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

20results about How to "Guaranteed detection speed" patented technology

Electric power field operation safety detection method and system based on hybrid expert model

The invention belongs to the field of electric power and the technical field of artificial intelligence, and particularly relates to an electric power field operation safety detection method and system based on a hybrid expert model. According to the method, the visual language model and the YOLO target detection model are combined, and efficient and accurate electric power field operation safety detection is realized under the condition of few samples through a hybrid expert model architecture. In the training stage, through multi-model cooperative training, an expert model set for different scenes and targets is constructed. In the detection stage, a two-stage detection mechanism is adopted, YOLO is firstly used for rapid preliminary detection, then VLM is used for rechecking a low-confidence target, and finally detection results are integrated to ensure the accuracy of detection. The method aims to effectively cope with complex environments and potential safety hazards in electric power field operation, safety detection efficiency and accuracy are remarkably improved, and compared with a single model architecture, the method shows wider application scenes and higher detection quality in an electric power field operation scene.
Owner:YANTAI HAIYI SOFTWARE

Photovoltaic inverter island detection method and system

The invention relates to the technical field of power grid island detection, in particular to a photovoltaic inverter island detection method and system, and the method comprises the steps: obtaining the photovoltaic power output by a photovoltaic inverter at each moment in each period in real time, and the load power consumed by a local load end at each moment in each period in real time, collecting the power grid frequency measured by the photovoltaic inverter in real time; determining a photovoltaic trend quantity and a photovoltaic fluctuation value of each moment in each period; photovoltaic feature importance at any moment in the photovoltaic historical data set is determined; constructing a prediction model, and obtaining a photovoltaic power prediction vector and a load power prediction vector; determining an adjustment factor of each moment in each period; and determining a chopping coefficient, and performing island detection on the photovoltaic power generation system in combination with the power grid frequency. According to the invention, the speed of island detection can be ensured, the disturbance signal is prevented from being greatly adjusted in a short time, the power quality of a power grid is not affected, and the island detection effect of the photovoltaic inverter is improved.
Owner:ZHEJIANG LEIYA ELECTRONICS CO LTD

Hybrid anchor lane line detection result fusion method based on attention mechanism

The invention provides a hybrid anchor lane line detection result fusion method based on an attention mechanism, and the method comprises the steps: carrying out the feature extraction of an original image, and obtaining a feature map containing high-level semantics; inputting the global feature map into two multi-layer perceptron in parallel for processing, and outputting a data structure shape matched with the row anchor definition and the column anchor definition; post-processing is carried out, and line anchor and column anchor identification results of lane line coordinates are obtained through conversion; taking identification results of the row anchor and the column anchor as input, integrating information of the row anchor and the column anchor through an attention mechanism, distributing different confidence coefficients for the row anchor and the column anchor, and calculating an offset value of an output lane line coordinate; carrying out normalization processing on the confidence coefficient and the deviation value; and fusing lane line detection results of the row anchor and the column anchor to obtain an identification result. The method can adapt to different road environments and weather conditions, has high real-time performance and good recognition precision, and has remarkable advantages in the aspect of improving the accuracy and robustness of lane line detection.
Owner:SHENZHEN TECH UNIV

Traffic target identifying and positioning method based on foggy day scene

The invention discloses a traffic target identification and positioning method based on a foggy day scene. The method comprises the following steps: S01, processing an obtained original fog-free image and an original fog-containing image by using an atmospheric light scattering prior migration generation model to construct an AtmoGAN Haze data set; and S02, inputting the constructed AtmoGAN Haze data set into a target identification and positioning model to obtain a foggy day target identification and positioning result. According to the invention, on the basis of ensuring the detection speed, the problem that the traffic target is difficult to identify due to the conditions of target detail missing, contrast reduction, color distortion and the like in the foggy day scene can be effectively solved, and the precision and speed of foggy day target identification and positioning are improved.
Owner:SHIJIAZHUANG TIEDAO UNIV

Filter surface defect detection system and equipment based on small sample training set

The invention provides a filter surface defect detection system and equipment based on a small sample training set. The system comprises an image acquisition module used for collecting defect image data of the filter; the image marking module is used for marking the acquired image; the image expansion module is used for training a StyleGAN3 generative adversarial network model by using the defect image, generating a defect image by using the trained model, fusing the defect image with the intact image, and expanding a predetermined number of sample data sets; and the target detection model is used for identifying the filter products with defects on the filter production line. According to the method, a simulated image expansion data set is generated for a small sample problem by using an image expansion method, so that a deep learning model can be effectively trained, a YOLOv7 network structure is optimized, an attention mechanism is added, a loss function is modified, the detection precision is improved while the detection speed is kept, and the detection efficiency is improved. The method is especially suitable for small target defect detection.
Owner:ZHEJIANG ZHENHANG IND GROUP CO LTD +2

Belt wear state detection method based on improved YOLOv8-EfficientNet

The present invention relates to the technical field of target detection methods, and in particular to a belt wear state detection method based on improved YOLOv8‑EfficientNet. The present invention uses the most advanced real-time monitoring algorithm YOLOv8 target detection algorithm as a basis, combines it with the improved EfficientNet convolutional neural network, and improves the combined network. The acquired conveyor belt wear picture is preprocessed, and the preprocessing technology uses the Retinex image enhancement algorithm to perform brightness enhancement, detail protection, color protection, naturalness restoration, image denoising, detail extraction, etc. on the image to improve the clarity of the belt wear picture. Finally, the improved algorithm is deployed to the conveyor real-time detection equipment to detect the conveyor belt, and the wear parts of the conveyor belt and the degree of wear of each part can be accurately obtained.
Owner:HEBEI UNIV OF ENG

Automatic detection method for full coverage of inner wall of variable-diameter steel pipe

The invention discloses a variable-diameter steel pipe inner wall full-coverage automatic detection method, which comprises the following steps: adjusting each camera on a camera module to an initial site after a pipe climbing device enters a pipe, shooting the inner wall of a variable-diameter steel pipe by the camera module in the process that the pipe climbing device moves back and forth along the pipe, and adjusting each camera site of the camera module in the shooting process, and 360-degree shooting of the inner wall of the reducing steel pipe is completed. According to the invention, the detection requirements of different pipe diameters in the large-pipe-diameter steel pipe can be met, the detection precision and the detection speed can be ensured while the stability is ensured, and the 360-degree full-coverage full-automatic detection requirements of the inner wall of the pipe are met.
Owner:BAOSHAN IRON & STEEL CO LTD

Fine-grained building detection algorithm based on improved YOLOV8

The invention discloses a fine-grained building detection algorithm based on improved YOLOV8, and the algorithm is based on the improvement of a YOLOV8 model, and aims to improve the accuracy and efficiency of building detection in a remote sensing image. The algorithm comprises the following detailed steps: S1, firstly, collecting abundant remote sensing building images, and constructing a special remote sensing building data set according to the images to provide a solid foundation for model training; step S2, then, utilizing the data set to carefully improve and optimize a YOLOV8 model, and through a training process, obtaining an accurate remote sensing building detection model; and S3, finally, the remote sensing building detection model is applied to remote sensing image data to be detected, and efficient recognition and positioning of the building are achieved.
Owner:CHINA THREE GORGES UNIV

Image overlap rate detection method, device, equipment and computer storage medium

The application provides an image overlap rate detection method, device, equipment and computer storage medium. When calculating the overlap boundary position by the image overlap rate detection method, only the boundary sub-image and each reference sub-image in the reference image need to be compared and calculated, the number of pixel points involved in the calculation process is less than that of directly comparing and calculating the target image and the reference image, so the detection speed is faster. Moreover, since all the pixel points in the target image are not involved in the calculation process, the possibility of misidentification is reduced, so the detection accuracy of the image overlap rate is higher for images containing a large amount of repeated image information, such as warehouses. It can be seen that the image overlap rate detection method provided in the application can ensure the detection accuracy and speed of the image overlap rate at the same time.
Owner:SF TECH CO LTD

A cigarette mouthpiece flavor capsule detection and grading device

ActiveCN117282690BRealize non-destructive testingGuaranteed detection speedSortingManufacturing computing systemsControl cellStructural engineering
This invention provides a device for detecting and grading cigarette mouthpiece capsules, comprising a frame with a horizontally mounted conveyor belt. Above the conveyor belt, from one end to the other, are sequentially arranged a cigarette mouthpiece feeding mechanism, a hyperspectral detection mechanism, a laser pointer, and a cigarette mouthpiece gripping mechanism. The feeding mechanism feeds cigarette mouthpieces at a constant speed to the beginning of the conveyor belt. The detection ports of the hyperspectral detection mechanism and the laser pointer face downwards. A photoelectric sensor and an incremental encoder, with their detection ports facing the cigarette mouthpieces on the conveyor belt, are also located on one side of the conveyor belt. Two horizontal tracks are positioned above the end of the conveyor belt, and the cigarette mouthpiece gripping mechanism controls the flow of cigarette mouthpieces onto the designated tracks. The device also includes a control unit mounted on the frame and electrically connected to other electrical components. This invention uses a hyperspectral detection mechanism to detect cigarette mouthpiece capsules, achieving non-destructive testing while maintaining high speed.
Owner:HENAN UNIV OF SCI & TECH

Novel electrocardiograph detection probe

The utility model discloses a novel electrocardiograph detection probe, which relates to the technical field of detection probes and comprises six groups of electrocardiograph detection probes, one ends of the six groups of electrocardiograph detection probes are all fixedly connected with signal lines, the outer walls of the six signal lines are provided with a winding mechanism, one end of the winding mechanism is provided with a fixing mechanism, and the other end of the winding mechanism is provided with a clamping mechanism. The winding mechanism comprises a winding box and a rotating rod, a rotating handle is arranged at one end of the winding box, a round seat is fixedly installed at one end of the rotating handle, six sets of fixing plates are fixedly installed on the outer wall of the rotating rod, and U-shaped plates are fixedly installed at the upper ends and the lower ends of the six sets of fixing plates. According to the utility model, the operation of a worker is not hindered, the operation speed of the worker is not influenced, the detection speed can be ensured, meanwhile, the phenomenon of winding or knotting among the six signal lines 11 is prevented, and the normal transmission of signals is ensured.
Owner:临沂市检验检测中心

Wireless monitoring terminal and wireless ad hoc network device

The utility model discloses a wireless monitoring terminal and wireless ad hoc network device, hollow arrangement in wireless monitoring terminal, and wireless monitoring terminal includes pole body, pole head and pole tail, and pole head is equipped with temperature sensor, and pole head is along the circumference and is equipped with a plurality of air inlet, and pole tail is equipped with gas sensor and sensor adapter board, and temperature sensor and gas sensor all are connected with sensor adapter board electricity, and sensor adapter board electricity connects wireless terminal circuit board, and wireless terminal circuit board electricity is connected with power supply and drive motor for power supply, and drive motor output shaft fixed connection has the flow guide fan blade, and wireless terminal circuit board electricity is connected with the wireless module for receiving and dispatching data, and wireless module electricity is connected with wireless data transmission ware for transmitting data. The present application can realize the quick collection and real -time monitoring of the gas data in the designated depth area of coal heap.
Owner:XUZHOU JI AN MINING TECHNOLOGY CO LTD

Industrial product surface nondestructive testing method and system based on improved YOLOv8

The invention discloses an industrial product surface nondestructive testing method and system based on improved YOLOv8, and relates to the technical field of computer vision and image processing. In a YOLOv8 backbone network, standard 3 * 3 convolution is replaced by a space channel selective kernel convolution module, and the nondestructive testing of the surface of an industrial product is realized by performing space and channel reconstruction on features and dynamically adjusting a receptive field. Redundant features are suppressed, and the modeling capability for complex textures is enhanced; a coordinate-channel-space joint attention module is embedded in front of a detection head classification branch, and extraction and focusing of small defect features are enhanced through coordinate, channel and space attention mechanisms; structural upgrading is carried out on the feature fusion part of the network, the detection scale is expanded to a P2 layer, and the capacity of capturing tiny targets is improved. In addition, multi-scale feature fusion and non-maximum suppression and weighted frame fusion in a post-processing stage are combined, so that the positioning precision and the result stability of the detection frame are further improved.
Owner:SHANGHAI JINGYI IND CO LTD

Target detection and tracking method, electronic equipment and storage medium

The invention discloses a target detection and tracking method, electronic equipment and a storage medium. The method comprises the following steps: acquiring a to-be-detected image containing personnel in a target scene by using a camera; inputting the to-be-detected image into a target detection model comprising a first detection head and a second detection head for personnel detection to obtain a personnel detection result of the target scene; adjusting the rotation angle of the camera based on the central point of the surrounding frame in the personnel detection result and the size information of the to-be-detected image; and determining whether to control a tracking device where the camera is located to move or not according to the area of the surrounding frame so as to track the personnel. According to the scheme disclosed by the invention, rapid personnel detection can be realized on embedded equipment without a neural network acceleration module, and a real-time personnel tracking effect is achieved.
Owner:MUYUAN FOOD GROUP CO LTD

Target recognition system and method for image / television guided aircraft with stable attitude and image

The present invention discloses a target recognition system and method for stabilizing attitude and image on an image / television guided aircraft. In the system, a television camera is used to collect a target area image sequence in real time, and electronic image stabilization technology is used to achieve high-precision image stabilization of a motion-shifted image sequence. A damping loop component design is used to improve the attitude stability of the image / television guided aircraft. The processed image sequence is input into a deep learning algorithm model to obtain real-time, effective and accurate target position information, and autonomous target detection and tracking are performed, thereby achieving accurate recognition and tracking of the target.
Owner:BEIJING INFORMATION SCI & TECH UNIV

Temperature switch accuracy detection system

The invention discloses a temperature switch accuracy detection system which is characterized in that a temperature control groove used for detecting a temperature switch is formed in the middle of the top surface of a detection table, a cross beam is fixed above the detection table, a detection tool clamp used for clamping the temperature switch is arranged on the front side of the top surface of the detection table, and the detection tool clamp is provided with a detection sensor of the temperature switch; a screwing knife used for screwing a temperature switch adjusting bolt is vertically and movably connected to the end face of the front side of the cross beam and located over the detection tool clamp, the two ends of the cross beam are fixed to the detection table through supporting columns, the screwing knife is in transmission connection with the bottom of a servo motor, and the servo motor is vertically and movably connected with the cross beam through a lifting device. According to the structure, the temperature switch accuracy detection system can ensure the detection quality of each temperature switch, and in addition, through automatic operation of the temperature switches, the detection efficiency is effectively improved.
Owner:淮安科畅科技信息有限公司

A device for precise and rapid identification of elements in drilling cuttings

This invention discloses a precise and rapid identification device for elements in drilling cuttings, relating to the field of geological exploration equipment. It includes a housing, a sample processing component, a rotating multi-station sample tray, an X-ray detection component, a cleaning component, a data calibration module, and a human-machine interface component. The sample processing component sequentially feeds, grinds, and presses the drilling cuttings into standard samples. The rotating multi-station sample tray carries the samples and moves them between stations. The X-ray detection component irradiates the samples and acquires elemental data. The data calibration module uses a machine learning model to correct the raw data in real time. The cleaning component automatically cleans the sample cups after use. This invention achieves a fully automated, integrated workflow from sample feeding to analysis, solving the problems of non-standard sample pretreatment, low detection efficiency, and poor data accuracy in the field, significantly improving the speed and accuracy of element identification in drilling cuttings.
Owner:ANHUI UNIV OF SCI & TECH

A ship detection method and device based on frequency domain feature fusion and a storage medium

The application provides a ship detection method and device based on frequency domain feature fusion and a storage medium, and belongs to the technical field of radar detection. The method comprises the following steps: inputting an acquired current remote sensing image into a ship detection model constructed based on a single-stage target detection method; generating frequency domain features corresponding to the current remote sensing image by a pre-constructed frequency domain feature extraction module in the ship detection model according to the current remote sensing image; generating spatial domain features corresponding to the current remote sensing image by a pre-constructed spatial domain feature extraction module in the ship detection model according to the current remote sensing image; generating fused features by the ship detection model according to the frequency domain features and the spatial domain features; and generating a detection result corresponding to the current remote sensing image by the ship detection model according to the fused features. The application aims to provide a ship detection method which can improve the accuracy and has real-time performance.
Owner:TSINGHUA UNIVERSITY +1

A method and device for detecting data quality

The present invention relates to the field of quality detection and control of structured and semi-structured data, and a method for data quality detection has the following steps: S1, defining basic rules; S2, creating business rules; S3, creating detection tasks; S4, executing quality detection; S5, performing quality scoring and overall volatility analysis. Compared with the prior art, the present invention provides a script engine to allow users to write detection rules in a scripting manner, thereby reducing the difficulty of rule creation and being able to more flexibly meet the needs of various scenarios.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Steel pipe detecting and labeling machine with positioning assisting function

The invention discloses a steel pipe detection marking machine with a positioning assistance function, and relates to the technical field of positioning detection, the steel pipe detection marking machine comprises a supporting mechanism, the supporting mechanism comprises a steel pipeline, a detection table is arranged at the bottom end of the steel pipeline, three stand columns are fixedly connected to the upper surface of the detection table, and a positioning mechanism is arranged above the detection table; a detection mechanism is arranged at the right end of the positioning mechanism, the positioning mechanism comprises clamping plates which are used for clamping and fixing the steel pipeline under the pressure action of the steel pipeline, the clamping plates are arranged on the front side and the rear side of the steel pipeline, and the positioning mechanism is used for clamping, positioning and assisting detection operation after the steel pipeline is placed; the device can automatically carry out auxiliary positioning on the steel pipe when the steel pipe is placed above the detection device, unnecessary time and steps are prevented from being consumed during positioning, meanwhile, deviation can be prevented through auxiliary positioning, the situation that detection data are wrong is avoided, and the detection efficiency is improved. In addition, the auxiliary positioning is short in time consumption and high in speed, the steel pipe detection and marking efficiency can be effectively improved, and the overall detection speed is guaranteed.
Owner:JIANGXI HONGRUIMA STEEL PIPE