20results about How to "Avoid background distractions" patented technology

The invention discloses a cross-modal foreground distillation method for multi-view three-dimensional target detection, and belongs to the technical field of automatic driving perception. According to the method, a laser radar or a multi-modal three-dimensional target detection model is used as a teacher model, a multi-view aerial view BEV perception three-dimensional target detection model is used as a student model, and the model performance is improved through multi-scale feature distillation; a space attention mechanism and a foreground mask module are introduced, and the student model can simulate feature responses of the teacher model in different space positions under multiple scales, focus on a foreground target and suppress background noise; the adaptive module ensures the consistency of the multi-scale features in feature dimensions and spatial resolution, and finally, the difference between the features and regression output is measured through loss functions such as mean square error and KL divergence, so that efficient cross-modal and multi-scale foreground feature distillation is realized. Finally, the multi-view three-dimensional target detection precision and efficiency are improved, and meanwhile, the distillation requirements of multi-scale features are fully considered.

The invention discloses a mushroom yield estimation method based on three-dimensional reconstruction lossless phenotype parameter extraction, belongs to the technical field of agricultural informatization and intelligentization, and solves the problem of low mushroom yield estimation accuracy. The method comprises the following steps: performing point cloud three-dimensional reconstruction on shiitake mushrooms by using a region of interest to generate dense point cloud data; preprocessing the dense point cloud data; based on an improved CP-PointNet + + model and a clustering algorithm, segmenting mushroom point cloud, extracting multi-dimensional key phenotypic parameters of pileus diameter, thickness and stipe height, and covering main features of mushroom phenotypic information; the improved PointNet + + network comprises the following steps: adding a CBAM module to an MLP layer of the PointNet + + network, and replacing common convolution with partial convolution PConv; and taking the phenotypic parameters of the shiitake mushrooms as input variables of the neural network model, and predicting the shiitake mushroom yield. The method is suitable for phenotypic character analysis and breeding research of edible mushrooms such as shiitake mushrooms and the like.

The invention discloses an immunodetection method based on holographic imaging mode conversion and deep learning, and belongs to the field of immunoassay detection. The deep learning holographic mode conversion system constructed based on the non-paired data set reduces the influence of diffraction interference on target quantification to the greatest extent, so that holographic super-resolution imaging is realized, and challenges in paired data set generation are overcome; besides, a functional glass slide is designed, and rapid and sensitive holographic imaging detection is realized in combination with a click reaction signal amplification strategy; the functionalized glass slide is combined with the portable holographic imaging equipment, so that the detection efficiency of the system is greatly improved while accurate signal amplification is carried out, the application scene is expanded, and antibiotic residues can be rapidly and sensitively detected. The invention opens up a new research direction for high-sensitivity on-site convenient detection of trace target objects in portable equipment and complex samples.

The invention relates to the technical field of sign language recognition, and provides a continuous sign language recognition method, electronic equipment and a storage medium. The method comprises the following steps: firstly, collecting and segmenting a continuous sign language video, extracting an isolated sign language action boundary through a BIO tag, and constructing a sign language library after data enhancement; then key point information of hands, faces and upper bodies is extracted, and comprehensive feature vectors are generated in combination with RGB features; and extracting double-flow sequence information by using an online CSLR model and an offline ISLR model, and translating in a text network to generate a sign language text sequence. According to the method, the accuracy and real-time performance of continuous sign language recognition can be effectively improved.

The invention belongs to the technical field of drug detection, and particularly relates to a method for detecting lycium barbarum glycopeptide metabolites in rat plasma and tissues based on non-targeted metabonomics. According to the method, after rat lycium barbarum glycopeptides are administered through intragastric administration, blood, liver, intestine, lung and brain tissue samples after administration are collected. A UPLC-Q-TOF-MS (Ultra Performance Liquid Chromatography-Quadrupole Time of Flight Mass Spectrometry) analysis method is combined with a statistical analysis method comprising principal component analysis (PCA) and orthogonal-partial least squares discriminant analysis (OPLS-DA) to carry out in-vivo metabonomics analysis on the wolfberry glycopeptide. Then, based on a human metabolome database (HMDB), lycium barbarum glycopeptide differential metabolite is searched, so that the pharmacological action mechanism of the lycium barbarum glycopeptide is clarified from the perspective of metabolism, and a foundation is laid for deep research and development of the medicinal value of the lycium barbarum glycopeptide in future.

The invention relates to the technical field of ceramic product manufacturing, and discloses a rapid color development generation method, device and equipment of ceramic pug and a medium, the method comprises the following steps: obtaining a rendering image of a product to be processed, and extracting a mud color gamut value from the rendering image; extracting color gamut data features by using a feature extraction algorithm, inputting the color gamut data features into a first threshold monitoring model for matching, and determining a reference threshold interval corresponding to the mud blank components and the firing conditions; carrying out shaping and firing treatment according to the reference threshold interval, and obtaining a real-time color gamut value of the outer surface of the pug prototype in the firing process; and dynamically evaluating the sintering state of the pug prototype by using the second threshold monitoring model, and controlling heating termination and cooling according to the sintering state. According to the invention, accurate evaluation of the firing state and intelligent control of heating termination and cooling start are realized, the problems of dependence on manpower, feedback lag and high trial and error cost of a traditional process are effectively solved, the accuracy and consistency of pug color development are improved, and the trial and error frequency and energy consumption are reduced.

The application discloses a kind of hemoglobin detection methods, comprising: taking 0.1-0.2mmol / L (6,5)-SWCNTs solution, add to the ultrafiltration centrifuge tube with the molecular weight of 100kDa, centrifugal 1-10min, discard filtrate;In the inclusion, add the same volume of SDS solution with filtrate, repeat centrifugal 6-15 times;Again, solution ultrasonic dispersion 0.2-1h, and centrifugal 2-15min;In DPPE-mPEG5000 solution, add the supernatant above, after mixing sufficiently, stand overnight;Again, using the ultrafiltration centrifuge tube with the molecular weight of 10kDa and 100kDa respectively to the mixed solution above sequentially centrifugal filtration, take the supernatant above, add hemoglobin solution to be measured, after mixing uniformly, stand incubation 10S above;With water as blank control, carry out UV-Vis-NIR absorption spectrum and near infrared fluorescence spectrum determination;Hemoglobin standard product is prepared into different concentration stock solution, and standard curve is drawn;The concentration of hemoglobin in sample is calculated according to standard curve.The application is simple in operation, short in time, and low in detection cost.

This invention discloses a method and system for multi-component analysis of aircraft exhaust plumes using micro-on-chip spectral imaging. The method involves acquiring multispectral image data of the exhaust plume region using a micro-on-chip spectral imaging system. This invention unmixes the mixed spectra using a non-negative matrix factorization algorithm and, combined with a pre-built fuel component spectral library, accurately identifies and quantitatively calculates the concentration distribution of key components such as carbon dioxide, carbon monoxide, nitrogen oxides, and unburned hydrocarbons in the exhaust plume. This method overcomes the errors caused by component overlap in traditional spectral analysis. By establishing a three-dimensional spatial coordinate model, high-precision extraction of the exhaust plume region is achieved, avoiding background interference. Furthermore, convolutional neural networks are used to perform spatiotemporal correlation modeling of the multi-component concentration data, generating a three-dimensional dynamic evolution map of the exhaust plume chemical components. This map reflects the diffusion patterns of exhaust plume components over time and space in real time, providing crucial data support for environmental impact assessment, aircraft emission control, and accident emergency response.

The invention provides a boundary detection method and device, equipment and a storage medium, and the method comprises the steps: obtaining a to-be-detected target image of target equipment, and enabling the to-be-detected image to comprise an image of a target assembly of the target equipment; detecting an edge region image in a to-be-detected target image, and determining a first target region image in the to-be-detected target image based on the edge region image; determining a second target area image in the to-be-detected target image based on the height of the first target area image and the height of the target component; based on the second target area image, extracting a dirty area image corresponding to the target component; determining a third target area image in the to-be-detected target image according to the second target area image and the width of the target component; and determining the boundary of the target component in the to-be-detected target image based on the second target area image, the third target area image and the dirty area image. By adopting the method, the precise extraction of the boundary is realized.

The invention discloses a water-soluble near-infrared aggregation-induced emission coumarin-quinolyl viscosity fluorescent probe and application thereof, and the water-soluble near-infrared aggregation-induced emission coumarin-quinolyl viscosity fluorescent probe is realized by the following method: carrying out Knoevenagel condensation reaction on a 7-(N, N '-diphenylamino)-coumarin-3-formaldehyde compound and 1, 2-dimethyl quinoline iodized salt as raw materials under the catalytic action of p-toluenesulfonic acid and piperidine to synthesize the water-soluble near-infrared aggregation-induced emission coumarin-quinolyl viscosity fluorescent probe. The chemical structural formula is shown as a formula (III). The preparation method has the advantages of simple reaction steps, mild reaction conditions and high yield. The fluorescent probe emits fluorescence in a near-infrared region, has the advantages of large Stokes shift, low background interference, small light damage to biological samples and the like, has aggregation / viscosity-induced fluorescence enhancement capability, and can be used for detecting viscosity changes in solutions and cells. And an effective research tool is provided for researching physiological activities under different viscosities in cells.

The invention discloses a lipid droplet fluorescent probe and a synthesis method and application thereof.The synthesis method comprises the steps that 4-diethylaminosalicylaldehyde and 3-dicyanomethylene indanone are dissolved in an organic solvent, then N, N-diisopropylethylamine is added, stirring and heating reflux are conducted at the room temperature, precipitates are filtered and purified, and then a red solid, namely the lipid droplet fluorescent probe, is obtained; the fluorescent probe is named as a fluorescent probe B41. The probe prepared by the invention can be accurately positioned on a lipid droplet, has relatively high sensitivity, good optical stability and specific response, and is rapid in response and relatively short in dyeing time consumption; background interference in a living body can be avoided, and the applicability in the living body is improved; the compound shows extremely low cytotoxicity, has relatively good biocompatibility and is suitable for cell imaging experiments; the preparation method is simple, purification is simple, raw materials are easy to obtain, and industrial production is easy to realize.

The invention discloses an aptamer regulation and control electrochemical sensor based on an Au (at) Ti3C2MXene composite material, and a preparation method and application of the aptamer regulation and control electrochemical sensor based on the Au (at) Ti3C2MXene composite material. A glassy carbon electrode is used as a working electrode, and the surface of the electrode is modified by an Au-coated Ti3C2MXene composite material prepared by an in-situ reduction method so as to enhance the electron transfer efficiency; a locking compound is formed by a specific aptamer of the lactobacillus acidophilus and an activation chain, and signal regulation and control are realized by combining the trans-cleavage activity of CRISPR-Cas12a. During detection, specific binding of the lactobacillus acidophilus and the aptamer causes conformational change, an activation chain is released to trigger the MB labeled DNA probe on the surface of the Cas12a cutting electrode, and quantification is realized through DPV detection signal change. The detection limit of the method is as low as 4 CFU / mL, the linear range is 10-106 CFU / mL, and the method is suitable for accurate detection of lactobacillus acidophilus in food and probiotic preparations.

The present invention relates to the technical field of chemical synthesis, and in particular to a six-membered cucurbitacin-based supramolecular framework material and a preparation method and application thereof. The preparation method comprises: placing 4,4'-biphenyl disulfonic acid and a six-membered cucurbitacin in water and stirring evenly to obtain a mixed solution, adding a lanthanum nitrate solution as an inducer to the mixed solution, and continuously placing the mixed solution in a hydrothermal reactor for heating, cooling the product, standing it, and drying it to obtain a six-membered cucurbitacin-based supramolecular framework material. The fluorescent probe in the present invention is useful for detecting Cu in water. 2+ The invention has the characteristics of convenient and quick operation, good selectivity and reusability.

The invention discloses a degradation identification method and system based on temperature difference adjustment of an infrared thermogram of an insulator string. The method comprises the following steps: obtaining the infrared thermogram of the insulator string; extracting an area where an insulator string is located in the image, and dividing an area where each insulator element is located; obtaining the maximum value and the minimum value of the brightness in the area where each insulator element is located; calculating the temperature corresponding to the maximum brightness value and the minimum brightness value in the area where the insulator element is located, obtaining an optimal temperature measurement range in combination with the current temperature, and adjusting the insulator string image to obtain an optimal insulator string image; calculating an abnormal region in the region where the insulator string is located, carrying out adaptive connected domain analysis on the abnormal region, optimizing the connected domain analysis through a conditional random field (CRF), and merging the adjacent abnormal regions to obtain a complete degraded region; according to the invention, the required time is greatly reduced when a worker checks a large number of insulator strings.

This invention provides an image analysis-based platform, system, and method for inspecting the quality of onboard components, relating to the field of onboard component quality inspection technology. The method includes acquiring multispectral image data and CAD design data of the circuit board to be inspected; performing coordinate matching between the CAD design data and the multispectral image data; comparing the measured geometric features with the geometric design features, and comparing the measured spectral features with spectral reference features to obtain the spectral deviation of the corresponding component; and determining the quality of the onboard component based on the geometric deviation and the spectral deviation. By introducing multispectral image data, while extracting local texture features, it also deeply analyzes the spectral response feature values ​​of each band, significantly improving the depth and reliability of the inspection.

The present application relates to the technical field of highway slope health monitoring, and provides a highway slope disease risk zoning method based on three-dimensional positioning and multi-source fusion, comprising: acquiring a slope multi-source monitoring data set covering cracks-displacement-deformation three elements with spatial geographic information; constructing an upstream crack three-dimensional positioning module based on YOLO11-MTA and NeRFusion and a downstream slope risk assessment module based on multi-source information fusion; obtaining crack three-dimensional elements with three-dimensional spatial coordinates and geometric attributes based on the upstream crack three-dimensional positioning module; performing spatial co-occurrence and collaborative evolution analysis of the crack-displacement-deformation three elements based on the downstream slope risk assessment module, and performing highway slope disease risk zoning, and outputting three-dimensional risk zoning results. The method can solve the problems of lack of three-dimensional spatial positioning of cracks, insufficient multi-source data fusion, inability to associate displacement anomalies with crack development space, and low risk assessment accuracy in the prior art.

The invention relates to the technical field of spinal deformity auxiliary observation, and discloses a spinal deformity auxiliary observation method, which comprises the following steps: S1, fixedly erecting a plurality of cameras in an evaluation site, calibrating the cameras, and collecting a multi-view video image of an evaluated person; s2, background filtering processing is carried out on the multi-view image, and a pure human body image is extracted; and S3, generating a 3D human body shape model by using the pure human body images under each view angle. Through a multi-camera dynamic capture technology, the back and spine forms of an assessed person can be observed in all directions in the dynamic processes of walking, stooping and the like, compared with traditional static image assessment, the dynamic observation mode can provide more comprehensive and three-dimensional data, doctors are helped to accurately assess the changes of the spine forms, and the assessment efficiency is improved. Therefore, the accuracy and comprehensiveness of diagnosis are improved, a doctor can better understand the spine structure of a patient through multi-angle and multi-action capture, and more effective support is provided for diagnosis and treatment of spine malformation.

The invention belongs to the field of food safety, and particularly relates to a p-coumarin imprinting fluorescence sensor and a preparation method thereof. The preparation method comprises the following steps: mixing a carbon source with a dimethyl sulfoxide solution, heating and refluxing in a dark place, dialyzing and drying to obtain the carbon quantum dots; the carbon quantum dots are wrapped by a molecular imprinting layer which is composed of ethyl orthosilicate, a silane coupling agent 3-aminopropyltriethoxysilane and p-coumarin; and carrying out specific labeling by taking coumarin as a template, so as to prepare the coumarin imprinting fluorescence sensor. The method can effectively avoid the background interference of the sample in the complex sample detection process, and has the advantages of high stability, high sensitivity and good accuracy.

The method for estimating the yield of shiitake mushrooms based on lossless phenotypic parameter extraction based on three-dimensional reconstruction belongs to the field of agricultural information and intelligent technology, and solves the problem of low accuracy in estimating the yield of shiitake mushrooms. The method of the invention comprises: using the region of interest to perform three-dimensional reconstruction of the point cloud of shiitake mushrooms to generate dense point cloud data; preprocessing the dense point cloud data; segmenting the shiitake mushroom point cloud based on the improved CP-PointNet++ model and clustering algorithm, extracting multi-dimensional key phenotypic parameters of the cap diameter, thickness, and stipe height, and covering the main features of the phenotypic information of shiitake mushrooms; the improved PointNet++ network comprises: adding a CBAM module to the MLP layer of the PointNet++ network, and replacing ordinary convolution with partial convolution PConv; using the phenotypic parameters of shiitake mushrooms as input variables of the neural network model to predict the yield of shiitake mushrooms. The invention is suitable for phenotypic trait analysis and breeding research of edible fungi such as shiitake mushrooms.