86results about How to "Avoid duplicate detection" patented technology

The invention discloses a method for detecting and tracking obstacles in front of a vehicle, aiming to overcome the defect and shortage in detection and tracking of obstacles in front of the vehicle by using a single-type sensor. The method comprises the following steps of: 1. establishing a relation for realizing data conversion between a millimeter wave radar coordinate system and a camera coordinate system; 2. receiving, resolving and processing the millimeter wave radar data, and carrying out preliminary classification on the obstacles; 3. synchronously collecting a camera image and receiving millimeter wave radar data; 4. classifying the obstacles in front of the vehicle: 1) projecting scanning points of the millimeter wave radar data on a camera coordinate system by combining the methods of millimeter wave radar and monocular vision, and establishing a region of interest (ROI) of the obstacles on the image; 2) carrying out preliminary classification on different obstacles in theROI established on the image, and confirming the types of the obstacles by using different image processing algorithms; and 5. tracking the obstacles in front of the vehicle.

The invention provides a method and a device and a system for supporting the ultimate consistency of a micro-service architecture transaction. The method for supporting the ultimate consistency of the micro-service architecture transaction used for a transmitting end comprises the steps that a service call is initiated, the logs are recorded, when the logs are written with actions, uninitiated service calls or logs with not returned results when the specified time is exceeded are checked regularly, and call requests are sent; the returned receipt information is received, the log records are queried, the call treatments are judged whether or not they have been completed according to the log status, if the calls are being treated, the returned results are called, and corresponding transaction interfaces are called according to the returned results, service calls are continually initiated, then through the method for supporting the ultimate consistency of the micro-service architecture transaction used for the message queueing services and the payments of a receiving end, asynchronous data calls for services are achieved through the logs and the message queueing, and the ultimate consistency of inter-service data is finally achieved.

A defect map image generating unit (72) of a defect inspecting device (100) generates a defect map image by combining a plurality of processed images generated by a processed image generating unit (61). The defect map image generating unit (72) has a coordinate calculating unit (721), an integrating unit (722), and a brightness setting unit (723). The coordinate calculating unit (721) calculates the coordinates of each pixel in the defect map image on the basis of the coordinates of each pixel in each processed image, the transport speed of a sheet body (2), and the frame rate set in the imaging device (5). The integrating unit (722) finds the number of defective pixels from among the pixels that had the same coordinates calculated by the coordinate calculating unit (721) and the total of gradation values in the defective pixel. The brightness setting unit (723) sets the brightness for each pixel in the defect map image according to the calculated value by the integrating unit (722).

The invention discloses a detection method, a detection device, a mobile robot and a storage medium, and belongs to the technical field of intelligent robots. The detection method is applied to the mobile robot, and comprises the following steps: detecting a regional environment through a detection sensor by the mobile robot to acquire a first regional environment map; based on the first regionalenvironment map, determining a detection target point, and based on the detection target point, generating a first detection path; in the process of moving according to the first detection path, detecting the regional environment through the detection sensor by the mobile robot to acquire a second regional environment map; when the mobile robot detects that the detection path executed by the mobile robot ends, generating a first detection route by the mobile robot based on the second regional environment map, and determining a third regional environment map according to the first detection path; circularly executing operation of determining the regional environment maps until the mobile robot detects that the whole regional environment map is completely drawn. According to the embodiment of the invention, the time spent for mapping by the mobile robot is shortened and the working efficiency is improved.

The invention provides a small-diameter tube nondestructive testing method based on a phased array ultrasonic flaw detector. The small-diameter tube nondestructive testing method comprises the following steps: carrying out CIVA and sound field simulation on a detected workpiece; debugging the phased array ultrasonic flaw detector by a simulation test block and verifying on a simulated workpiece; grinding two sides of a welding seam of the detected workpiece, detecting the detected workpiece ground smoothly by the debugged phased array ultrasonic flaw detector; and analyzing the detection graph to obtain a detection result. The method can perform CIVA and sound field simulation on the detected workpiece before field detection, and adopts an appropriate comparison test block and the simulation workpiece for debugging the phased array ultrasonic flaw detector; the method adopts different scanning modes according to the different thicknesses of the simulation workpieces in a debugging process, can improve the debugging precision, can improve the field detection sensitivity, can prevent repeated detection, saves the detection time and reduces the detection cost.

The invention discloses a one-step multi-PCR detection method for simultaneously detecting four important citrus pathogenies. According to the method, primers for the four important pathogenies including Citrus tristeza virus, Citrus exocortis viroid, Citrus tatter-leaf virus and Liberobacter asiaticum spreading through grafting are preferably selected, and primer concentration, PCR amplificationcondition and the like are optimized, therefore, the four important citrus pathogenies spreading through grafting can be simultaneously detected. The detection method provided by the invention is quick and accurate, has the advantages of good detection stability, high specificity and high consistency, is suitable for large-scale generalization, and can be used for guiding the introduction of varieties and generalization of detoxifying treatment of seedlings to ensure the safe production of citrus; in addition, by adopting the detection method, repeated detection in the conventional PCR is avoided.

The invention provides a device and method for detecting the smoothness of a laser track, and the method comprises the steps: detecting and obtaining a horizontal base measurement value Xi and a vertical base measurement value Y1 of a to-be-measured position Pi through a photoelectric measurement target; detecting a horizontal random deviation value delta(Xi) and a vertical random deviation valuedelta(Yi) of a laser reference beam through a deviation detection unit on the photoelectric measurement target, and correcting the horizontal random deviation value delta(Xi) and the vertical random deviation value delta(Yi); superposing the horizontal base measurement value Xi and a horizontal random deviation correction value delta(Xi)*Ki, and obtaining an engineering detection value Xi' in a horizontal direction; superposing the vertical base measurement value Yi and a vertical random deviation correction value delta(Yi)*Ki, and obtaining an engineering detection value Yi' in a vertical direction. The method solves a problem that the engineering detection result of a conventional laser smoothness detection device is low in precision and poor in reliability. The method is suitable for other laser alignment engineering measurement in an outdoor environment under the long-distance condition.

The invention provides a ship target detection and recognition method based on deep learning, and the method comprises the following steps: S1, building a pixel attention model, and preprocessing a ship image; S2, generating a ship anchoring frame by using KMeans clustering, and converting a label boundary frame; S3, building a YOLOV3 network structure based on a pixel attention model; S4, training a network by using a training optimization method; and S5, performing post-processing on network output by using a non-maximum suppression algorithm to avoid the problem of repeated detection. According to the ship target detection and recognition method based on deep learning, ship target detection and recognition can be realized under various complex backgrounds and resolutions, and the ship target detection and recognition method has a good application prospect in the fields of ship industry, maritime affair management and the like.

The invention discloses a steel enterprise blast furnace by-product gas emergence size prediction method comprising the following steps: reading emergence size data of blast furnace gas from a real time database of a steel enterprise field; preprocessing a collected original data sequence, and detecting an abnormal value in the blast furnace gas data sequence; inputting the preprocessed data sequence into a set least square support vector machine model for prediction, using an improved particle swarm algorithm to optimize a nucleus width parameter and a punishment factor parameter of the least square support vector machine, thus improving prediction precision. The method is accurate, can fast detect abnormal data in the blast furnace gas emergence size, and can replace the abnormal data in the original data; the least square support vector prediction model based on minimum structure risk is set, and optimized by the improved particle swarm algorithm, thus improving prediction precision of the model, and a prediction result can provide basis for reasonable utilization of the gas resource.

The invention discloses an insulator defect detection method and system, electronic equipment and a readable storage medium, and the method comprises the following steps: inputting a detected power grid aerial image into a pre-trained insulator defect detection model, outputting an insulator defect detection result of the aerial image of the detected power grid through a pre-trained insulator defect detection model, wherein the insulator defect detection model comprises an insulator detection and foreground segmentation module which is used for obtaining an area image only containing an insulator according to an input power grid aerial image; and an insulator defect detection module which is used for judging whether the insulator has defects or not by utilizing an image classification network based on multi-head self-attention and outputting an insulator defect detection result according to the obtained area image only containing the insulator. According to the method, the classification task of power grid aerial image insulator defect detection can be completed, and the technical problem of model precision in the prior art can be specifically solved.

The invention relates to the technical field of vehicles, and discloses a parking space detection method and device. The parking space detection method includes the steps that a reachable area matchedwith a vehicle in an environment where the vehicle is located is detected; parking spaces in the reachable area are identified, and a parkable space is determined from the parking spaces, and parkable position information of the parkable space is saved, so that repeated detection of the parkable space is avoided. By adopting the parking space detection method and device, the parkable space in which the vehicle can park can be determined from the detected reachable area, one or more parkable spaces can be determined, and the position information of the determined parkable space can be furthersaved; when a driver wants to park the vehicle in a missed parkable space, the information of the parkable space can be directly obtained, it is unnecessary to repeatedly detect the parkable space, the time for identifying the parkable space is saved, and therefore the efficiency of automatic parking is improved.

The invention discloses a multi-agent interactive environment perception and path planning movement system. The multi-agent interactive environment perception and path planning movement system specifically comprises a data integration host and a plurality of intelligent cars, the data integration host comprises a data processing unit, a first wireless transmission module and a first data storage module, and every intelligent car comprises a car body, a power system, a processing module, a positioning module, a data acquisition device, a second wireless transmission module and a second data storage module. The multi-agent interactive environment perception and path planning movement system has the advantages that with the aid of collaboration of the data integration host and the intelligent cars, the intelligent cars detect known areas through cameras, infrared sensors and ultrasonic sensors, and the data integration host establishes a real-time global simulation map by combining detection results of the intelligent cars, so that detection paths of the intelligent cars are arranged reasonably, and repeated detection is avoided; the system is capable of detecting the unknown areas automatically without assistance of workers, and accordingly working time is saved and working efficiency is improved.

The invention provides an electric power business hall passenger flow statistics method and system based on target dynamic tracking. The method includes detecting a pedestrian target in the video frame image after image preprocessing; performing de-duplication processing on the detected targets existing in the tracking target list; tracking targets in the tracking target list by using a KCF algorithm and updating target parameters; obtaining the average moving speed of the pedestrian target in the video by analyzing the target parameters; predicting a video frame number and a specific positionwhen the pedestrian target arrives at the counting line according to the average moving speed; using a target detection model of a KCF algorithm to verify the position of the video frame and the pedestrian target existence condition in the neighborhood range of the video frame, and performing counting statistics on the business hall passenger flow according to the verification result and the initial position of the target; according to the invention, the target tracking process is reduced, the calculated amount of the system is reduced, the target tracking performance of the system is improved, and the high execution rate of the system is ensured.

The invention discloses a liver echinococcus gene segment screening method, an amplification primer and a kit.The screening method comprises the following steps: eliminating an influence of a human genome and a close genetic relationship tapeworm group genome from whole genomes of echinococcus granulosus and echinococcus multilocularis; and screening to obtain a third echinococcus granulosus gene segment, a third echinococcus multilocularis gene segment and a common gene segment, and designing three types of amplification primers by using three types of the gene segments respectively. A primer pair group for detecting echinococcosis of human tissues is obtained by further screening and a kit and a use method of the kit are provided based on the primer pair group. False positive results caused by human genes or close genetic relationship tapeworm genes existing in to-be-detected tissue DNA is avoided from the source, the to-be-detected DNA aiming at the primer during design is a human tissue sample, the false negative results in clinical detection are remarkably reduced, specific primers have higher accuracy and higher specificity, and clinical use effects of the primer pair and the kit are obviously enhanced.

The invention relates to a biochemical index detection integrated chip comprising an upper layer and a lower layer; the upper layer and the lower layer are connected in a water tightness manner, the upper layer is provided with a sample through hole, the lower layer comprises a sample tank, a liquid storage tank, a sample waste liquid tank, a sample quantification tank and a micro-reflection surface, and the tanks are connected through flow channels; the sample waste liquid tank is characterized in that the sample waste liquid tank comprises a first waste liquid tank and / or a second waste liquid tank or two or more waste liquid tanks, and freeze-drying reaction reagents are preloaded in the first waste liquid tank and / or the second waste liquid tank or two or more waste liquid tanks. Whenthe chip is used for detecting the pH value, the cost and the consumption of biological samples and reagents can be greatly reduced, and meanwhile, the defect that the pH value cannot be detected through micro-fluidic in-vitro rapid diagnosis is overcome.

The invention belongs to the technical field of machine room management, and discloses a machine room inspection method based on a two-dimensional code technology, which comprises the following steps:generating a two-dimensional code of each inspection device in a machine room by adopting the two-dimensional code technology, and setting the two-dimensional code in the corresponding inspection device; issuing a first inspection task through the server; generating a first inspection route according to the first inspection task; detecting inspection equipment in the machine room according to thefirst inspection route; The two-dimensional code of a to-be-detected device is scanned, if the two-dimensional code of the to-be-detected device is recognized, the to-be-detected device is not detected, detection of the to-be-detected device is conducted, and if the two-dimensional code of the to-be-detected device is not recognized, detection of the to-be-detected device is completed, and detection of the next inspection device is conducted. The same equipment can be prevented from being repeatedly detected by a plurality of inspection workers, and the efficiency is improved. The invention further discloses an electronic device and a storage medium.

The invention discloses an image detection method and device. The image detection method comprises the steps: obtaining a to-be-detected image, extracting a model according to a preset multi-scale feature, extracting multi-scale feature information of the to-be-detected image, carrying out dimension reduction on the multi-scale feature information; obtaining target image feature information; obtaining target image feature information according to the target image feature information, searching historical image feature information according to the target image feature information to obtain a search result, if the historical image feature information matched with the target image feature information exists in the search result, calling a historical detection record corresponding to the historical image feature information, and outputting the historical detection record as a detection result of the to-be-detected image. According to the image detection method, repeated detection is avoided, and richer features can be extracted, and the image can be better described.

The invention discloses a poultry food intake parallel anomaly detection method based on BIM and artificial intelligence. The poultry food intake parallel anomaly detection method comprises the stepsof: splicing and fusing poultry house images to obtain a poultry house panoramic image, and carrying out projection transformation on the poultry house panoramic image to a poultry house building information model; conducting poultry detection on the poultry house panoramic image; carrying out head key point detection on a region-of-interest image of each poultry in a period of time after the foodis fed; carrying out heat map superposition on the poultry head key point thermodynamic diagrams of which the poultry head key points fall into the a feeder region-of-interest within a period of timeafter the food is fed; inputting a superposition result into a poultry abnormal food intake analysis neural network to obtain a poultry abnormal food intake grade, and generating an abnormal food intake signal; and visualizing various kinds of information in the poultry house building information model. According to the poultry food intake parallel anomaly detection method, automatic poultry foodintake state monitoring is realized, the detection efficiency is high, and the detection accuracy is high.

The invention discloses a road detection method and device based on an unmanned aerial vehicle, and a storage medium. The detection method comprises the steps of: obtaining a to-be-maintained road section, and obtaining an inspection path through planning according to the to-be-maintained road section; when an unmanned aerial vehicle flies according to the inspection path, collecting all-road-surface data; obtaining pavement diseases according to the all-road-surface data, and recording parameter information of the pavement diseases; and acquiring position information of the unmanned aerial vehicle, and identifying the parameter information on the to-be-maintained road section according to the position information to obtain a road surface disease positioning map. The method is helpful forrealizing automatic and intelligent detection of the road, effectively reduces the road detection cost and improves the road detection efficiency.

The present invention discloses a vacuum and pressure test bench for full pipelines of a braking system and relates to the field of automobile braking system testing. The device comprises: a frame body, a collecting device and a transmission device, wherein a brake fluid pot, a boosting device and a pipeline system are provided on the frame body, a pipeline system is disposed on the frame body, the brake fluid pot is in communication with the pipeline system through the boosting device, the collecting device is disposed on the pipeline system and is configured to collect vacuum degree and pressure values of at least two points of the pipeline system, and one of the two points is one end of the pipeline system away from the boosting device, and the transmission device is configured to receive the collected vacuum degree and the pressure values and to transmit. The vacuum and pressure test bench can detect the vacuum degree and the pressure values of all the pipelines of the braking system during a filling process, so as to obtain accurate vacuuming time and reasonable vacuum leak detection parameters, and at the same time provides testing and evaluation basis for subsequent mass production.

The invention discloses a pig drinking water detection imaging method based on BIM and artificial intelligence, and the method comprises the steps: carrying out the automatic marking of a pig house sample image set, and training a drinker target detection network; splicing and fusing the pig house images to obtain a pig house panoramic image; carrying out drinker detection on the hog house panoramic image; carrying out dirt detection on the detected water dispenser; carrying out heat map superposition on the dirty thermodynamic diagrams for a period of time; inputting the superposition resultinto a waterer dirt analysis network to obtain a waterer dirt grade, and generating a cleaning signal; visualizing various kinds of information in the pig house building information model. According to the method disclosed in the invention, automatic and intelligent hog house drinker cleaning condition monitoring is realized, the detection efficiency is high, the detection accuracy is high, the result is more real-time and objective, and hog house management is facilitated.

The invention discloses a PCB detection review method, a PCB detection review device, electronic equipment and a storage medium. The method comprises the following steps: acquiring first PCB data; based on a preset rule, designing the first PCB data according to the detection points on the first PCB data to obtain third PCB data conforming to the preset rule; establishing a detection review reportaccording to all elements corresponding to the third PCB data; obtaining a detection review result according to the detection review report; and obtaining completely detectable third PCB data according to the detection and review result, and determining a detection method according to the detection and review result. According to the method, repeated detection is avoided while the machine cost issaved, smooth PCB production detection is promoted, the product reliability is guaranteed, the whole NPI period is shortened, and more profits can be created for enterprises.

The invention provides a low-power-consumption bluetooth roll call system which can cope with a large number of roll call objects and efficiently performs roll calling. The low-power-consumption bluetooth roll call system comprises a center device capable of performing roll calling of peripheral devices and a plurality of peripheral devices capable of being connected with the center device throughlow-power-consumption bluetooth. After the center device detects the roll call objects and stores the roll call data of the roll call completion devices, the center device establishes bluetooth connection with the roll call completion devices and transmits an instruction to stop broadcasting within the required time to the roll call completion devices. When the roll call completion devices receive the instruction, the roll call completion devices stop transmitting broadcast information within the required time.

The invention discloses a method and system for rapidly detecting RFID tags based on multi-tag marking, and belongs to the field of tag detection. According to the invention, the information of different types of articles is written into different RFID tags, and the RFID tags are fixed on the articles, so that the articles can be marked by multiple tags. A back-end server combines the identification numbers of the RFID tags and the numerical value of a random seed to serve as an initial value of the hash function; the result of the hash function is controlled by selecting random seed values; the hash function value of only one RFID tag on each article is a specific value, one RFID radio frequency identification tag is selected as a representative tag to participate in detection, so that multiple RFID tags on the same article are prevented from participating in detection. According to the invention, the informatization and automation degree of warehouse management can be improved, the labor cost and the supervision cost of goods are significantly saved, illegal removal and theft in the warehouse are effectively prevented, and the management efficiency of warehouse articles is improved.

The invention discloses determination methods for the urban gas pipeline network detection range and detection coverage rate. The determination method for the detection range comprises the steps that the real-time wind direction and wind speed are detected in the moving process of pipeline network detection equipment; a real-time included angle formed between the real-time wind direction and the pipeline network detection equipment moving direction is calculated; the left-side detection distance and the right-side detection distance of the pipeline network detection equipment under the windless condition are acquired; the left-side actual detection distance and the right-side actual detection distance of a detection car in the actual detection process are calculated, and the actual detection coverage range of the detection car is determined; and the length of a pipeline covered by the detection coverage range of the detection car is determined by combining an urban gas pipeline network map. The determination method for the detection coverage rate comprises the step that the detection coverage rate is determined through the length of the pipeline covered by the detection range and the total length of all pipelines. According to the scientific and reasonable determination methods for the urban gas pipeline network detection range and detection coverage rate, the pipeline network detection coverage rate can be calculated in a quantized manner, therefore, the detection range can be effectively determined in time, and generation of a non-detection zone is avoided.

The invention discloses a composite foundation load detection method. The composite foundation load detection method includes the following steps that (a), site clearing is performed; (b), two-way cement stirring piles are selected; (c), load detection is performed; and (d), the two-way cement stirring piles are analyzed. According to the method, the selected two-way cement stirring piles are subjected to number marking, repeated detection of loads of the two-way cement stirring piles is prevented, the construction period can be shortened, and cost can be reduced. According to the method, the average value of test data corresponding to lime powder detection points of the two-way cement stirring piles is obtained, the average load at the positions of the two-way cement stirring piles is acquired, influences caused by the fact that the load measured through a single lime powder detection point is too high or too low are eliminated, the deviation arrange of the obtained composite foundation load and the actual load is small, the acquired test data are high in precision, extremely high reference value is achieved, the cement stirring piles and tidal marsh mud around the piles can form a composite foundation jointly, and therefore the bearing capacity of the foundation is improved; and meanwhile, by means of the method, the detection stability of a detection device can be improved, and load detection is wide in application range.

The invention discloses a pet guy rope detection method and device and a computer readable storage medium. The pet guy rope detection method comprises the steps of obtaining a to-be-detected image; performing pet and human shape detection on the to-be-detected image, and in response to the detected pet and human shape, obtaining a pet position coordinate and a human shape position coordinate; combined images are obtained, each combined image comprises the combination of any pet and any human shape, and all the combined images are subjected to guy rope recognition; and in response to the fact that the recognition result of the combined image is that the pet and the human shape in the combined image are subjected to rope pulling, marking association is performed on the pet and the human shape in the combined image, and rope pulling detection on the pet with the association mark is stopped. By means of the mode, repeated detection can be avoided, resources can be saved, and the calculation amount can be reduced.

The invention discloses an adaptive uploading acceleration method based on distributed agent servers. The method comprises the steps that: 1) a user end submits an uploading request to the agent server; 2) the agent server issues an address of an available cache server to the user end; 3) the user end uploading file fragments to be uploaded to the cache server; 4) the cache server sends the file fragments to the agent server for reforming a file and searching a corresponding acceleration demand degree [beta], if the corresponding acceleration demand degree [beta] is not found, other agent servers are used for searching the corresponding acceleration demand degree [beta], and if no response is received, an acceleration demand degree calculation instruction is initiated for selecting out an optimal agent server; 5) the optimal agent server informs the agent server of the acceleration demand degree; 6) the agent server sends the reformed file to the optimal agent server and stores the acceleration demand degree; and 7) the optimal agent server sends the uploaded file to a receiver. According to the invention, the uploading speed is increased, and the uploading experience is improved.

The invention relates to a one-step triple RT-PCR detection primer for distinguishing CHUV, BCV and DAV and kit thereof, belonging to the technical field of veterinary infectious disease detection. The kit includes 3 pairs of primers, respectively CHUV-P1 and CHUV-P2, BCV-P1 and BCV-P2, DAV-P1 and DAV-P2; and also comprises a blank control template, a positive control template and a PCR amplification reagent; the blank control template is RNase Free Water; there are three positive control templates, namely CHUV, BCV and DAV inactivated viruses respectively. By adopting the kit of the invention, the one-step RT-PCR reaction can detect three PALV serotype virus such as CHUV, BCV and DAV at the same time, avoiding repeated detection of conventional PCR, having the advantages of low cost, highefficiency and the like, and being easy to popularize and apply.