11results about How to "Reduce spatial resolution" patented technology

The invention discloses an improved YOLOv9 transformer substation insulator and a defect detection method and system thereof, and the method comprises the steps: obtaining and preprocessing an insulator and defect image of a transformer substation, and obtaining a preprocessed image; inputting the preprocessed image into an improved YOLOv9 model for training to obtain an MPDIOU loss function for optimization, and obtaining a transformer substation insulator and defect detection model; and inputting transformer substation insulator and defect images acquired in real time into the transformer substation insulator and defect detection model, and outputting a transformer substation insulator and defect detection result. A diversity branch block DBB is embedded in a RepNCSPELAN, the DBB enhances the representation capability of a single convolution and enriches feature spaces, including convolution sequences, multi-scale convolution and average pooling, by combining diversity branches of different scales and complexity, and the model ensures the running speed and the resource efficiency while improving the performance.

The invention discloses a no-reference light field image quality evaluation method based on a visual converter, and the method comprises the steps: extracting a sub-aperture image array of a distorted light field image, and extracting a central sub-aperture image and a sub-aperture image array of which the central angle resolution is a * a; inputting a central sub-aperture image of the distorted light field image into a space blocking module to obtain a distorted light field image space block rich in space information, and inputting a sub-aperture image array of which the central angle resolution is a * a of the distorted light field image into an angle blocking module to obtain a distorted light field image angle block; obtaining multi-layer features on a spatial domain of the distorted light field image, obtaining multi-layer features on an angle domain of the distorted light field image, and splicing the multi-layer features to obtain fusion features rich in spatial features and angle features; and carrying out regression on the fusion features by utilizing a quality score prediction network to obtain a quality score of the distorted light field image, and training the network by utilizing gradient back propagation according to a configured related network model and training parameters.

This invention relates to the field of smart agriculture information technology, and discloses an agricultural pest and disease prediction system and method based on multimodal data fusion and edge AI, comprising: a data acquisition module, an edge AI analysis module, and a communication interaction module; the data acquisition module is used to collect agricultural monitoring data containing agricultural environmental information and crop status information; the edge AI analysis module is used to call a pest and disease prediction model that integrates multimodal agricultural feature extraction to perform multimodal joint feature extraction on the agricultural monitoring data containing agricultural environmental information and crop status information, and infer pest and disease prediction results based on the multimodal joint features, and generate pest and disease early warning information based on the pest and disease prediction results; the communication interaction module is used to upload the agricultural monitoring data collected by the data acquisition module and the pest and disease prediction results and pest and disease early warning information output by the edge AI analysis module to a cloud platform. This invention enables agricultural pest and disease prediction on resource-constrained edge devices.

A method and system for super-resolution reconstruction of infrared images based on convolutional neural networks, relating to the field of electronic digital data processing, is disclosed. The method includes: inputting a low-resolution infrared image into a preset convolutional neural network to obtain multi-layer feature maps of the low-resolution infrared image; scaling the feature maps of different layers in the multi-layer feature maps according to a preset ratio and then stitching and fusing them to obtain a fused feature map; generating feature vectors from the fused feature map using global average pooling, and transforming the feature vectors using a fully connected layer to obtain attention weights; weighting the attention weights with the fused feature map to obtain an enhanced feature map; and performing upsampling reconstruction processing on the enhanced feature map using an upsampling structure, introducing a residual connection structure during the upsampling reconstruction process to generate a high-resolution infrared image. Implementing this method generates high-resolution infrared images with more detail.

The invention discloses a heart medical image segmentation method based on improved U-Net, relates to a medical image segmentation method, and provides a multi-dimensional context attention module (MDCA) and a reverse feature modulation module (RFM) through an improved U-Net model for technical challenges existing in heart MRI image segmentation. The modules not only enhance the segmentation precision of the model on a complex heart anatomical structure, but also effectively solve the problem of class imbalance in multi-class segmentation. By means of the MDCA module, the model can better fuse global and local information, so that the detail capturing capability of the heart image is improved. And the RFM module ensures the high-precision performance when the boundary blur and small-area region is processed through dynamic weight adjustment. Through the improvement, effective technical support is provided for automatic diagnosis and evaluation of cardiovascular diseases, and meanwhile, a solid foundation is laid for further development of the field of medical image analysis in the future.

The present invention belongs to the field of flow field testing technology, and specifically relates to a probe for measuring all parameters of a two-dimensional steady-state flow field in the boundary layer of the inner wall of a casing, including a probe head, a temperature sensor, a heat-insulating seal, a temperature sensor cable lead-out channel, a pressure measuring hole, a pressure-leading pipe channel, a probe support rod, a temperature sensor cable and a pressure-leading pipe. The probe head is cylindrical, and a pressure measuring middle hole, a pressure measuring left hole and a pressure measuring right hole that are not connected to each other are opened on the windward surface. A trapezoidal groove is opened axially on the leeward side facing away from the pressure measuring middle hole. The temperature sensor is placed in the trapezoidal groove and is located in the low-speed separation zone on the leeward side of the probe head. The probe for measuring all parameters of a two-dimensional steady-state flow field in the boundary layer of the inner wall of the casing of the present invention can simultaneously measure the total temperature, total pressure, static temperature, static pressure, Mach number, deflection angle, speed and density of the two-dimensional steady-state flow field in the boundary layer of the inner wall of the casing, and has the characteristics of small size, large airflow insensitivity angle, high reliability, high spatial resolution, high measurement accuracy and fast response time.

The invention discloses an SERS-optimization algorithm detection method for nano-plastics by using a silver nanowire network structure, which comprises the following steps: S1, obtaining separated and purified silver nanowires, and dissolving the separated and purified silver nanowires in absolute ethyl alcohol with the same volume to generate a silver nanowire solution; step S2, obtaining a microporous membrane with a silver nanowire network structure; s3, sequentially dripping different types of micro-nano plastic molecule suspensions with the same concentration on the microporous membrane with the silver nanowire network structure by using a glass microtube, and then carrying out surface enhanced Raman spectrum detection and acquisition on the microporous membrane; s4, the contribution coefficient of each sample is solved through a non-negative least square method, and finally, a visual three-dimensional diagram result is output through python drawing. The method has the advantages that various nano-plastic targets are separated and analyzed, the equipment building cost is low, operation is easy, the application potential is huge, data are accurate and visual, and the like.

This invention relates to the field of monitoring corrosion morphology and pH dynamic distribution in steel, and particularly to a rapid and intelligent monitoring method and system for in-situ monitoring of pitting morphology and surrounding pH dynamic distribution during electrochemical testing of steel pitting corrosion. First, an in-situ steel test sample with an observation surface is prepared and encapsulated, and then horizontally mounted in an adjustable electrolytic cell. Next, a methyl orange calibration solution with a pH gradient of 1-7 is prepared, and images of the sample at different pH values ​​are captured and imported into the system for calibration, establishing a quantitative mapping relationship between pH and the Lab values ​​of the calibrated images. Finally, in-situ electrochemical testing is conducted in a colorless salt test solution containing the same concentration of methyl orange, simultaneously monitoring the morphology of pitting initiation and development, as well as the dynamic evolution of the surrounding pH. This system can achieve millisecond-level dynamic in-situ monitoring of the spatial distribution of pH around pitting corrosion during the corrosion growth process, and can continuously capture real-time pH evolution information during the initiation and expansion of pitting corrosion.

The present invention belongs to the field of flow field testing technology, and specifically relates to a probe for measuring all parameters of a subsonic three-dimensional steady-state flow field, including a probe head, a temperature sensor, a convection heat exchange groove, an insulating seal, five pressure measuring holes, a pressure pipe channel, a probe support rod, a pressure pipe and a temperature sensor cable. The probe head is cylindrical, and the top of the cylinder has a concave ball socket structure perpendicular to the center line of the cylinder. The inner wall of the ball socket is provided with a pressure measuring middle hole, a pressure measuring upper hole, a pressure measuring lower hole, a pressure measuring left hole and a pressure measuring right hole that are not connected to each other, and a cross-shaped convection heat exchange groove is provided on the back of the ball socket. The temperature sensor is placed in the convection heat exchange groove and faces the center line of the pressure measuring middle hole. The probe of the present invention can simultaneously measure the total temperature, total pressure, static temperature, static pressure, Mach number, deflection angle, pitch angle, speed, density and other parameters of a subsonic three-dimensional steady-state flow field, and has the characteristics of small size, long life, wide airflow insensitive angle, high reliability, high spatial resolution and high measurement accuracy.

The invention relates to the technical field of reservoir monitoring, and particularly discloses a multi-modal small reservoir impounded water monitoring system, which comprises a data acquisition module, a model construction module, a data monitoring module, an impounded water decision estimation module and a database module which are electrically connected with one another, the data acquisition module obtains three-dimensional topographic data and water level data of the small reservoir through unmanned aerial vehicle surveying and mapping, and the model construction module is used for constructing a three-dimensional model of the small reservoir according to the three-dimensional topographic data and the water level data; the data monitoring module is used for acquiring real-time water level data of the small reservoir, the remaining reservoir capacity of the reservoir and the water inflow speed; the water storage decision pre-estimation module calculates a pre-estimation decision of the small reservoir through a pre-trained water storage estimation model according to the water inflow speed of the small reservoir and the residual reservoir capacity of the reservoir; the objective of the invention is to solve the problem that an existing reservoir prediction model is lack of pre-estimation and judgment of future water retaining operation of a plurality of small reservoirs.

The invention discloses a lens defect detection method and device, equipment, a medium and a program product, and relates to the technical field of defect detection.An existing YOLO model is transformed, in a network structure of the YOLO model, a down-sampling layer of a first target convolutional layer is removed, the number of channels of a second target convolutional layer is reduced, and a target YOLO model is obtained; and detecting lens defects of the to-be-detected lens based on the target YOLO model. When multiple defects possibly existing on a lens and different defects on different lenses simultaneously exist, a new defect detection model does not need to be trained and applied, and the capability of detecting other large-size defects can be reserved while the capability of detecting small-size defects can be improved through the modified YOLO model, so that the detection efficiency is improved, and the detection cost is reduced. Universal and rapid detection is realized, and the detection requirements of multiple varieties and short period of a lens product production line can be met.