641results about How to "Detection speed" patented technology

The invention relates to the technical field of environmental sound event detection, in particular to an environmental sound event detection method based on multi-modal data fusion, which utilizes a microphone array, a camera and a sensor to synchronously acquire audio, video and environmental data to form a multi-modal data source. And the collected multi-modal data is preprocessed, so that the data quality and the accuracy of subsequent analysis are improved. And key features are extracted from the processed data, and the features are fused to form multi-modal features. And a deep learning model is constructed, and multi-modal features are used for training, so that a model capable of identifying an environmental sound event can be obtained. And performing optimization such as pruning, quantification and knowledge distillation on the trained model, and deploying the model on edge equipment to realize real-time preliminary feature extraction and event detection. The problems that an environment sound event detection method in the prior art is poor in robustness, low in real-time performance and limited in generalization ability are solved.

The invention provides a textile defect detection method based on machine vision, and the method comprises the steps: obtaining a corresponding camera resolution parameter, an algorithm complexity parameter and a detection sensitivity parameter from a database according to a textile quality requirement, and carrying out the initialization setting of a machine vision system; performing feature extraction on the optimized textile surface image, extracting texture and morphological features related to wrinkle flaws, and constructing a feature spectrum capable of reflecting wrinkle features; identifying a suspected wrinkle flaw area in the characteristic spectrum, determining the contour of the flaw, and obtaining the position and range information of the wrinkle flaw; according to a pre-established wrinkle defect type database, performing mode matching on the quantized wrinkle characteristics, and if the matching degree exceeds a preset threshold value, determining the specific type of the wrinkle defect; and a support vector machine algorithm is adopted to classify the wrinkle degree quantitative indexes, wrinkle depth and density parameters are combined, different levels of wrinkle flaws are divided, and the wrinkle severity is evaluated.

The invention discloses a ship target detection method, device and equipment and a storage medium, relates to the technical field of image recognition, and discloses a ship target detection method comprising the following steps: obtaining a preset ship image data set; training a preset target detection model based on the preset ship image data set to obtain a ship target detection model, the preset target detection model comprising a feature extraction network, a feature fusion network and a multi-scale detection head which are connected in sequence, the feature extraction network is a lightweight convolutional neural network improved based on an attention mechanism; and obtaining a to-be-detected image, and performing ship target detection on the to-be-detected image through the ship target detection model to obtain a ship target detection result. According to the scheme, the ship target detection model has high real-time performance and accuracy when processing large-scale image data, and the detection precision of ship targets of different scales is improved.

The invention relates to the technical field of optical detection, in particular to semiconductor detection equipment, which comprises a reinspection light source for emitting reinspection light, a bright field light source for emitting bright field light and a dark field light source for emitting dark field light, the reinspection light, the bright field light and the dark field light are respectively guided to irradiate the surface of a wafer, the reinspection light is reflected by the wafer to form reinspection signal light, and the reinspection signal light is transmitted to the light source. The bright-field light is reflected by the wafer to form bright-field signal light, and the dark-field light source is scattered by the wafer to form dark-field signal light; the optical separation element is used for collecting the bright-field signal light, the dark-field signal light and the reinspection signal light and performing spatial separation, so that the dark-field signal light, the bright-field signal light and the reinspection signal light are emitted to different transmission paths for respective imaging; wherein a dark field illumination light spot formed by the dark field light on the surface of the wafer, a bright field illumination light spot formed by the bright field light on the surface of the wafer and a reinspection illumination light spot formed by the reinspection light on the surface of the wafer do not coincide with one another. The wafer defect detection device is at least beneficial to improving the detection speed and the detection precision of wafer defect detection.

The invention discloses a network protocol fuzz testing method and device based on state guidance and seed variation, and the method comprises the steps: 1), manually constructing a high-quality basic seed according to an official RFC protocol document, and enabling the seed to be mapped with a corresponding state; 2) inputting the message sequence into a target program for fuzzy testing, interacting with the target program, monitoring a program state, and obtaining feedback; 3) according to the protocol state code and path coverage rate feedback, selecting seeds with high coverage rate to carry out information retention variation, and reserving the state conversion function of the seeds to reduce the number of invalid seeds; and 4) generating a state guide message sequence: selecting a target test state according to a current state and a returned protocol state code, preferentially selecting a state which is not reached or has few arrival times as a target, and then generating a message sequence capable of reaching or approaching the target state according to the basic seed. According to the method provided by the invention, the state information of the protocol is fully utilized, the state conversion capability of the seed is reserved in the seed variation process, and the efficiency and the quality of the network protocol fuzz test are improved through state guidance and targeted message sequence generation.

The invention discloses a container damage information detection counting method based on yolov9 and DeepSort, and the method comprises the steps: collecting the data of a container through a camera, inputting the obtained container data into a trained target detection model and a semantic segmentation model, converging the results of the two models, and transmitting the results to a related system for the next operation. The automatic detection of the damaged position and category information and the accurate statistics of the container throughput are completed. The invention provides a comprehensive and effective method which can be applied to improving the efficiency and quality of container management.

The invention relates to the technical field of quality management, in particular to a real-time quality management method and system for a PVC pipe, and the method can be applied to quality management of the PVC pipe, especially real-time defect detection of a high-speed production line. The method comprises the following steps: firstly, acquiring a multi-modal data set of the PVC pipe in real time and preprocessing the multi-modal data set to obtain preprocessed data; secondly, constructing a deep learning model, extracting multi-scale features of the preprocessed data by using depth separable convolution and asymmetric convolution, and reducing parameters of the deep learning model; thirdly, fusing the extracted multi-scale features by using multi-modal fusion, and carrying out feature dimension reduction in combination with global mean pooling; then, training a deep learning model and evaluating the detection performance thereof; and finally, detecting and alarming the surface defects of the PVC pipe in real time. According to the method, the surface defects of the PVC pipe are detected based on the deep learning model, and the detection accuracy is ensured while the real-time performance of detection is improved.

The invention provides an abnormal network traffic identification method based on small sample data enhancement, and the method comprises the steps: S1, converting one-dimensional traffic data into a two-dimensional gray-scale map, and employing a twin network combined with a dynamic attention mechanism to analyze the differences between various types of traffic data pair by pair; parameters of an attention mechanism in the twinborn attention network are analyzed, and inter-class difference features are identified; s2, selecting a training domain by using the inter-class feature difference matrix, introducing a comparative learning method to judge the difference between real data and generated data, and generating an enhanced data set for each class of traffic; s3, after the enhanced data set issued by the central server is received, each edge server uses the enhanced data set and local sample data to train the twinborn attention network in the step S1; due to different local sample data sets, each edge server is trained to obtain a personalized abnormal traffic identification and classification model suitable for local data distribution, and abnormal traffic is effectively classified.

The invention relates to the technical field of assembly welding, and particularly discloses an assembly welding positioning method and device for automobile parts. A welding state image between a target hush pipe and a target partition plate is collected through a camera; carrying out welding state mask segmentation on the welding state image by using an image identification and analysis algorithm based on computer vision, and then carrying out welding state feature extraction on the segmented welding detection area state mask image; and according to the expression obtained through neighborhood importance optimization of the extracted welding detection state characteristics, intelligent detection on whether defects exist in the welding state between the target hush pipe and the target partition plate or not is achieved. In this way, tiny defects such as tiny cracks and internal pores can be captured, and therefore the accuracy of defect recognition is improved. Moreover, the detection speed is greatly improved, the consistency and stability can be maintained, and the probability of missing detection or false detection is reduced, so that each welding point is ensured to be subjected to strict quality control.

The invention relates to the technical field of industrial intelligent manufacturing, in particular to a flexible production line appearance defect optical detection method. Comprising the steps of performing image acquisition on semi-finished products and finished products on a production line; carrying out preprocessing and spatial transformation on the collected image; performing feature extraction and clustering analysis on the positive sample image of the to-be-detected product by using unsupervised learning to form a feature library; comparing the feature vector of the to-be-detected image with a feature library, and outputting the defect position and type of the sample; an improved RTDETR model with supervised learning is adopted, a sample judged as a defect is used for training, and the improved RTDETR model adopts a ResNet and Visual Transform network structure; and performing real-time detection and result feedback on the deployment model. According to the technical scheme, the appearance defect detection efficiency and the product quality of products manufactured on the flexible production line can be improved.

The invention discloses a low-cost intelligent fire monitoring system and method based on multi-modal data fusion. The system comprises a data acquisition module, a data preprocessing module, a feature extraction module, a data processing module, a dynamic threshold generation module and a fire alarm module. The data acquisition module is used for acquiring data; the data preprocessing module is used for carrying out standardization, denoising and time synchronization on the acquired data of each sensor; the feature extraction module extracts features corresponding to the flame data; the data processing module obtains a classification result whether there is fire or not; the dynamic threshold generation module generates a fire alarm dynamic threshold; and the fire alarm module is used for comparing the final fire probability value with a fire alarm dynamic threshold value and sending out an alarm signal when the probability value is greater than the fire alarm dynamic threshold value, and manual fire extinguishing needs to be carried out in time. According to the method, effective fusion of multi-sensor data is realized, corresponding threshold values can be adaptively adjusted, and the fire prevention capability is improved.

The invention discloses a big data hypergraph network modeling method and device, computer equipment and a product, aims to solve the problem that efficiency and accuracy are difficult to consider when large-scale data of intellectual property is processed in the prior art, and aims at the characteristics of high increment, high timeliness and multiple modes of the intellectual property data. The method comprises the following steps: analyzing and concluding passed intellectual property files, classifying according to corresponding professions, and establishing a corresponding intellectual property text library; constructing a text corpus based on intellectual property by using a BERT algorithm model, performing capsule graph neural network processing on the image information of the corresponding category, obtaining a correlation between image objects and text attributes thereof, and constructing an image database; capturing complex correlation characteristics in the text by utilizing the characteristics of the graph convolutional neural network; and constructing a hypergraph neural network model. The invention provides a big data hypergraph network modeling method capable of processing high-increment, high-timeliness and multi-modal data.

The invention relates to the technical field of rice quality detection, in particular to a head rice rate online detection method and system based on machine vision, and the method comprises the steps: obtaining an initial binary image of a rice image; intelligently screening a rice grain adhesion region in the initial binarized image by using a BP neural network to obtain a to-be-segmented binarized image; segmenting each rice grain adhesion region in the to-be-segmented binary image by using a multi-distance transformation watershed segmentation method to obtain a first segmentation result image; segmenting a rice grain adhesion area in the first segmentation result image by using an angle limitation concave point matching segmentation method to obtain a second segmentation result image as a final segmentation result image; and obtaining the length of each rice grain in the rice image on the basis of the obtained segmentation result image by using a minimum bounding rectangle method so as to calculate the head rice rate of the rice image. According to the method, the segmentation accuracy is improved, the segmentation method is high in applicability, and subsequent measurement of characteristic parameters of single-grain rice is facilitated.

The invention discloses a chamfer defect detection method, device and equipment and a storage medium, and relates to the technical field of defect detection.The method comprises the steps that an obtained to-be-detected device image is preprocessed, and chamfer contour points and chamfer contour point pixel coordinates are determined in the preprocessed image; correcting the pixel coordinates of the chamfer contour points, and fitting a chamfer edge straight line by using the corrected pixel coordinates of the chamfer contour points; according to the chamfer edge straight line, screening the corrected chamfer contour point pixel coordinates, and determining a target chamfer end point; and calculating the actual chamfer length based on the target chamfer endpoint, and comparing the actual chamfer length with the preset chamfer length to judge whether the chamfer has defects or not. According to the method, the detection requirements of chamfers of different shapes and sizes can be met by preprocessing and correcting the images, fatigue and subjective judgment errors possibly existing in traditional manual detection are avoided through automatic image processing and data analysis processes, and the detection efficiency is improved.

The invention relates to the technical field of pressure vessel detection, in particular to a pressure vessel leakage detection device which comprises a transversely-arranged detection barrel, a leakage detection mechanism suitable for sealing detection of various types of pressure vessels is arranged on the detection barrel, and the leakage detection mechanism comprises movable ring bodies arranged at the two ends of the inner side of the detection barrel in a sliding mode respectively. The movable ring body is fixed in the middle of the inner side of the detection barrel, the detector bodies are fixedly installed on the movable ring body and the limiting ring body respectively and arranged in a circumferential array mode, and a positioning assembly capable of limiting the positions of pressure containers of different sizes is arranged on the inner side of the detection barrel. According to the invention, the detection device can detect the sealing performance of containers with different sizes more conveniently, the accuracy of the detection result of the detection device is improved, the application range of the detection device is expanded, the situation that the detection result is easy to have errors when the pressure containers with different sizes are detected by the existing detection device is avoided, and the detection efficiency is improved. And the working efficiency of the detection device is improved.

The invention relates to a power transmission line fire smoke identification method based on improved YOLOv9. The method comprises the following steps: constructing a fire smoke image data set; constructing a power transmission line fire smoke detection model; inputting the training set into the power transmission line fire smoke detection model for training, and storing the optimal power transmission line fire smoke detection model obtained through training; and inputting a to-be-identified power transmission line fire smoke picture into the optimal power transmission line fire smoke detection model to obtain a power transmission line fire smoke picture detection result. According to the method, depth separable convolution is introduced, so that the calculation amount can be reduced, parameters are reduced, and the network detection speed is increased; a parallel weighted mixed domain attention module is adopted to enhance extraction of target features in the fire smoke image; the up-sampling content perception feature recombination network structure CARAFE has a larger receptive field, the perception of important content is enhanced, and the lightweight level of the model can be kept due to the fact that the operation amount is small.

The invention discloses a method and a system for detecting nonuniformity of internal components of transparent glass by adopting OCT (Optical Coherence Tomography). The method comprises the following steps: S1, obtaining a three-dimensional image in the glass through the OCT; and S2, carrying out fault analysis on the three-dimensional image in the glass, and detecting defects in the glass according to refractive index change caused by non-uniform components. By adopting the technical scheme of the invention, the defects of uneven components, bubbles and microcracks in the glass can be accurately positioned and identified, and the quality control level of transparent glass products can be favorably improved.

The invention relates to a target detection method based on lightweight deep learning, and belongs to the technical field of image recognition. The method comprises the following steps: preprocessing an image through a multi-scale Retinex image enhancement algorithm with color protection to obtain an enhanced image, and merging the enhanced image into a training set; in order to solve the problem of missing detection and error detection of small targets, an original 20 * 20 detection head is replaced by a 160 * 160 small-scale detection head, two transverse connection paths are added on the basis of an original neck network, cross-scale fusion is carried out on shallow-layer features and deep-layer features, and the feature fusion capability is further enhanced; the improved model is lightened, a lightweight network MobileNetv3-ECA is constructed to serve as a backbone network of YOLOv5s, a channel pruning method is adopted to compress the network model, and the parameter quantity is further reduced; according to the invention, target detection can be deployed on the edge computing device with low computing power.

The invention discloses blind hole light leakage detection equipment and a detection method, which are used for detecting a blind hole of a screen. The bearing module comprises a rotating disc rotating in the circumferential direction and a plurality of adsorption platforms fixed to the rotating disc, the feeding module is used for conveying the screens to the adsorption platforms, and the adsorption platforms are used for adsorbing and fixing the screens; the correction module is used for correcting the position of the screen on the adsorption platform; the detection module comprises an upper shooting assembly and a lower shooting assembly which are vertically opposite, the adsorption platform is located between the upper shooting assembly and the lower shooting assembly, the upper shooting assembly is used for detecting the upper side of the blind hole of the corrected screen, and the lower shooting assembly is used for detecting the lower side of the blind hole of the corrected screen; and the discharging module is used for sorting and discharging the screens detected by the detection module. The problems that the screen blind hole detection efficiency is low, the position of the to-be-detected screen cannot be automatically corrected, and detection errors are likely to occur are solved.

The invention discloses a distributed collaborative modularized rapid detection method and device for a box-type substation, and the method comprises the following steps: enabling each distributed module to judge whether the distributed module has a fault possibility or not based on collected operation data; the distributed module with the fault possibility initiates an abnormal signaling; after the other distributed modules receive the abnormal signaling, whether correction characteristic parameters of the other distributed modules are filled in corresponding positions in the abnormal signaling or not is confirmed, and the abnormal signaling is sequentially transmitted among all the other distributed modules; and summarizing all the obtained correction characteristic parameters, calculating a posterior fault probability by the distributed module which initiates the abnormal signaling, and judging that a fault exists when the posterior fault probability exceeds a set threshold value. According to the distributed architecture, the bottleneck of a centralized system is avoided, the modules are processed in parallel, and the detection efficiency is improved. Through the feature correlation model, interference of redundant information is avoided, and the accuracy of fault judgment is improved.

The present invention proposes a circuit and working method for realizing power supply monitoring with high efficiency and low power consumption, including a voltage divider circuit, a reference voltage source, a comparator, a high-speed power-on detection circuit, a NOR gate, a clock generation and shutdown circuit, a delay module and an output drive module. The voltage divider circuit is used to generate a reset threshold voltage that is proportional to the input voltage; the reference voltage source is used to generate a reference voltage that is independent of the power supply voltage and temperature; the comparator is used to compare the voltage after voltage division with the reference voltage; the high-speed power-on detection circuit is used to generate an on-chip reset signal of a power supply monitoring circuit with anti-interference capability; the clock generation and shutdown circuit is used to generate a clock signal of a delay unit and shut down a clock generation circuit; and the delay module is used for timing. It introduces a high-speed power-on detection circuit to avoid the reset failure problem caused by the comparator failing to flip in time or the power supply glitch interference, and at the same time introduces a clock shutdown circuit to effectively reduce power consumption.

The invention aims at providing a moon cake sorting method and system based on visual inspection. The method comprises the steps that images of moon cakes to be sorted are obtained; preprocessing the images of the moon cakes to be sorted; and judging and sorting the processed mooncake images. According to the mooncake detection system and method, mooncake images shot at multiple angles are fused, mooncake images at shooting dead corners are intelligently calculated, the technical problem that mooncake defects cannot be detected at the shooting dead corners is solved, mooncake detection models are improved, mooncakes with defects can be detected more rapidly and more accurately, and the mooncake detection efficiency is improved. And the production efficiency of moon cakes is greatly improved.

The invention discloses an Internet of Vehicles anomaly detection lightweight method based on deep learning and knowledge distillation, and the method comprises the steps: carrying out the preprocessing of a time sequence message of each vehicle in a data set through employing a sliding window strategy by employing a public Internet of Vehicles data set VeReMi Extension, obtaining a time window, and dividing the time window into a training set and a test set; constructing a teacher network, and performing reconstruction-based unsupervised learning training by using a large number of normal time windows in a training set; constructing a lightweight student network, and guiding the student network to realize knowledge distillation on the normal time window in the training set by using the trained teacher network; and deploying the trained lightweight student network and the tested preset threshold value to a roadside unit of the Internet of Vehicles, thereby realizing rapid Internet of Vehicles anomaly detection. According to the invention, the knowledge learned by the teacher network with high precision and large capacity is migrated to the lightweight student network, and rapid vehicle networking anomaly detection is realized while the detection precision is ensured.

The invention discloses an implementation method and device for fast scanning CRDS sensing, and relates to the technical field of ring-down cavities, and the method comprises the following steps: employing a PID algorithm to control and adjust the temperature and pressure in a ring-down cavity to stabilize the resonance mode of the ring-down cavity, and carrying out the collection operation of a cavity mode signal after the adjustment of the temperature and pressure is completed; obtaining a wavelength value of the laser light source after entering the etalon based on the transmittance value, feeding back the wavelength value to a wavelength controller, and adjusting the laser to a spectrum detection wavelength by using the wavelength controller; scanning operation is executed based on the detection wavelength to determine the resonant wavelength, secondary scanning is performed with the resonant wavelength as the center to obtain a ring-down curve, and gas characteristic absorption line measurement is completed through point-by-point scanning. According to the invention, the etalon, the precise wavelength locking and adjusting system and the unique cavity mode scanning mode are utilized to realize high-repetition-frequency rapid scanning of the ring-down signal, so that the triggering speed of the ring-down event is improved.

The invention discloses a lightweight scenic spot pedestrian counting system based on improved YOLOv10n and DeepSort. According to the method, an improved YOLOv10n model is adopted as a detector to obtain a target detection result in a video scene. The influence of outdoor weather on a detection result is considered, and the detection result is more accurate under a complex background by fusing an attention feature fusion structure DC-FFA of dynamic convolution. A DeepSort multi-target tracking model is fused, pedestrians are tracked through Hungary matching and Kalman filtering, an SEAMNet36 pedestrian re-recognition network is designed, and appearance features of the pedestrians can be better extracted. In the counting aspect, the counting algorithm based on biconvex trajectory measurement and calculation can count the number of pedestrians in the picture and calculate the number of pedestrians entering and leaving the monitoring picture. According to the method, the model parameter quantity is reduced while the tracking accuracy is improved, the stronger apparent feature extraction capability is realized through a lighter network, the problems of missing detection, false detection, too many ID hopping times and the like in the prior art are solved, and the detection and tracking effects are improved.

The invention provides a bar code detection method and system based on improved YOLOv8, and relates to the technical field of target detection.The method comprises the steps that a sample set with a plurality of bar code pictures is established, and each bar code picture is provided with a bar code position label and a bar code category label; a bar code detection model is constructed, and the bar code detection model comprises a backbone network module, a neck network module and a detection head module which are connected in sequence; establishing a joint loss function comprising a DFL loss function and a CIoU loss function; inputting the extended data set into a bar code detection model to train the bar code detection model until the joint loss function value is smaller than a preset joint loss function value; obtaining a to-be-detected bar code picture; and inputting a to-be-detected bar code picture into the trained bar code detection model, and outputting a predicted bar code position and a predicted bar code category. Detection resource consumption is reduced, and detection accuracy and detection speed are improved.

The invention discloses an isolating switch opening and closing state detection method, which comprises the following steps of: 1, acquiring a plurality of sample pictures of a transformer substation to obtain a data set, and dividing the data set to obtain a training set; in addition, an improved InceptionV3 model is constructed; 2, training the improved model by adopting training set data, and replacing a full connection layer, a Softmax layer and an output layer of the trained improved model by adopting a full connection layer, a Softmax layer and an output layer in an untrained improved model; then, performing fine tuning training on the replaced improved model to obtain an image classification network; and step 3, inputting a to-be-detected transformer substation picture into the image classification network to obtain an isolation switch opening and closing state identification result. The method has the advantages of being high in speed, better in recognition effect and higher in accuracy when detecting the opening and closing states of the disconnecting switch.

The invention discloses a full-automatic transparent bottle curved surface printing detection control system, and relates to the technical field of automatic control, and the main scheme is as follows: obtaining a transparent bottle curved surface printing image through an image acquisition module; the intelligent image processing module is used for accurately analyzing the acquired image, so that the detection speed is increased; image information of the image acquisition module and the intelligent image processing module is transmitted to the central control module for comprehensive processing, and a parameter control instruction C and a fault control instruction H are sent out according to a processing result, so that the stability of the system is ensured; the feedback adjusting module adjusts the detection equipment according to the parameter control instruction C and the fault control instruction H, so that the detection efficiency is improved; the evaluation module judges whether the printing effect is qualified or not according to the comprehensive evaluation value M and the comprehensive evaluation threshold value Ma and reflects the actual condition of the printing effect; the early warning module gives out early warning when the printing qualified rate U is lower than the printing qualified rate threshold value Uc.

A method for automatically generating a three-dimensional model of power transmission line construction equipment comprises the following steps: performing target detection on a to-be-detected image based on an SSD network model and generating candidate boxes, and screening the candidate boxes by using a non-maximum suppression method to obtain a to-be-reconstructed image; the method comprises the following steps of: performing feature point extraction and matching on any two to-be-reconstructed images by using an SURF algorithm and an AKAZE algorithm to obtain a first feature point matching set and a second feature point matching set, and finally performing three-dimensional reconstruction on the power transmission line construction equipment based on the first feature point matching set and the second feature point matching set to generate a three-dimensional model of the power transmission line construction equipment. According to the method, on the basis of extracting the main feature points by using the SURF algorithm, the edge feature points are extracted by using the AKAZE algorithm, so that the extracted feature points are more comprehensive, and the subsequent three-dimensional model reconstruction precision is further improved.

The invention discloses an unmanned aerial vehicle low-altitude visual angle target detection method and device based on deep learning, and belongs to the technical field of computer vision. The method comprises the following steps: performing data enhancement on a collected target detection object image data set, and dividing the enhanced target detection object image data set into a training set, a verification set and a test set; an attention mechanism module is added in a backbone network of the YOLOV7-OBB model; the YOLOV7-OBB model is trained based on the training set, the YOLOV7-OBB model in the training process is evaluated based on the verification set, and the trained YOLOV7-OBB model is obtained; and inputting the test set into the trained YOLOV7-OBB model, and carrying out target detection to obtain a detection result. By enhancing a target detection object image data set and adding an attention mechanism module, the YOLOV7-OBB model fully learns key feature information of a target, and the detection precision and robustness are remarkably improved.