Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

42results about How to "Reduce identification costs" patented technology

RFID chip image anomaly detection method and system based on intelligent learning

The invention relates to the technical field of RFID chip manufacturing, in particular to an RFID chip image anomaly detection method and system based on intelligent learning. The method comprises the following steps: acquiring a real-time RFID chip sampling image set, performing feature alignment based on a registration template, generating an average grey-scale map by using an alignment image set, and obtaining a chip edge mask image set by using an edge search algorithm; segmenting the edge mask image set of the RFID chip to obtain an effective edge mask variance image set of the RFID chip; integrating the variance image set to obtain a pre-generated variance image; acquiring field environment data of the RFID chip and performing sensitivity coefficient estimation to obtain an edge sensitivity coefficient; and performing convolution filtering smoothing processing on the pre-generated variance image to obtain a chip edge variance image, and constructing an RFID chip image anomaly detection model based on the edge variance image and the average grey-scale image. According to the invention, the detection accuracy and stability are improved.
Owner:SUZHOU XINCHUAN INTELLIGENT EQUIPMENT CO LTD

Method for noninvasive prenatal genetic relationship judgment by adopting two-state SNP (Single Nucleotide Polymorphism) sites

PendingCN119120711AReduce identification costsMicrobiological testing/measurementObstetricsPhysiology
The invention relates to the field of biological detection, in particular to the field of paternity test and detection, and particularly relates to a method for non-invasive prenatal genetic relationship judgment by adopting a two-state SNP (Single Nucleotide Polymorphism) site. According to the method, the minimum number of SNP sites required for judging the genetic relationship is calculated, the genetic relationship is judged by screening the sites containing fetal information in the free DNA sample of the pregnant woman and combining the indexes, the genotype of the pregnant woman sample does not need to be additionally detected, meanwhile, whether the parent-child relationship between a fetus and a suspected parent conforms to the parent-child relationship or not can be accurately judged, and the application range is wider.
Owner:上海蓝沙生物科技有限公司

Rice high-yield salt-tolerant molecular marker and application thereof

The invention belongs to the technical field of agricultural biology, and relates to a rice high-yield salt-tolerant molecular marker and application thereof. The rice high-yield salt-tolerant molecular marker is located at the 615th and 560th sites of chromosome 6 of a rice reference genome IRGSP1.0, and the polymorphic site is G / A. The invention further discloses a preparation method of the rice high-yield salt-tolerant molecular marker. The high-yield and salt-tolerant characteristics of the germplasm carrying the A nucleotide allelic variation at the site are obviously lower than those of the germplasm carrying the G nucleotide allelic variation, specifically, the yield of the GG genotype is the highest, the yield of the GA genotype is the middle, and the yield of the AA genotype is the lowest. By utilizing the molecular marker and the corresponding identification method, the genotype can be accurately and rapidly identified in the accurate design of the high-yield salt-tolerant rice, the phenotype identification cost of a field test in the later period is reduced, and the application of an accurate design technology of the rice in breeding is promoted.
Owner:THE INST OF BIOTECHNOLOGY OF THE CHINESE ACAD OF AGRI SCI

Head-removed shrimp posture detection method based on machine vision

A head-removed shrimp posture detection method based on machine vision comprises the following steps: carrying out three-channel separation on a head-removed shrimp image in an HSV space, and selecting an optimal channel according to a foreground and background difference to obtain a head-removed shrimp binary image; obtaining three distance transformation heat maps of the binarized image of the head-removed shrimp, and selecting an optimal heat map according to the extraction matching degree of the central area of the shrimp head to obtain a central area image of the shrimp head; performing corner detection on the prawn head center area image, and fitting corner coordinates through a straight line to obtain a prawn head and prawn back orientation datum line; comparing the distances between the two wide sides of the minimum enclosing rectangle of the binarized image of the head-removed shrimp and the two end points of the shrimp head orientation datum line to obtain a shrimp head orientation vector; comparing the distance between the long side, tightly attached to the shrimp back, in the minimum bounding rectangle of the binarized image of the head-removed shrimp and the two end points of the shrimp back orientation datum line to obtain a shrimp back orientation vector; and the orientation vectors of the shrimp head and the shrimp back represent the attitude information of the head-removed shrimp. The method can accurately and stably detect the postures of the head-removed shrimps at low cost, and belongs to the shrimp posture image processing technology.
Owner:SOUTH CHINA AGRICULTURAL UNIVERSITY

A guava ISSR-PCR molecular marker combination and its application

The present invention discloses a guava ISSR-PCR molecular marker combination and its application, which mainly realizes the function of identifying guava genetic diversity analysis based on an ISSR primer set composed of SEQ ID NO: 1 to 10. And the primer set in the present invention can achieve high-precision measurement work with a larger sample size compared to the traditional method, and the identifiable polymorphism is as high as 89.68%. Moreover, based on this method, its band resolution is higher, the amplified fragments are clearer, the reaction is more stable, the polymorphism recognition is higher, and the identification of large quantities of experimental materials can be completed in a short time. It can accurately distinguish the relationship between guava germplasm resources, which is of great significance to the identification of guava germplasm resources.
Owner:POMOLOGY RES INST GUANGDONG ACADEMY OF AGRI SCI

User intention recognition method, interaction method, device, system, equipment and medium

ActiveCN114580426BGuaranteed to determine the accuracyReduce identification costsDigital data information retrievalSemantic analysisDegree of similarityData science
The disclosed embodiments relate to a method for identifying user intent, an interaction method, an apparatus, a system, a device, and a medium, wherein the method for identifying user intent may include: obtaining a user request sentence to be identified; obtaining at least one user intent sample that matches the user request sentence according to a text similarity algorithm; and determining the user intent implied in the user request sentence from at least one user intent sample according to a sentence implication model. The technical solution provided by the disclosed embodiments does not require the construction of a large number of user sentence samples and the annotation of a large number of user intents during the process of identifying user intent, and the cost of identifying user intent is low. At the same time, the solution has high generalization and can be applied to any intelligent interaction scenario that requires identifying user intent.
Owner:ALIBABA GROUP HOLDING LTD

Device type identification method based on flow sampling, terminal devices and storage media

This invention discloses a device type identification method, terminal device, and storage medium based on traffic sampling. It eliminates the need to collect complete device traffic data; device identification is achieved simply by sampling traffic at the gateway. To address the issue of missing traffic features, traditional tensor imputation algorithms learn the embeddings corresponding to tensor rows, columns, and depths, but cannot generalize to unknown rows, columns, or depths. This results in repeated retraining, time-consuming and costly feature imputation. This invention proposes an inductive tensor imputation method that utilizes historical information to learn and generate embedding functions, enabling fast and effective device traffic feature imputation.
Owner:HUNAN UNIV

An identification device for protected area or habitat bird species diversity assessments

ActiveCN116973935BAchieve regular self-cleaningImprove outdoor battery lifeCamera lensLiquid storage tank
This invention belongs to the technical field of bird diversity monitoring equipment, specifically relating to an identification device for assessing bird species diversity in protected areas or habitats. It includes an installation unit, a monitoring unit located at the top of the installation unit, and a lidar located at the top of the monitoring unit. The monitoring unit and the lidar are controlled to rotate by motor one and motor two, respectively, to monitor bird activity. An infrared camera is mounted on the outer end face of the monitoring unit, and a lens cleaning mechanism and a liquid storage tank are located at the top of the infrared camera. This invention enables motor two to drive the lidar to monitor bird spatial location information in real time, while simultaneously coordinating with a pressurization component to pressurize the liquid channel within the lens cleaning mechanism. This allows the cleaning fluid to be periodically sprayed out, achieving periodic self-cleaning of the infrared camera lens. This eliminates the need for an external spray nozzle control circuit and program, reducing device cost and overall power consumption, and increasing the outdoor operating time of the identification device.
Owner:NANJING INST OF ENVIRONMENTAL SCI MINIST OF ECOLOGY & ENVIRONMENT OF THE PEOPLES REPUBLIC OF CHINA

Pig posture recognition method, device and equipment, storage medium and program product

The invention provides a pig posture recognition method, device and equipment, a storage medium and a program product, and relates to the technical field of computer vision. The method comprises the following steps: inputting a pig image into a first feature extraction layer in a posture recognition model to obtain an initial feature map; inputting the initial feature map into a second feature extraction layer in the posture recognition model to obtain at least one hierarchical feature map; inputting the initial feature map and the at least one hierarchical feature map into a feature fusion layer in a posture recognition model to obtain a fused feature map; the feature fusion layer is used for up-sampling the input feature maps of different scales into up-sampling feature maps of which the scales are preset initial scales, and carrying out feature fusion on the up-sampling feature maps to obtain a fused feature map; and inputting the fused feature map into a posture recognition layer in a posture recognition model to obtain a pig posture recognition result. The pig posture recognition accuracy can be improved, and the pig posture recognition cost is reduced.
Owner:SHANGHAI IFLYTEK HEGUANG TECHNOLOGY CO LTD

Tobacco and fast-moving consumer goods display shape recognition method and apparatus

This application relates to a method and apparatus for recognizing the display shape of tobacco and fast-moving consumer goods, including acquiring an image to be detected and performing product location recognition and product specification recognition to obtain location and specification recognition results that represent the location and specification information of each product; determining the global boundary points and minimum bounding rectangle of the product area in the image to be detected based on the location and specification recognition results, performing perspective transformation on the image to be detected based on the global boundary points and minimum bounding rectangle to obtain geometric correction results; performing cluster analysis on the products based on the geometric correction results, constructing a grid canvas based on the cluster analysis results to obtain grid construction results; determining the product whose specification information represents the target specification as the target product based on the location and specification recognition results and the grid construction results, and determining whether the actual display shape of the target product conforms to the target display shape based on the unique location of the target product to obtain the display shape recognition result.
Owner:SHENZHEN AIMALL TECHNOLOGY CO LTD

A crude oil identification method and device based on structure-oriented lumping

PendingCN122842747AReduce identification costsImprove recognition efficiency
A crude oil identification method and device based on structure-oriented lumping, the method comprising: obtaining multiple property values of crude oil to be identified from a calibration report of crude oil detection; analyzing the multiple property values of the crude oil in combination with a first molecular structure database established in advance to determine SOL molecular structure data of the crude oil; comparing the SOL molecular structure data of the crude oil with SOL molecular structure data in a second molecular structure database established in advance to determine a crude oil sample with the maximum similarity; and taking the crude oil sample with the maximum similarity as an identification result.
Owner:RICHFIT INFORMATION TECH +1

High-pressure oil way OMV abnormal work identification method and device, diesel engine and medium

The invention provides a high-pressure oil way OMV abnormal work recognition method and device, a diesel engine and a medium, and belongs to the technical field of engine fuel injection control. The method comprises the steps that the first rail pressure deviation of a first OMV in the working time period and the second rail pressure deviation of a second OMV in the working time period are determined based on a control item of a PID algorithm; and when the first rail pressure deviation is smaller than or equal to the deviation threshold value and the second rail pressure deviation is larger than the deviation threshold value, it is determined that the first OMV works abnormally. Whether the first OMV works abnormally or not is determined according to the first rail pressure deviation and the second rail pressure deviation, the working state of the OMV mechanical part in the normal state of the OMV driving circuit can be recognized, and the recognition accuracy of the working state of the OMV is improved.
Owner:DONGFENG COMML VEHICLE CO LTD

Automatic spontaneous development identification method based on enhanced spatial-temporal characteristic network

The invention relates to the technical field of video recognition and echocardiogram video automatic analysis, and particularly provides an automatic spontaneous development recognition method based on an enhanced spatial-temporal feature network, and the method comprises the steps: carrying out the preprocessing of a to-be-recognized video, and obtaining a video frame set; wherein the video to be identified is a transesophageal echocardiogram video; inputting the video frame set into a trained automatic spontaneous development recognition model, and outputting a corresponding spontaneous development recognition result by using the automatic spontaneous development recognition model; wherein the automatic spontaneous development recognition model is obtained by training according to a plurality of training data, and the training data comprise transesophageal echocardiography videos; the automatic spontaneous development recognition model comprises an attention map creation module, a spatial-temporal feature extraction module and a classification module. According to the automatic spontaneous development recognition method based on the enhanced spatial-temporal feature network, the data cost can be effectively reduced, and the recognition accuracy is high.
Owner:SUZHOU UNIV

Methods, apparatus and electronic equipment for lithological identification of tight gravelly sandstone reservoirs through well logging

This invention relates to the field of lithology identification methods, specifically a method and apparatus for identifying lithology in tight gravelly sandstone reservoirs through well logging. The method includes: determining key sensitive parameters for different lithologies within a target tight gravelly sandstone reservoir; establishing Q-models for specific lithologies and other lithologies based on the key sensitive parameters; identifying samples of specific lithologies based on the Q-models for those lithologies; and identifying samples of other lithologies based on the Q-models for those lithologies. This invention achieves precise identification and quantitative characterization of lithology in tight gravelly sandstone reservoirs, providing an intuitive and effective reference for subsequent calculations of tight reservoir parameters. It enables the identification and characterization of lithology using conventional well logging data, significantly improving the efficiency and reducing the cost of well logging interpretation.
Owner:PETROCHINA CO LTD

A method for evaluating the carbon management level of an enterprise

PendingCN122713866AWide recognition coveragekeep intact
The application discloses a kind of enterprise carbon management level evaluation methods, it is related to enterprise carbon management level evaluation technical field, existing enterprise carbon neutral management system has not been established, lack clear enterprise carbon neutral development evaluation framework;Existing enterprise disclosure type document identification extraction efficiency is poor.The present application provides a kind of enterprise carbon management level evaluation method, adopts the double-channel fusion architecture of original text fast channel, multi-modal visual identification main channel, and channel decision is carried out to each page respectively;Through multidimensional quality heuristic determination to original text flow, the page of insufficient reliability is automatically abandoned, and visual identification is turned into;Identification cost is significantly reduced, and identification stability is improved;Build the enterprise carbon neutral management and development CROCS model including sure carbon, carbon reduction, carbon offset, carbon emission and carbon stimulation five modules;Based on the model, the development of enterprise carbon neutral is evaluated.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Molecular marker for rapidly identifying transverse diameter of cucumber fruit, identification method and application

The invention discloses a molecular marker for rapidly identifying the transverse diameter of a cucumber fruit, an identification method and application, and belongs to the technical field of cucumber fruit shape identification. The invention provides two molecular markers T6-1 and W6-4 which are closely linked with the transverse diameter of a cucumber fruit, the T6-1 and the W6-4 are located in a chromosome 6, and the physical distance is 141.89 kb; the small-transverse-diameter fruits are exchanged between the molecular markers T6-1 and W6-4, the genotype of the molecular markers T6-1 and W6-4 in a long-fruit inbred line is set as AA, the genotype of the molecular markers W6-1 and W6-4 in a round-fruit inbred line is set as BB, the bands of the molecular markers T6-1 and W6-4 in the small-transverse-diameter fruits are set as AB or BA, and the bands of the molecular markers T6-1 and W6-4 in the large-transverse-diameter fruits are set as BB; by adopting the molecular marker and the identification method provided by the invention, the transverse diameter of the cucumber fruit in the commercial melon period can be rapidly detected in the seedling stage, the identification time is greatly shortened, the identification cost is saved, and the identification result is not influenced by environmental factors and is stable and reliable; the method has important significance in simplifying cucumber shape breeding work and promoting cucumber shape breeding process.
Owner:SHANDONG AGRICULTURAL UNIVERSITY

Mobile phone PIN lock screen password recognition method and system based on computer vision

The present invention belongs to the technical field of video analysis, and discloses a method and system for identifying a mobile phone PIN lock screen password based on computer vision, collects videos containing the process of a user unlocking a mobile phone screen through a PIN code, detects the positions of fingertips and numeric keys appearing in the video frame, and automatically determines whether it belongs to the unlocking process according to the detection situation; calculates the touch point according to the detected fingertip position and uses the optical flow algorithm to assist in tracking the fingertip movement; calculates the overall keyboard layout according to the local numeric key position, and uses the affine mapping principle to fine-tune the keyboard position when there is occlusion; uses the optical flow method to calculate the fingertip motion parameters, and determines the movement or pressing state of the fingertip according to the speed and acceleration; finally, calculates the possible pressed digital sequence through the position and motion state, and outputs the three groups of PIN sequences that the user is most likely to press after the unlocking process is completed. The present invention uses a machine learning algorithm to replace the manual processing steps to reduce the recognition cost.
Owner:XIDIAN UNIV

Specific SNP (Single Nucleotide Polymorphism) site combination and primer for identifying red and white pitaya and hybrid seeds and application of specific SNP site combination and primer

The invention discloses a specific SNP (Single Nucleotide Polymorphism) locus combination for identifying red and white pitaya and hybrids, which comprises 10 SNP loci, and the 10 SNP loci are obtained by screening through multiple standards such as FST, allele frequency difference and LD pruning on the basis of SLAF-seq data of 45 core germplasms. The specific SNP site combination can be used for accurately distinguishing red-pulp pitaya, white-pulp pitaya and filial generations thereof, the problem of germplasm identification caused by phenotype confusion and interspecific hybridization is solved, and an accurate, efficient and low-cost molecular identification tool is provided for pitaya germplasm resource management, parent selection, molecular breeding and the like. The invention also discloses a primer for amplifying the specific SNP sites and application of the specific SNP site combination.
Owner:POMOLOGY RES INST GUANGDONG ACADEMY OF AGRI SCI

A method and device for detecting a roll-shaped material, an electronic device and a storage medium

This invention provides a method, apparatus, electronic device, and storage medium for detecting rolled materials. The method involves acquiring the center of the side boundary of the rolled material, scanning the side boundary along any direction from the center to obtain marker point and contour point data, fitting the contour point data to a reference line in the corresponding direction based on the marker points, and performing multiple straight line fittings on the contour point data using the reference line as a reference to obtain multiple fitted straight lines. The roll state is determined based on the reference line and the fitted straight lines. This application reduces labor costs by automatically detecting the contour point data of rolled materials. By fitting the shape of the rolled material to the contour point data, multiple fitted straight lines are obtained. The roll state of the rolled material is judged based on the relationship between the straight lines, and the output results are directly transmitted to subsequent processes, facilitating adjustments by the robot and improving production efficiency.
Owner:CISDI RES & DEV CO LTD

Charging pile identification method and device

PendingCN121947237AEliminate the process of on-site inspection and identificationImprove charging experienceCharging stationsReliability engineeringElectrical and Electronics engineering
The embodiment of the invention discloses a charging pile identification method and device. According to the method, charging messages reported in the charging process of a to-be-identified charging pile are analyzed, a multi-gun parallel charging self-checking result is stored as to-be-rechecked charging messages, and when the number of the to-be-rechecked charging messages is larger than a preset number, the to-be-rechecked charging messages are reversely checked to determine a corresponding target charging order. And if the average current value of the target charging order is greater than a preset current value, determining that the target charging order is a multi-gun parallel charging order, and when the number of the multi-gun parallel charging orders corresponding to the to-be-identified charging pile is greater than a preset order number, determining that the to-be-identified charging pile supports multi-gun parallel charging. According to the method, whether the to-be-identified charging pile supports multi-gun parallel charging is automatically identified based on the charging message reported by the to-be-identified charging pile, so that the process of field inspection and identification of operation and maintenance personnel is omitted, the identification cost is reduced, and appropriate charging piles are matched for different types of vehicles according to the identification result.
Owner:ZHEJIANG XIAOJU GREEN ENERGY TECHNOLOGY CO LTD

Vehicle speeding detection methods, devices, equipment and storage media

ActiveCN117854292Bimprove accuracyReduce identification costs
This invention discloses a vehicle speeding identification method, device, equipment, and storage medium. The method includes: when a vehicle is detected traveling on the road, determining the vehicle's position offset within a target time period based on the vehicle's position coordinates in a target coordinate system at different times; determining the vehicle's positioning interval time; determining the driving speed at each stage based on the positioning interval time and the vehicle's position offset within the target time period; determining the current driving speed based on the vehicle's position offset within the target time period; and comprehensively identifying the vehicle as speeding based on the driving speed at each stage and the current driving speed. By using the above method, determining the vehicle's position offset within the target time period based on its position coordinates at different times, determining the current driving speed, and determining the driving speed at each stage based on the positioning interval time, and then comprehensively identifying the vehicle as speeding based on the target speed limit, the accuracy of identifying vehicle speeding can be effectively improved, and the identification cost can be reduced.
Owner:GEER TECH CO LTD

Low-resistivity oil layer identification method

PendingCN119572221AHigh measurement accuracyReduce identification costsSurveyPorosityWell drilling
The invention relates to a low-resistivity oil reservoir identification method, and belongs to the field of low-resistivity oil reservoir identification, and the low-resistivity oil reservoir identification method comprises the steps: obtaining the porosity, resistivity and historical oil test and production test data in historical drilling data, building a corresponding physical property-electrical property-oil content relation chart for each sedimentary microfacies by using the data, and obtaining the corresponding physical property-electrical property-oil content relation chart for each sedimentary microfacies; acquiring a porosity lower limit and a resistivity lower limit corresponding to the oil reservoir under each sedimentary microfacies through the drawing board, and taking the porosity lower limit and the resistivity lower limit as standards for determining whether the corresponding sedimentary microfacies reservoir contains oil or not; different identification standards are set for different sedimentary microfacies reservoirs, so that the identification accuracy of the low-resistivity oil reservoir is improved.
Owner:CHINA PETROLEUM & CHEMICAL CORP +1

Method and system for identifying mixed batches of PCBs, electronic equipment and medium

The invention relates to the technical field of PCB batch management, in particular to a method and system for identifying mixed batches of PCBs, electronic equipment and a medium, and the method comprises the following steps: distributing a detection through hole identifier for each batch of PCBs; the method comprises the following steps: acquiring panorama images of to-be-tested PCBs in batches, and sequentially performing graying and binarization processing on the panorama images; carrying out image registration and difference operation on any group of binarized images in the binarized images of the PCBs to be detected in batches to obtain a difference image; dividing the PCB to be detected corresponding to the full-homodyne image into the same batch, marking a feature identifier on the corresponding binary image, performing similarity analysis on the non-homodyne image to obtain a similarity analysis value, and performing batch identification based on the similarity analysis value and the feature identifier corresponding to the binary image; and outputting batch identification results of the to-be-detected PCBs in batches. Through batch detection, the detection efficiency is higher, and the batch identification requirement of PCBs of the same size can be met.
Owner:SICHUAN MEIJIESEN CIRCUIT TECH CO LTD

A method, device and apparatus for identifying the judgement area in a court trial video screen

This article relates to the field of image recognition, and in particular to a method, device and equipment for identifying the judge's desk area in a court trial video screen. The method includes performing a first feature recognition on the court trial video screen to obtain a human area, wherein the first feature is a human body feature; performing a second feature recognition on the human area to obtain a judge's desk sub-area, wherein the second feature is a predetermined feature of the judge; and combining the judge's desk sub-areas to obtain the judge's desk area in the court trial video screen. Through the embodiments of this article, the recognition of each stationary object in the entire court trial video screen is avoided, and the amount of calculation for detecting the court trial video screen is reduced, thereby improving the efficiency of detecting the judge's desk area in the court trial video screen and saving the recognition cost. In addition, according to the characteristic that the predetermined features of judges in different courts are the same, the method described in the embodiments of this article is applicable to the recognition of the judge's desk area in all court trial video screens, thereby improving adaptability.
Owner:CHINASYS TECH

Iris recognition method and device

The present application relates to the field of artificial intelligence technology, and specifically discloses an iris recognition method and device, wherein the method comprises: obtaining standardized three-dimensional iris image data of an iris to be recognized; using a two-dimensional convolutional neural network to extract and classify features of the standardized three-dimensional iris image data, and obtaining target feature data and a target user label corresponding to the iris to be recognized, wherein the two-dimensional convolutional neural network comprises a three-dimensional image processing layer, and the three-dimensional image processing layer performs dimensionality reduction processing on the standardized three-dimensional iris image data to obtain multiple two-dimensional iris image data, and the multiple two-dimensional iris image data include oblique section data; retrieving iris feature data corresponding to the target user label from a three-dimensional iris image database, wherein the three-dimensional iris image database stores iris feature data of each user among multiple users; generating an iris recognition result according to the target feature data and the retrieved iris feature data. The above scheme can improve the accuracy of iris recognition.
Owner:INDUSTRIAL AND COMMERCIAL BANK OF CHINA

Element recognition point data processing method and device, electronic equipment and storage medium

ActiveCN117435680BEnsure coverageensure completenessPattern recognitionEngineering
The application provides an element recognition point data processing method and device, electronic equipment and a storage medium, relates to the technical field of electronic maps, can be applied to various scenes such as cloud technology, artificial intelligence, intelligent transportation and auxiliary driving, and the method comprises the following steps: receiving recognition point data of a road image reported by a terminal; performing initial aggregation processing on the recognition point data based on a time sequence to obtain a plurality of recognition point sequences; extracting a recognition point subsequence corresponding to an element label of at least one element type from each recognition point sequence of the plurality of recognition point sequences; determining a recognition target difference and an image time difference between two adjacent recognition point data in the recognition point subsequence; and performing same element aggregation on the recognition point data in the recognition point subsequence according to the recognition target difference, the image time difference and an element similarity condition to obtain a target sequence segment corresponding to the recognition point subsequence. The application can ensure the coverage and integrity of road elements and reduce the cost of the terminal.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Method for identifying resistance of japonica rice sheath blight disease

The invention provides a japonica rice sheath blight resistance identification method, and belongs to the technical field of plant disease resistance identification. The invention provides a method for identifying the sheath blight resistance of japonica rice. The method comprises the following steps: planting and culturing japonica rice seeds to be detected in an intelligent greenhouse, performing sheath blight induction from a tillering end stage to a young ear differentiation stage, observing the attack condition of the sheath blight, measuring the average scab length of the japonica rice to be detected, calculating the disease index, and evaluating the sheath blight disease grade of the japonica rice. According to the method, the japonica rice rapidly enters the tillering last stage, the plant requirement of sheath blight identification is met, and the identification period is remarkably shortened; the method can complete simultaneous identification of multiple varieties at the same time, is not limited by other conditions in the field, and reduces the influence of environmental factors, thereby improving the accuracy and repeatability of sheath blight resistance screening. The banded sclerotial blight identification can be carried out for 3-4 times in one year, the dependence on professional equipment and large-area test fields is reduced, the method is more economical and universal, the identification efficiency is improved, and the identification cost is reduced.
Owner:SHANGHAI AGROBIOLOGICAL GENE CENT

Automatic welding position identification method for large workpieces to be welded

ActiveCN114273826BAccurate identification of welding positionseasy to operateWelding/cutting auxillary devicesAuxillary welding devices
The present invention discloses a method for automatically identifying the welding position of a large workpiece to be welded. The method mainly reconstructs the unit model of the large workpiece to be welded by using the PointNetLK++ point cloud registration network model that adds a spatial attention mechanism and a channel attention mechanism on the basis of the PointNetLK network model, and the point cloud data converted from the images of the large workpiece to be welded at different angles collected by a binocular camera, and then extracts the boundary points of the welding model using the gradient change of the normal vector, and then further selects the points to be welded according to the distance from the points at the intersection to different planes, so as to accurately identify the welding position of the workpiece to be welded. The present invention not only effectively reduces the recognition cost, but also greatly improves the accuracy of the three-dimensional reconstruction of large welding models and the accuracy of the recognition of the position to be welded. At the same time, it facilitates the operation and management of welding operations by technicians.
Owner:NANJING OUOT INTELLIGENT TECHNOLOGY CO LTD