26results about How to "Reduce false detection" patented technology

The invention provides a module and a method for automatically detecting Pt-derived superfine defects of ultra-thin glass, and a system and a method for automatically detecting poor appearance of ultra-thin glass by using the module. The automatic inspection system for appearance defects comprises: an edge inspection module for inspecting peeling or wedge-shaped defects when physically cutting ultra-thin glass in units of units; the surface inspection module is used for inspecting scratches, cracks or foreign matters on the surface area of the ultra-thin glass; the phase measurement light deflection inspection module is used for measuring and inspecting stains or recesses in the surface area of the ultra-thin glass through phase change; and a Pt-derived ultrafine defect inspection module for inspecting Pt-derived ultrafine defects generated in the production process of the ultra-thin glass mother substrate. The Pt derivative superfine defect inspection module comprises a holographic restoration device; the scanning device is used for moving the holographic restoration device to a preset scanning path; and an ultra-fine defect determination means for determining Pt-derived ultra-fine defects by a machine learning algorithm using the inherent Moore pattern of the image obtained from the holographic restoration means.

The invention relates to the technical field of thermostat detection, and provides an automobile thermostat sensitivity test device, the automobile thermostat is provided with a connecting end and a large and small circulation output end, the automobile thermostat sensitivity test device comprises a rack with a liquid storage space, and a temperature control part, an extraction part and a detection part which are arranged on the rack; the temperature control part is positioned in the liquid storage space and below the liquid storage space; the extraction part is located in the liquid storage space and communicates with the connecting end; and the detection part is respectively communicated with the large and small circulation output ends. The temperature control part controls the temperature of the cooling liquid, the extraction part sends the cooling liquid to the automobile thermostat, the automobile thermostat sends the cooling liquid to the detection part through the large and small circulation output ends, the detection part detects the flow velocity difference of the large and small circulation output ends, and the sensitivity of the automobile thermostat to the temperature is determined through the flow velocity difference and the corresponding temperature. According to the automobile thermostat sensitivity test equipment provided by the invention, the sensitivity of the automobile thermostat can be accurately detected under the condition of relatively low cost.

The present invention discloses a method for detecting three-dimensional changes in ground objects, an electronic device and a storage medium, wherein the detection method comprises accurately registering two time-phase point clouds, and setting a reference time-phase point cloud and a time-phase point cloud to be detected; calculating the normal vectors of the time-phase point cloud to be detected and the reference time-phase point cloud; calculating the local Euclidean distance and the local density; improving the local Euclidean distance according to the local density to obtain the density-adaptive local Euclidean distance; extracting the points to be detected whose density-adaptive local Euclidean distance in the time-phase point cloud to be detected is greater than the distance threshold to the candidate change area; eliminating the misdetected points in the candidate change area caused by modeling deformation; clustering the points in the candidate change area, calculating the area corresponding to the clustering cluster, and further eliminating the misdetected points according to the area and the area threshold. The present invention has better noise resistance and better detection accuracy.

The invention relates to the technical field of cylindrical grinding machines, in particular to an automatic detecting and screening centerless grinding device which comprises a grinding machine body, a left vertical seat and a right vertical seat are arranged at the top of the grinding machine body, a guide wheel is mounted on the left vertical seat, and a grinding wheel is mounted on the right vertical seat. A first hopper located below the guide wheel and the grinding wheel is fixed between the two vertical seats, and a supporting frame is fixed to the first hopper. In the prior art, the outer diameter tolerance of the grinding rod is detected manually, the efficiency is low, errors are easy to occur, high-precision products highly depend on personnel, the outer diameter tolerance of the grinding rod can be detected continuously, the detection error is low, an alarm is automatically given out for unqualified products, and production of the defective products is avoided. The structure that the laser detection equipment is connected with the discharge port of the grinding machine is adopted, so that the outer diameter tolerance detection of the grinding rod can be continuous, the detection error is low, and an automatic alarm is given for unqualified products, so that the manpower is saved, the product precision is improved, and the production of the defective products is avoided.

The application discloses a head tracking method in a conference room multi-camera system and related devices, and the method comprises the following steps: collecting video stream data in the conference room based on the multi-camera system, and performing head tracking processing on the video stream data based on a multi-target tracking algorithm to obtain head tracking data in the video stream data; performing glass reflection head filtering processing on the head tracking data in the video stream data based on a pre-trained glass reflection filtering model to obtain filtered head tracking data; performing glass inside and outside distinguishing processing on the filtered head tracking data based on a monocular depth estimation glass boundary distinguishing mode to obtain head tracking data in the glass, and displaying the head data in the glass in real time to a specified area of a conference display screen. In the embodiment of the application, the tracking accuracy can be improved in the scene of multiple people overlapping in the conference room, and the interference of glass reflection and data inside and outside the glass can be effectively removed.

The present invention discloses a cable flaw detection method, medium and system, the method comprises the following steps: obtaining a cable image and generating a three-dimensional point cloud; obtaining the Gaussian curvature K of the point cloud by surface fitting; obtaining N local concave-convex position points according to the point cloud and searching for the neighboring points of each position point, fitting the coordinates of each neighboring point into a plane, and obtaining the plane normal vector P; fusing the Gaussian curvature K and the normal vector P to obtain a fused eigenvalue; performing a convolution operation on the fused eigenvalue to obtain the defect value of each position point; comparing the defect value of each position point with a preset threshold; if the defect value is greater than the preset threshold, judging the position point as a preliminary defect point, otherwise it is a normal point. The present invention has the advantages of high recognition accuracy and strong practicality.

Provided is an analysis device that reduces false detection of an attack event to appropriately output an anomaly notification. The analysis device configured to be communicable with a plurality of monitoring-target devices collects monitoring results of each of the monitoring-target devices, determines whether an anomaly has occurred in each of the monitoring-target devices, based on the monitoring results, and determines whether to output an anomaly notification indicating the anomaly, based on a result of the determination and code verification results of each of the monitoring-target devices.

The utility model relates to cable detection technical field especially relates to a kind of signal cable on-off detector, including detector one and detector two, detector one and detector two all include detection circuit, detection circuit includes detection circuit A, detection circuit B, detection circuit B is connected with detection circuit A by detection terminal, one end of the cable to be measured is connected with detector one by detection terminal one, the other end of the cable to be measured is connected with detector two by detection terminal two.The utility model has the advantages that: one end of signal cable is connected with detector one through cable connector, the other end of signal cable is connected with detector two through cable connector, detection personnel can operate detection switch on closed detector, detection result of the cable to be measured is displayed through indicator light, single long distance cable detection can be realized, detection personnel does not need to run back and forth between the two ends of cable or multiple cooperative operation, and detection efficiency is improved.

The invention relates to an absolute flight time calculation method, a flow velocity calculation method and a flow velocity calculation system, and the absolute flight time calculation method comprises the following steps: searching a maximum peak position of a waveform of a signal wave; intercepting a maximum valve according to the maximum peak position; reducing the cut maximum valve by a preset proportion to form a template valve; starting from the initial position of the waveform of the signal wave, matching the waveform of the signal wave by using a template valve to obtain a first valve which exceeds a preset similarity threshold value as a matched valve; the absolute time of flight of the signal waves is calculated using the peaks of the matched valves. According to the method for determining the matched valve disclosed by the embodiment of the invention, the error of the signal wave amplitude change caused by the environment to the calculation result is eliminated. And the calculation is more accurate. And based on the absolute flight time calculation method, the flow velocity can be calculated more quickly and accurately.

The application provides a kind of turbine blade in-situ nondestructive testing device based on temperature sensor, including: machine body, a pair of caterpillar, detector, sliding mechanism and heating mechanism, a pair of caterpillar is located in the opposite sides of machine body, detector is located in the bottom of machine body, sliding mechanism is located in the front end of machine body in a retractable manner along the direction of travel of machine body, heating mechanism is located in the bottom of machine body and heating mechanism is connected to sliding mechanism, along the direction of travel of machine body, heating mechanism is located in front of detector, sliding mechanism has extended state and contracted state, when sliding mechanism is in extended state, part of sliding mechanism and heating mechanism are located outside of machine body, when sliding mechanism is in contracted state, sliding mechanism and heating mechanism are located inside of machine body. By setting sliding mechanism, heating mechanism can be stored inside of machine body, so that caterpillar can climb up the steps, so that the distance between detector at the rear end of machine body and blade step is closer, improve the detection accuracy of device.

The embodiment of the invention discloses a laminated slab mounting and positioning method and device based on space conversion. A specific embodiment of the method comprises the steps of performing feature information extraction on a three-dimensional model of the laminated slab to obtain positioning feature point information and a first common control point position; point position measurement is carried out on public control points arranged on the construction site to determine a construction coordinate system and the position of a second public control point; performing space conversion processing on the construction coordinate system and the design coordinate system to generate coordinate system space conversion information; performing feature point measurement correction on the target laminated slab to obtain actually measured feature point information of the laminated slab; generating actual measurement pose information of the laminated slab and target feature point information of the laminated slab; laminated slab installation error information is generated; and the laminated slab installation error information is sent to a construction monitoring terminal so that a constructor can install and adjust the target laminated slab. According to the embodiment, the overall positioning precision of the laminated slab can be improved, so that the mounting error is reduced and the construction quality is improved.

The utility model relates to the technical field of medical instruments, discloses a monitoring device for clinical internal medicine, and solves the problems that equipment is inconvenient to operate, connection is unstable, airflow control is inaccurate, and detection results are affected in the detection process of the clinical internal medicine. A display is arranged on the detector, so that data can be checked conveniently; and a handle groove facilitates holding operation. The safety lock catch guarantees stable connection of the air pipe, the special structure of the safety lock catch achieves convenient operation and flexible locking, the air pipe tail connecting piece facilitates equipment maintenance, and the male and female bidirectional check valves accurately control airflow. The reset spring assists the locking block to work stably, all the components cooperate to enable gas to flow smoothly, a stable detection channel is formed from the blowing nozzle to the detector, the detection efficiency and accuracy are effectively improved, and reliable guarantee is provided for clinical internal medicine detection.

According to the skin-attaching induction method of the beauty instrument, the stable multi-frequency signals are generated through the PID control algorithm, it can be ensured that the voltage signals on the electrodes are stable, and the accuracy and reliability of the signals are improved; detecting each electrode by using the generated multi-frequency signal in a rotation training mode to obtain current effective values under different frequencies; by changing the frequency, measuring the impedance change under different frequencies and analyzing the change of capacitance and resistance, the fitting state of the electrode and the skin and the moisture content are judged.

The utility model belongs to the technical field of non-contact temperature measurement, and particularly relates to a temperature measuring device. The temperature measuring device comprises a measuring tube which is arranged on the furnace wall in a penetrating mode, one end of the measuring tube is a radiation incident end extending into the furnace, and the other end of the measuring tube is a radiation emergent end located outside the furnace; the light shield is mounted at the radiation incident end; the thermodetector is arranged at the radiation emitting end of the measuring tube and is used for receiving the infrared radiation emitted by the radiation emitting end; the measuring pipe cools a measuring channel from two angles of ventilation cooling and heat source isolation so as to ensure long-term stable work; a light shield is arranged at the tail part of the measuring tube, so that most of heat radiation from a non-measured part can be shielded, the situation that unnecessary interference radiation enters a measuring channel and is mistakenly detected by a thermodetector is reduced, the cooling pressure of the measuring tube can be reduced, the cooling effect is improved, and the measuring accuracy is further ensured; the measuring tube is of an integral structure, so that disassembly and assembly are more convenient and flexible.

The invention relates to the technical field of quality detection, and discloses an SMT patch quality detection method and device based on machine vision and a medium. The method comprises the following steps: acquiring a to-be-detected SMT patch image acquired by a machine vision module; performing image preprocessing according to the SMT patch image to obtain image filtering information; performing morphological reconstruction according to the image filtering information to obtain an SMT patch edge image; obtaining the actual size of the SMT patch according to the SMT patch edge image; determining a position area to be measured according to the actual size of the SMT patch; and according to the position area to be measured, carrying out measurement to obtain quality information of the SMT patch component. According to the method, the SMT patch quality is detected through machine vision, the accuracy of SMT patch image segmentation is improved, the accuracy of SMT patch appearance quality detection is improved, and error detection is reduced.

The utility model discloses a single-person physical sign monitoring belt, which is provided with a piezoresistive sensor, and the piezoresistive sensor is used for detecting the pressure condition of the whole monitoring belt and transmitting pressure data to a main control module; therefore, the main control module can detect the pressure on the monitoring belt according to the value of the pressure data, so that the main controller can control the piezoelectric signal sensor to collect physical sign data only when an object with a certain mass is pressed on the monitoring belt; meanwhile, the system is also provided with an alarm module, and the alarm module can give an alarm in real time under the control of the main control module. Through the above design, the problem of human body error detection in the traditional technology can be reduced, the monitoring authenticity is improved, and on-site and real-time alarm can be carried out without being combined with terminals such as a mobile phone and the like; therefore, the utility model is very suitable for old people to use, and can be applied and popularized on a large scale in the technical field of health monitoring.

The utility model provides weight and metal detection equipment for bagged finished kebabs. The weight and metal detection equipment comprises a rack, a weight detection module, a metal detection module, a conveyor belt assembly penetrating through the two modules and a removing mechanism arranged at the output ends of the weight detection module and the metal detection module, wherein the weight detection module and the metal detection module are arranged in sequence; the metal detection module is located at the tail end of the conveyor belt assembly in the outlet direction. According to the utility model, the weight detection module, the metal detection module, the rejecting mechanism, the marking device and the like are integrated together, and the bagged skewers sequentially pass through each detection link on the conveyor belt, so that a one-stop detection process from weight detection, metal detection, rejecting of defective products and marking of qualified products is realized, and manual carrying and operation among a plurality of devices are not needed; the detection efficiency is greatly improved, the method is particularly suitable for enterprises with large-scale production, and the overall production efficiency can be remarkably improved.

The invention relates to a target intelligent monitoring method and system based on a complex environment. The method comprises the following steps: screening historical monitoring data based on an environment monitoring tag to obtain event sequences corresponding to different environment types k under the same historical monitoring data; for each environment type, determining a characteristic event sub-sequence based on the event sequence; obtaining a current event sequence corresponding to different environment types based on the current monitoring data, and processing the current event sequence based on the first feature event subsequence and the second feature event subsequence; and performing prediction based on the current monitoring data. Based on historical monitoring data supported by big data, starting from a time-based event sequence, high time resolution information about complex scene changes is provided by revealing the occurrence sequence and influence of events, dialectical processing is carried out on the monitoring data, stable monitoring data output is maintained, and target monitoring can be carried out more accurately.

The invention provides a scanning area detection method, device and equipment and a medium, and the detection method comprises the steps: scanning a scanning area through scanning equipment, and obtaining original scanning data; respectively calculating an average value of channel data of each scanning module in each projection direction according to the original scanning data; according to the original scanning data and the average value of the channel data of each scanning module in each projection direction, abnormal signals of all scanning channels are calculated, and corresponding signal evaluation values are generated; and comparing the signal evaluation value with a threshold value so as to detect the scanning area. Through the scanning area detection method and device, the equipment and the medium provided by the invention, whether the object exists on the scanning area can be confirmed.

This utility model provides an anti-cheating truck scale, including a truck scale body. Two narrow slots are formed on the upper side of the truck scale body. A support plate is installed on the inner wall of each narrow slot, and multiple weighing sensors are installed on the inner wall of the narrow slots, below the support plate. By setting up a linkage structure of the support plate, sliding rod, fixing block, and U-shaped double-trigger switch, as well as a detection mechanism of I-shaped side plate, trapezoidal block, rotating rocker, and push switch, when the vehicle is not fully on the scale, the support plate drives the slider and connecting rod to deflect the sliding rod, causing the trigger plate on the fixing block to touch the U-shaped double-trigger switch, triggering an audible and visual alarm. When the tire squeezes the side wall, the I-shaped side plate is pushed, and through the trapezoidal block and connecting frame, it drives the rotating rocker to press down the push switch, similarly triggering an alarm. This achieves real-time monitoring and warning of two types of weighing deviation problems, blocking cheating paths from a mechanical structure level and ensuring the accuracy and fairness of weighing data.

The invention relates to a hybrid rice sowing strip forming performance evaluation method, device and equipment and a medium, and the method comprises the steps: in a C2f structure in a backbone network of an original YOLOv8n model, replacing a Conv module in a Bottleneck structure with a PConv module to determine a PConvC2f structure, and adding an ECA channel attention mechanism before up-sampling operation of a neck network to construct an improved YOLOv8n model; adopting an improved YOLOv8n model trained to a convergence state to carry out target detection on the seedling tray seeding area image so as to determine coordinate information and types of rice bud seeds in the seedling tray seeding area, and determining the quantity of the rice bud seeds in a strip qualified area in the seedling tray seeding area image according to the coordinate information; calculating and determining the ratio of the quantity of the rice bud seeds corresponding to the qualified strip forming area to the total quantity of the rice bud seeds in the seedling tray sowing area, and taking the ratio as the seedling tray sowing strip forming percent of pass. According to the method, the detection precision and robustness of the rice bud seeds in the seedling tray seeding area can be remarkably improved.

The invention relates to the technical field of image analysis, and in particular to a method, system and device for detecting grape downy mildew spores based on image analysis. In order to solve the problem of low accuracy and poor stability of detection results when analyzing spore images in the prior art, the invention first sequentially processes a grape downy mildew spore image to be detected through convolution, multiple feature downsampling and global pooling, so as to obtain feature downsampling output and global pooling output that can reflect middle-level features, appropriate scale features and high-level features of grape downy mildew spores; then multi-layer cross feature fusion processing is performed to obtain multiple cross feature fusion images; then, output quality is controlled based on bounding box distance loss and confidence weight distribution loss, and a classification result corresponding to the maximum value of the weighted average value of multiple outputs is used as a grape downy mildew spore detection result; the method is applied to grape downy mildew spore image analysis, so as to improve the accuracy and stability of the detection and analysis results.

The invention relates to a mechanism for ammunition detection of on-off of an opening thread, and belongs to the technical field of automatic measurement. The device comprises a pressing mechanism, a jacking mechanism, an anti-explosion telescopic mechanism, an anti-explosion tightening mechanism, an anti-explosion torque sensor and a thread detection mechanism, a projectile body is fixed through the jacking mechanism and the pressing mechanism, then an anti-explosion automatic feeding mechanism completes feeding and retreating actions, the anti-explosion tightening mechanism drives the thread detection mechanism to detect a projectile opening thread, and the anti-explosion torque sensor detects the projectile opening thread. The anti-explosion torque sensor is used for controlling the tightening action, and first-step thread-through detection is completed. And the line body continues to act, station transfer is completed, the operation in the first step is repeated, thread detection in the second step is carried out and completed, and data are recorded. The problems that manual detection is low in efficiency, time-consuming and labor-consuming are solved, safety is guaranteed, and safe and efficient production tasks can be completed in the automation process through the automatic detection mechanism for the elastic opening thread pass-stop mechanism.

The application provides a rotating system and method for Gaussian distribution of an infrared point target, comprising: a target rotating and neighborhood pixel position generating module, which rotates each pixel of the target according to a preset shooting angle to determine the position relationship of four neighborhood pixels of the rotated pixel; a pixel radiation energy Gaussian distribution module, which determines a Gaussian distribution model based on distance change; a pixel distribution module based on energy and barycenter constraint, which determines an energy and barycenter constraint model; and an iterative calculation pixel distribution module, which uses Newton iteration to solve the radiation energy of the four neighborhood pixels based on the Gaussian distribution model and the energy and barycenter constraint model, thereby obtaining the position and radiation energy distribution of each pixel of the rotated infrared target. The application uses the four neighborhood pixels of the rotated pixel as the benchmark on the basis of the conventional rotation transformation, and uses the Gaussian distribution model based on distance change for the pixel radiation energy distribution, thereby ensuring that the radiation energy of the infrared target does not change before and after rotation and that the relative barycenter of each pixel does not change.

The embodiment of the invention provides a gene variation confidence coefficient determination method and system, electronic equipment and a storage medium. The method comprises the following steps: sequencing a to-be-detected sample pre-judged to have gene variation, and determining a first coverage ratio of a first basic group corresponding to a functional gene to a second basic group corresponding to a non-functional gene on a gene specific nucleotide GSN site in the to-be-detected sample; wherein the non-functional gene comprises a pseudogene and / or a homologous region of the functional gene; determining an error comparison coefficient according to the first coverage ratio; based on a comparison result of the error comparison coefficient and a reference error comparison coefficient range, the pre-judged confidence degree of the gene variation is determined, the reference error comparison coefficient range is determined based on a reference error comparison coefficient obtained based on a second coverage ratio, and the reference error comparison coefficient range is determined based on a reference error comparison coefficient obtained based on a second coverage ratio. The second coverage ratio is determined based on a first basic group corresponding to a functional gene on the GSN site and a second basic group corresponding to a non-functional gene on the GSN site in a predetermined number of reference samples.

This invention discloses an image forming system and an image forming method. The image forming system includes a processor. When a human body sensor detects a person in a first region at a distance of a first distance from the human body sensor, the processor controls the human body sensor to detect a person in a second region at a distance of a second distance shorter than the first region. The processor also restores the image forming device, which is in a first power state, to a second power state with a higher power state than the first power state. When a person is detected in the second region, the processor restores the image forming device to a third power state with a higher power state than the second power state.