20results about How to "Keep more" patented technology

The invention provides an unmanned aerial vehicle RGB image cotton yield prediction method based on an attention mechanism. The unmanned aerial vehicle RGB image cotton yield prediction method comprises the steps of 1, selecting a proper prediction object; and step 2, spraying a defoliating agent with a reasonable dosage. And step 3, obtaining test data. And 4, constructing a yield prediction model. And 5, predicting the cotton yield. And step 6, evaluating the model. According to the method, the unmanned aerial vehicle carries the visible light camera to collect the cotton canopy RGB image, the problem that the prediction precision of a single feature is not high is solved, image color features and texture features are extracted and combined, data are processed through a principal component analysis method, a CNN-Bi LSTM cotton yield prediction model based on an attention mechanism is established, and the cotton yield prediction precision is improved. And comparing and analyzing a plurality of deep learning yield prediction models of different cotton varieties, and screening out an optimal prediction model, so as to provide reference for rapidly predicting the cotton yield by using the unmanned aerial vehicle.

The utility model belongs to the field of fruit and vegetable processing and drying equipment, and relates to a fruit and vegetable dryer which comprises a hot air device, a drying device, a driving device, a control cabinet and a noise reduction device. Fruit and vegetables are loaded into the drying cylinder, the air energy host provides hot air, the hot air enters the hot air box, the drying cylinder is located above the hot air box, the drying cylinder rotates to dry the fruits and vegetables, hot strong wind low-temperature drying is achieved, more nutritional ingredients of the fruits and vegetables are kept, drying efficiency is high, and noise reduction and environmental protection are achieved; the device can be widely applied to the fruit and vegetable drying field.

The invention relates to the field of nanometer friction power generation sensing technology and film material manufacturing, in particular to a high-friction-voltage hydroxyethyl cellulose sensing material and a preparation method thereof.The sensing material comprises three layers of structures which are an upper layer hydroxyethyl cellulose film, a polyvinylidene fluoride film and a lower layer hydroxyethyl cellulose film from top to bottom, the HEC film with aramid nanofiber introduced into the outer layer serves as a friction layer and a mechanical supporting layer, the PVDF film in the middle serves as an electrostatic retention phase, and organic combination of electrostatic coupling and charge storage is achieved. According to the invention, a new thought is provided for the development of a friction nanometer power generation technology, and a more efficient and environment-friendly solution is provided for the application in the fields of wearable equipment, self-powered sensors and the like.

The application discloses a micro-fluidic chip and a method for recovering nucleic acids with different fragment sizes. The method can realize recovery of nucleic acids with different fragment sizes by repeatedly washing and recovering magnetic beads through the micro-fluidic chip. The method can improve the overall nucleic acid recovery effect by adjusting the adding concentration of the magnetic beads and PEG salt and the washing times, and can distinguish and control the nucleic acid length, and all the nucleic acids with different fragment lengths can be obtained by continuously adjusting the concentration. Moreover, the method can realize small volume, high throughput and automation.

The invention discloses a basin-type insulator infrared thermal imaging defect detection system and method, and relates to the technical field of infrared thermal imaging detection, the basin-type insulator infrared thermal imaging defect detection system comprises an input module and a processing module; the input module is used for receiving an infrared thermal imaging image of the basin-type insulator and gradually generating image features through a plurality of convolution blocks; and the processing module performs up-sampling operation, and fuses the up-sampled feature map and the corresponding feature maps with different resolutions in the input module layer by layer through jump connection to generate a segmentation map of the insulator defect. According to the infrared thermal imaging defect detection method for the basin-type insulator, nondestructive detection is carried out, a target object does not need to be contacted, temperature information of the target object is provided, the target temperature is not disturbed, and temperature distribution is visual and visible.

The present invention relates to the technical field of image processing, and in particular to an image deraining method, system, electronic device and storage medium. The image deraining method comprises: obtaining a rain streak feature map, a background feature map and a residual channel map of an initial rainy day image; fusing the rain streak feature map, the background feature map and the initial rainy day image to obtain a preliminary derained image, and fusing the preliminary derained image with the residual channel map to obtain a target derained image. The present invention improves the clarity restoration effect of rainy day images in real scenes, so that the result after deraining is closer to a real rain-free image, thereby better meeting the image requirements for clarity and accuracy.

The present invention relates to the field of computer vision technology, and discloses a quasi-incremental endoscopic image lesion classification method based on channel attention self-derivation, wherein an endoscopic image belonging to a category already seen by a classification model is input into a classification model that has completed training, and a classification result of the endoscopic image is obtained; the training process of the classification model comprises: the classification model comprises a feature extractor and a classifier; the training process of the old classification model comprises an old task stage, and the training process of the new classification model comprises a plurality of incremental learning stages, the new classification model is initialized using the parameters of the old classification model, and the new classification model is trained by a total loss consisting of a cross entropy loss, a logical value distillation loss, and an attention distillation loss; the present invention retains more old knowledge in the incremental learning stage through a distillation method of channel attention self-derivation, and more effectively alleviates catastrophic forgetting.

The present invention provides a global positioning method for a large-scale scene based on multivariate statistical information. First, a three-dimensional point cloud map of the scene is grid-divided to obtain a three-dimensional grid map; then, the point cloud falling into each three-dimensional grid in the three-dimensional grid map is counted to obtain a point cloud set of each three-dimensional grid, and the maximum frequency of the point cloud in all point cloud sets is counted to calculate the mean and variance of each three-dimensional grid; then, each three-dimensional grid is refined in the z direction and calculated as the score after the point cloud to be matched hits the target grid; finally, point cloud registration and positioning are performed. The present invention uses multivariate statistical information to describe the characteristics of the three-dimensional scene, divides the scene into grids of different resolution sizes, and uses a global search method to achieve global positioning.

This application discloses a method and apparatus for edge location detection, a self-moving device, a storage medium, and a program product. The edge location detection method includes: performing at least one region update operation during the movement of the self-moving device to update the target region; if a target region update is detected, updating the target map information to the attribute information of each first location point; if, based on the target map information, it is determined that among the multiple first location points, at least one target location point's height information conforms to a preset height range, determining the edge location based on at least one target location point. This method can reduce the storage space occupied by the self-moving device's map storage during edge location identification.

A GNSS multipath signal suppression method based on TVF-EMD-SVD, firstly, a GNSS signal containing multipath effect is subjected to time-varying filtering empirical mode decomposition to obtain m intrinsic mode function components, and multipath signals are often concentrated in low-frequency intrinsic mode function components. The m intrinsic mode function components obtained by decomposition are used to construct a time-frequency matrix, and the time-frequency matrix constructed by IMF components is subjected to singular value decomposition to decompose the frequency components of the multipath signal into different time-frequency subspaces, and then the correlation coefficient between the autocorrelation function of each time-frequency subspace and the autocorrelation function of the original signal is calculated, and the time-frequency subspace with a correlation coefficient greater than or equal to 0.5 is selected for signal reconstruction, thereby achieving suppression of multipath signals. The present invention can avoid the mode aliasing that occurs when EMD is decomposed, and at the same time, for the problem that the reconstruction order cannot be accurately selected when SVD is used for noise reduction, the autocorrelation function and the autocorrelation coefficient are introduced to help SVD to accurately select the reconstruction order.

The invention discloses a drying method for fresh traditional Chinese medicinal materials, which comprises the following steps: firstly, primarily drying the cleaned fresh traditional Chinese medicinal materials by using steam, then controlling the initial air expansion pressure ratio by using compressed air, quickly cooling to-20 to-60 DEG C within 10-30 minutes, and finally changing the air expansion pressure ratio to dry. And the refrigerated mixed gas is blown to the surfaces of the traditional Chinese medicinal materials in the form of cold dry air which is 10-30 DEG C lower than the eutectic point of the traditional Chinese medicinal materials, so that the moisture content of the traditional Chinese medicinal materials is reduced to 12% or below. The drying method has the advantages of being high in freezing speed, low in cooling temperature and high in drying speed, enzyme and sensitive chemical components can be comprehensively reserved, the content of the enzyme and the sensitive chemical components is high, the use requirements of the fresh traditional Chinese medicinal materials are met, a theoretical basis is provided for drying treatment of the fresh traditional Chinese medicinal materials, and the cost is reduced. Technical support and reference methods are provided for quality control of traditional Chinese medicinal materials, and the method is suitable for popularization and application.

The present invention belongs to the technical field of vehicle environment perception, and specifically discloses a vehicle environment perception method based on multi-view and multi-scale feature fusion. This method aims at the problem of information loss in the projection process of the projection-based point cloud segmentation method, and builds a vehicle environment perception network based on multi-view and multi-scale feature fusion. In terms of network input, the present invention uses multi-layer distance view representation and bird's-eye view feature dual encoding to design a multi-level multi-projection fusion deep learning network, which effectively improves the information extraction accuracy of targets in point clouds with prominent vertical information and long distances, and reduces the information loss of separated projections. In terms of network structure, the present invention proposes a multi-view fusion module, which combines MFB and MMViT to calculate the high-order correlation between BEV features and RV features, and deeply fuses multi-view features. The present invention is conducive to avoiding losses incurred during the projection process and improving the vehicle environment perception capability.

The invention relates to the technical field of noise reduction, in particular to an FPGA (Field Programmable Gate Array)-based noise reduction method, which comprises the following steps of: S1, converting an image into two mif files which can be identified by an FPGA as an operation image and a backup image, and storing the two mif files through a storage module; s2, performing 5 * 5 Gaussian Laplacian operator convolution on the operation image, and thresholding the operation image; s3, using templates of sobel operators in four directions of 0 degree, 45 degrees, 90 degrees and 135 degrees to calculate maximum first-order partial derivatives in four directions at a central point in the 7 * 7 array; and S4, for a suspicious zero cross point, when the direction of the suspicious zero cross point is consistent with the solved normal direction of the gradient at the central point, the point is considered as a true zero cross point. According to the noise reduction method based on the FPGA, the image obtained by sleeving the image edge noise reduction model into the image splicing model and the backup image are extracted to obtain the noise reduction image, so that the image noise reduction effect is improved, the image edge continuity is better, and more details are reserved.

The invention relates to an adipose tissue active material as well as a preparation method and application thereof, and the adipose tissue active material is prepared by the following method: (1) taking adipose tissue and cutting into pieces; (2) adding 0.05 wt%-0.1 wt% of a type I collagenase solution, uniformly mixing, and digesting; (3) centrifuging a digestion product at 1000g-3000g for 5-15 minutes, and taking a middle-layer clear liquid 1; and (4) centrifuging the middle-layer clear liquid 1 at 2000g-3000g for 5-10 minutes, taking middle-layer clear liquid 2, filtering, and taking filtrate, so as to obtain the traditional Chinese medicine composition. The adipose tissue active material retains more bioactive components, has better anti-oxidation, anti-apoptosis and inflammation regulation effects, and has great application prospects in treatment of tissue repair related diseases including myocardial infarction, acute kidney injury, acute liver injury and the like; and the preparation method is efficient, simple and short in time consumption.

The present application relates to a kind of low-dose X-ray CT image-oriented noise removal method, by the method of semi-supervised contrast learning, low-dose CT image is removed noise by teacher-student consistency network and prior knowledge transfer method, reduce effective information loss, retain more detail information, to provide high-quality input data for subsequent image reconstruction, realize the reconstruction of high-quality CT image under low-dose X-ray condition.Compared with the traditional method based on low-pass filter or image statistics, the present application can better remove noise, so that the image after denoising is more real and clear, and by adjusting its network structure and hyperparameter, it can be applied to various low-dose CT image denoising tasks, including different scanning modes, different organs, etc., with high versatility and scalability.

The present application relates to the technical field of waterborne polyurethane materials, and particularly relates to a low VOC waterborne PU foam pad and a preparation method thereof. The foam pad is formed by foaming and curing of a waterborne polyurethane dispersion, and two types of aldehyde-trapping sites are simultaneously introduced into the same porous framework, i.e. an amidoxime group formed by post-conversion of a nitrile group precursor by hydroxylamine, and an aminooxy group obtained by coupling and deprotection of T-BOC-aminooxy-diglycol-amino through a carboxyl anchoring site under an EDC and NHS activation system; and a water-dispersible blocked polyisocyanate crosslinking agent is used to form a crosslinking network by pyrolytic deblocking, so as to achieve rapid capture and durable retention of aldehydes such as formaldehyde and acetaldehyde under water washing and humid heat conditions, and simultaneously help to reduce VOC emission of the material.

The invention discloses a handwritten Chinese recognition method and system based on text detection and text recognition, and the method comprises the steps: inputting a to-be-recognized document image into a trained text detection model, and obtaining a text detection result; the trained text detection model firstly performs preprocessing operation on a to-be-recognized document image, performs feature extraction on a preprocessing operation result, performs feature fusion on extracted features, performs regression operation and probability graph prediction on fused features, and generates a textbox based on a predicted probability graph; inputting the text detection result into the trained text recognition model to obtain a text recognition result; the method comprises the following steps of: preprocessing a text region image in a text box, performing image augmentation processing on the preprocessed text region image, executing block embedding operation on the image subjected to the augmentation processing, performing global fine-grained feature extraction on the image subjected to the block embedding operation, and identifying the extracted global fine-grained features. And obtaining a text recognition result.

The utility model discloses a kind of forage chopping rubbing silk integration regulating device, including support leg four, four The top end of the support leg is fixedly connected with shell, transmission assembly is fixedly arranged on the shell one side, adjusting assembly is fixedly arranged on the shell top end, the adjusting assembly includes handle, the bottom end of the handle is rotatably connected with reduction gearbox, the bottom end of the reduction gearbox is fixedly connected with support column.The utility model discloses a kind of forage chopping rubbing silk integration regulating device, by setting adjusting assembly, staff only needs to swing handle, hammer piece component can be slightly displaced along vertical direction, reach the effect of fine adjustment, by controlling the gap between hammer piece component and rubbing board, corresponding finished product can be produced according to requirement, when gap is smaller, the forage output can be finer and softer;When gap is larger, relatively thick forage finished product can be produced, can retain more fiber.

The invention provides an improved papermaking process and device for high-bulkiness, high-water-absorption and high-strength moisture absorption paper, and relates to the technical field of pulping and papermaking engineering, and the improved papermaking process specifically comprises the following steps: defibering New Zealand thermo-mechanical pulp; after the defibered chemical long fibers and the defibered thermo-mechanical pulp are put into different pulp pools respectively, pulping operation is conducted through a complete dissociation sand removing machine and double-disc grinding equipment; mixing different pulps after beating, and adding polyester fibers, a wet strength agent and other wet end additives into the mixed pulp; performing fiber paper surface forming on the fed mixed pulp through a fourdrinier wire and a top wire forming device; squeezing and drying the formed fiber paper surface; the squeezed and dried paper is glued; and carrying out infrared drying on the gluing layer on the paper. According to the improved papermaking process and device for the high-bulk, high-water-absorption and high-strength moisture absorption paper, the water absorption efficiency and the water absorption capacity of the moisture absorption paper are improved, and the strength of the moisture absorption paper is improved.

The invention belongs to the technical field of wastewater treatment, and particularly discloses an iron monatomic modified copper film and a preparation method and application thereof. The preparation method comprises the following steps: mixing a nitrogen-doped carbon material, ferric salt and a solvent, and carrying out carbonization reaction to obtain nitrogen-doped iron single atoms; then copper powder is adopted for modifying the foamy copper, and modified foamy copper is obtained; and finally, the surface of the modified foamy copper is coated with nitrogen-doped iron single atoms, and the iron single atom modified copper film is obtained. Wherein the nitrogen-doped carbon material is obtained by sequentially carrying out hydrothermal reaction, salt sealing and carbonization reaction on aluminum salt and 2-aminoterephthalic acid. The obtained iron monatomic modified copper film is stable in property and can be used for degrading organic pollutants in wastewater for a long period; in addition, activation of PMS can be accelerated, and the degree of mineralization is improved. The invention also solves the problems that the traditional powdery catalyst is difficult to recover and easily causes secondary pollution.