edge sensing nodes in other areas jointly participate in comparison and verification of fault information, so that the accuracy of fault detection is improved.

The invention discloses a power equipment detection method and device based on data acquisition of an inspection unmanned aerial vehicle, electronic equipment and a storage medium, and the method comprises the steps: obtaining a multi-view image of to-be-detected power equipment, and inputting the multi-view image into an abnormal region detection model, and generating an anomaly existence probability and a suspected anomaly region coordinate of the equipment under the current view angle. When it is detected that the abnormal probability at a certain visual angle exceeds a preset threshold value, a reinspection instruction is sent to the inspection unmanned aerial vehicle in an adjacent area, and image data of the equipment at a new visual angle are fed back. A second anomaly existence probability is calculated by re-inputting the new view angle image to the anomaly detection model. If the probability exceeds a preset threshold value, judging that the power equipment is abnormal, and sending an alarm signal; otherwise, judging that the equipment is normal. According to the invention, the abnormal accurate positioning and intelligent alarm of the power equipment can be realized, and the efficiency and accuracy of equipment inspection can be effectively improved.

The invention provides a subway tumble detection method and system based on cloud edge collaboration and an X-CLIP model, and relates to the technical field of subway tumble detection, and the method comprises the steps: obtaining a real-time video stream in a subway, and analyzing the video stream data into frame image data and video stream data; inputting the frame image data into the YOLOv8n-c3xghost neural network model to obtain all human body target area detection frames; performing identification detection on the human body target area detection frame through a BoT-SORT target tracking algorithm to obtain candidate images of abnormal behaviors; inputting the candidate image of the abnormal behavior into an X-CLIP model, outputting an abnormal region fragment classification result of the candidate image, identifying an abnormal region fragment again, determining the falling behavior according to the situation that the falling probability is greater than a set threshold value, outputting a position coordinate where the falling behavior occurs and a corresponding original image, and giving an alarm; wherein the model is deployed at the cloud end and trained, the model sinks to the edge side after being compressed and packaged, and real-time video frame detection is realized at the edge side.

The invention provides an intelligent industrial quality inspection method and system based on AI visual identification, and relates to the technical field of visual identification, and the method comprises the steps: inputting an industrial product image collected at an edge end into a pre-trained defect region detection model, and obtaining a defect region detection result; extracting defect area features according to a defect area detection result, carrying out dimension reduction processing to obtain compressed defect area features, and deciding to unload a defect classification task to a cloud end or directly carry out defect classification at the edge end according to an adaptive task unloading strategy in combination with working data of the edge equipment; if the defect classification task is determined to be unloaded to the cloud, transmitting the compressed defect area features to the cloud through a network, performing defect type identification on the cloud by adopting a pre-trained defect classification model, outputting a classification result of the defect area, returning the classification result to an edge end, and combining a defect area detection result and the classification result of the defect area to obtain the defect classification task. And generating a defect visualization effect picture and a quality inspection report.

The invention discloses a pump shell welding seam quality detection method based on image segmentation. The method comprises the following steps: generating a steady-state pump shell welding seam image flow under the driving of motion compensation; obtaining a domain adaptive DINOv2 visual embedded feature map; performing adaptive pyramid fusion and cross-scale attention operation on the domain adaptive DINOv2 visual embedded feature map to generate a semantic form segmentation map; generating a semantic-texture fusion mask; performing uncertainty weighted optimization on the semantic-texture fusion mask in combination with the pixel-level confidence map to obtain a weld defect instance map; generating an interpretable texture anomaly heat map; and through multi-view supplementary shooting or manual auditing, supplementary pump shell welding seam image data is obtained, and the steady-state pump shell welding seam image flow is updated. According to the method, the system can continuously keep accurate positioning of the pixel-level segmentation boundary in a weak-label or even non-label migration scene, and boundary drift and area missing detection of a segmentation result are effectively avoided.

The invention discloses a fishing boat name identification method and system based on image processing and deep learning. The method comprises the following steps: S1, fishing boat image acquisition; s2, image preprocessing and enhancement are carried out to realize image noise reduction, deblurring and brightness adjustment processing, and image quality judgment is carried out after processing to form closed-loop optimization; s3, self-adaptive image enhancement is carried out to realize illumination compensation and image dynamic enhancement; s4, ship name area detection and segmentation; s5, ship name region feature extraction and optimization; s6, feedback and optimization of an identification result; s7, character recognition and post-processing; s8, performing correction and verification; s9, log identification and report generation; and S10, displaying and storing a result. According to the invention, the fishing boat name identification precision can be effectively improved.

The disclosure discloses a method, an apparatus and a robot for out-of-stock detection of shelf commodity. The method includes: acquiring a plurality of shelf RGB images and a plurality of shelf depth images; executing an out-of-stock area detection step to obtain all vacant areas in the shelf for shelf RGB images and shelf depth images; stitching the shelf RGB images into a complete shelf image, merging and de-duplicating on all vacant areas and detection boxes of commodities, shelf label and layer lattice, and mapping them to the complete shelf image; generating a shed grid area corresponding to each commodity for the complete shelf image, and dividing all vacant areas in the shelf based on the shed grid area; and determining an out-of-stock detection result of each commodity based on the position information and the depth information of the vacant area and the shed grid area.

The invention relates to the technical field of data processing, and provides a target detection method and device, a model training method and device, electronic equipment and a medium. The target detection method comprises the steps that a to-be-recognized image and a query text are acquired, and the query text is used for querying a target object corresponding to the query text in the to-be-recognized image; performing image recognition on the to-be-recognized image to obtain image description features and region detection visual features; performing regional multi-modal fusion processing on the image description features and the regional detection visual features to obtain regional multi-modal fusion features; performing feature fusion processing on text features obtained based on the query text and the regional multi-modal fusion features to obtain text regional fusion features corresponding to the query text; and a target detection result is obtained based on the text features and the text region fusion features, so that the fusion degree of text semantics and image region features is improved, and the accuracy and robustness of target detection in a complex scene are improved.

The invention relates to the technical field of image processing, and provides an image artifact detection method and system based on a deep learning technology, and the method comprises the following steps: carrying out the preprocessing of an obtained to-be-processed image, and carrying out the feature extraction of the preprocessed image; position coding is carried out on the extracted feature map A, and the extracted feature map A is fused with the feature map A; performing multi-layer encoding and decoding on the fused feature map through an encoder and a decoder to obtain a feature map B containing an artifact target area; and generating an anchor frame of an artifact region for a target region in the feature map B, and dynamically adjusting the size and position of the anchor frame according to local information of the down-sampling rate, texture complexity and edge strength of the feature map B to obtain an artifact region detection result after the anchor frame is labeled. Automatic artifact detection and quantitative evaluation of the influence degree can be achieved, the accuracy and efficiency of medical image interpretation are improved, and more reliable data support is provided for clinical decision making.

The invention discloses an archive management system based on artificial intelligence, and the system comprises a data preprocessing module which is used for obtaining and preprocessing original archive data, a missing region detection module which is used for carrying out the missing region detection and feature extraction of the preprocessed archive data, and generating missing region description information; the global search optimization module is used for carrying out global search by adopting a variable-scale Levy flight algorithm based on the missing region description information; the local optimization module is used for carrying out detail optimization on a local missing region by utilizing an improved grey wolf optimization algorithm based on the global search candidate data; the data fusion and consistency matching module is used for fusing the locally optimized filling data and the preprocessed archive data; and the filling quality evaluation and optimization module is used for performing error feedback evaluation on the filled archive data and finally filing the corrected archive data. According to the invention, the overall consistency and rationality of archive filling in the archive management process are improved.

The invention discloses a highway pavement microcrack detection system based on an improved swarm algorithm, and the system comprises an image collection module which is used for outputting a standardized highway pavement image; the image preprocessing module is used for generating a preprocessed highway pavement image; the parameter optimization module is used for performing global search and local refinement search on the preprocessed highway pavement image based on a two-stage bitter fish optimization algorithm model; the image segmentation module is used for generating a preliminary micro-crack candidate region map; the feature extraction module is used for forming a depth feature map; the region reconstruction module is used for outputting a final highway pavement micro-crack region segmentation result; and the detection and output module is used for carrying out candidate region detection and positioning on the highway pavement micro-crack region segmentation result and outputting a final highway pavement micro-crack detection result containing the micro-crack position and region information. According to the method, the response capability to a weak edge is improved, a crack topological structure consistency function is fused in a local refining stage, and the detection structure reduction precision of a micro-crack region is improved.

The invention relates to the field of image cultural relic disease recognition and evaluation, in particular to a cultural relic disease recognition and evaluation system and method based on image analysis, and the system comprises a multispectral image collection module, an image processing module, a disease recognition module, a repair evaluation module, a decision optimization module and a disease database. The multispectral image acquisition module optimizes a light source through a reflective area detection algorithm to obtain a multispectral image; the image processing module uses a multi-band collaborative filtering algorithm to eliminate noise and extract fusion features, and divides disease areas; the disease identification module determines disease positions through a connected region marking algorithm, and performs disease classification by means of a neural symbol model; the repair evaluation module outputs a quantitative score; the decision optimization module weighs the repair effect, the cost and the time by introducing a multi-objective optimization model of a genetic algorithm, and outputs an optimal scheme; according to the invention, the disease identification precision and the automation and scientificity of repair evaluation are improved.

The invention discloses an unstructured file identification method based on primitive identification, and the method comprises the following steps: (1) preprocessing: cutting and zooming an electrical wiring drawing to a required size, and carrying out the gray processing; (2) primitive recognition: constructing a feature extraction network of an electrical primitive detection model by adopting a YOLO electrical primitive detection algorithm fused with an attention mechanism; (3) character recognition, which comprises the following steps: removing primitives, detecting an annotated text area, constructing a text candidate box, segmenting and adjusting an annotated text boundary, recognizing annotated text content, and filtering an electrical text recognition result; and (4) electrical element association relationship analysis, which comprises the following steps: frame element extraction, primitive group region division, template matching and electrical primitive-annotation text association. According to the method, the primitives and characters of the electrical wiring diagram can be obtained, the problem that different fonts and styles appear in marked characters can be solved, and semantic information can be understood.

The invention discloses an ancient textile image restoration system based on artificial intelligence. The system comprises a multi-source image acquisition module, a damaged area detection module, a pattern generation module, a color restoration module, a texture synthesis module and a multi-scale fusion module. The system introduces a wavelet guidance-frequency domain attention mechanism and a rotation invariant Haar wavelet basis function to realize accurate identification and classification of a damaged area; a saliency-guided wavelet decomposition control and self-adaptive threshold denoising method is combined, so that the perception capability of slant textures and edge details is improved; the texture synthesis module constructs a hierarchical modeling strategy fusing Gram style loss, Wasserstein style loss and a total variation regular term, and realizes generation of high-quality textures with unified styles and smooth edges; the system can be widely applied to cultural relic digital repair and display scenes.