120 results about "Foreign object detection" patented technology

The application discloses a pharmaceutical raw material foreign matter detection method and system based on image analysis and a terminal, and belongs to the technical field of pharmaceutical raw material detection. The method comprises the following steps: performing image acquisition on the pharmaceutical raw material to obtain an initial image set; performing a pre-processing operation on the initial image set to generate a basic image set; and performing a foreign matter identification operation on the basic image set to determine a basic image containing foreign matter as a foreign matter-containing image. The method excludes position offset false positives through a process of first performing position correction and then performing review identification, improves correction accuracy by dividing the foreign matter-containing image into shape groups according to the shape features of the foreign matter and calculating the average offset of the groups, and dynamically optimizes the correction process through a closed-loop feedback mechanism of generating an updated offset value after review to re-perform position correction, thereby improving the accuracy, reliability and robustness of detection.

The application belongs to the technical field of weak and small target recognition of nuclear power plants, aims to solve the problem that the existing target detection method is difficult to effectively detect high-speed falling foreign matters, discloses a high-speed weak and small foreign matter detection method based on event and image fusion, carries out data acquisition, constructs a real data set, calibrates the real data, constructs a simulation data set for data enhancement, constructs a cross-modal feature fusion model by using a physical model of a motion image and an event stream generation mechanism, carries out adaptive space-time alignment on the event stream and the video frame image, carries out cross-modal data complementary enhancement fusion on the event stream and the video frame image after space-time alignment, carries out training by using a target detection network, and carries out feature extraction of weak and small targets by combining local and global attention. The application can effectively detect high-speed falling foreign matters by combining event and image information, combining the instant reactivity of event data and the detail retention of image data.

The application discloses a railway catenary foreign matter detection method based on frequency-space cooperation purification, and relates to the field of railway engineering technology.The method comprises the following steps: at the front end of the main network, input shallow feature maps are respectively processed by a spatial domain adaptive compensation branch and a frequency domain dynamic filtering branch, and a purified feature map is obtained through fusion; the bottleneck layer of a feature extraction module in the main network is reconstructed, and linear topological features are extracted by using a multi-scale parallel strip convolution path; a spatial attention map is generated by a shape perception substream for the feature map output by the neck network, pixel-level weighting is performed on the regression substream features, and a bounding box prediction result is output, and the network is trained by using a total loss function comprising a classification loss, a bounding box overlap loss and a shape penalty loss.The application can inhibit regular background noise, improve the continuity of foreign matter feature expression, and help improve the positioning accuracy of small foreign matters.

This invention discloses a lightweight method for detecting foreign objects (FOOs) in power transmission lines, relating to the fields of power line inspection and computer vision. A YOLOv10-based FEO detection model is constructed, comprising a feature extraction part, a feature interaction part, and a detection head part. The C2f module in the feature extraction and feature interaction parts is replaced with an expert dynamic extraction module, and the detection module in the detection head part is replaced with a parameter-sharing detection module. The trained FEO detection model is obtained by collecting and evaluating a calibrated FEO dataset of power transmission lines. FEO keyframes are input into the trained FEO detection model to obtain detection results. The expert dynamic extraction module acquires feature maps from multiple receptive fields, achieving rich representation in FEO detection environments with varying scales. The parameter-sharing detection module, based on this, reduces redundant computation and enhances the semantic representation of small targets through parameter sharing and grouping normalization, effectively improving the efficiency of FEO detection in power transmission lines.

The present invention relates to the technical field of object detection. Disclosed are a training method and apparatus for a railway foreign object phrase localization model, and a device and a medium. Cross alignment can be performed on an image feature vector and a text feature vector, so as to obtain an aligned image feature vector and an aligned text feature vector; the pair of the aligned image feature vector and the aligned text feature vector is then used to perform training, such that a model can accurately align a foreign object described in a text with a target region in an image, thereby ensuring accurate phrase localization in a complex scenario, and being applicable to fine-grained scenario description in railway foreign object detection; and a trained railway foreign object phrase localization model can thus effectively execute and complete railway foreign object phrase localization tasks, thereby effectively implementing phrase localization of railway foreign objects.

This utility model relates to a foreign object detection device before packaging of automotive crystal oscillators, including a Y-axis slide, an X-axis slide, and a vision screening component. The vision screening component is installed on the side of the Y-axis slide, which is installed on the X-axis slide. The vision screening component includes a light source backplate, a coaxial light source, a ring light source, and a shadowless light source installed on the side of the Y-axis slide. From top to bottom, a camera, a lens element, a coaxial light source, a shadowless light source, and a ring light source are sequentially installed on the side of the light source backplate. A vertically arranged cylinder is arranged at the lower part of the light source backplate, outside the coaxial light source, the shadowless light source, and the ring light source. A suction nozzle fixing component that slides up and down is installed on the side of the cylinder. The piston rod at the lower end of the cylinder is connected to the suction nozzle fixing component, and a suction nozzle is fixed on the suction nozzle fixing component. This utility model achieves high-precision scanning and analysis of every automotive crystal oscillator on the production line, accurately identifying and removing foreign objects or defects, and preventing defective products from flowing out at the source.

This invention relates to the field of intelligent driving and path planning technology, and particularly to an autonomous driving path planning method based on tire trajectory strip pre-aiming. The method includes acquiring vehicle control parameters and constructing tire trajectory strips for each tire accordingly; collecting road environment information in real time through an onboard perception module to construct a two-dimensional grid map for foreign object detection on each tire trajectory strip; classifying the detected foreign objects by category and hazard level, and constructing a hazard intensity grid map; constructing a trajectory strip mask for each tire based on the two-dimensional grid map, and calculating the tire safety risk index for each tire in conjunction with the hazard intensity grid map; and performing path risk assessment and optimization based on the tire safety risk index. This invention, by constructing tire trajectory strips and introducing a pre-aiming mechanism, refines safety considerations to the tire level, which is in direct contact with the road surface, thereby improving tire lifespan and vehicle driving safety.

The application discloses a foreign matter detection circuit applied to a wireless charging system transmitting end and a method thereof, and the circuit comprises a sampling circuit, a linear voltage stabilizing source, two comparators and a microprocessor; wherein the linear voltage stabilizing source is responsible for charging a resonant cavity circuit, the sampling circuit samples a resonant waveform, filters out a negative voltage and outputs the same to the comparators, the comparators extract resonant frequency, resonant time and peak value information, and the microprocessor calculates a Q value through the information and performs foreign matter detection judgment. The application can not be affected by a specific structure resonant cavity, a delay of a wireless charging system transmitting end full-bridge inverter driving circuit and a comparator offset voltage in the foreign matter detection circuit, and can realize extremely high foreign matter Q value detection precision under a higher resonant frequency, and has important significance for improving a safety coefficient of wireless charging system application.

This invention discloses a terahertz-band foreign object detection radar system and method for airport runways. The system includes: a transmitting module for generating and transmitting a 240 GHz frequency-modulated continuous wave detection signal; a receiving module for receiving the echo signal and down-converting it to an intermediate frequency signal; a turntable system for driving the transmitting and receiving modules to rotate synchronously for azimuth scanning; and a digital control and processing module for generating baseband waveforms, acquiring angle information and intermediate frequency signals, and performing data processing to detect and locate foreign objects. This invention utilizes the physical law that the radar cross-section of a target is inversely proportional to the fourth power of its wavelength, fundamentally enhancing the electromagnetic scattering response of small targets and achieving high-sensitivity detection of millimeter-sized metal debris and non-metallic foreign objects, providing a reliable technical solution for foreign object detection on airport runways.

This foreign matter detection device comprises an acquisition unit and a determination unit. When a substrate work machine performs prescribed work on a substrate, the acquisition unit captures images of an inspection region of at least a portion of the substrate as the work on the substrate progresses, and acquires multiple pieces of image data resulting from capturing of images of the same inspection region. The determination unit determines the presence / absence of foreign matter adhered to the inspection region, on the basis of inspection region characteristic-amount differences, obtained by image processing: reference image data, which is a one piece of image data of said multiple pieces of image data; and inspection image data, which is image data to be inspected and acquired after the reference image data. Furthermore, if the work on the substrate stops after the acquisition of the reference image data but before the acquisition of the inspection image data, the acquisition unit acquires an image of the inspection region at the point in time when the work on the substrate stopped, to obtain image data, which is first image data.

The application discloses a PCBA foreign matter detection method based on a multi-resolution subspace projection, acquires a to-be-detected board and a standard reference board image, determines an adaptive down-sampling multiple based on a minimum foreign matter physical area, performs image registration with the aid of a mask to eliminate geometric deformation, extracts a multi-resolution feature map through a pre-trained deep convolutional neural network, calculates feature differences, and uses a dynamic threshold to screen a preliminary candidate point set, constructs a local principal component subspace of a local neighborhood of a reference image, performs first-stage screening by calculating the orthogonal projection error of a test feature vector in the space, maps remaining candidate points to a multi-scale feature space and splices them, constructs a global multi-scale principal component subspace, performs second-stage screening through a global projection error, and outputs a final result selection, and through the implementation of the application, the problems of a high-definition image computing power bottleneck and a high false alarm in comparison are solved, the application has zero-sample generalization capability, and sample-free training can accurately detect tiny foreign matters.

In one embodiment, a semiconductor device is disclosed comprising a buffer circuit configured to selectively output a charging signal to an inductor-capacitor node of a power driver to charge the inductor-capacitor node to a predetermined voltage level, and an amplifier circuit configured to monitor a voltage difference across a capacitor of the inductor-capacitor node of the power driver. The amplifier circuit is configured to output a positive-side signal and a negative-side signal. The semiconductor device further comprises an output configured to provide at least one signal, based on the positive-side signal and the negative-side signal, to an analog-to-digital converter for measurement by a controller.

This application provides a method, apparatus, and electronic device for foreign object detection. In this application, by establishing a loss function for each pixel in an X-ray sample image and optimizing the loss function corresponding to that pixel, the mass thickness of each suspected component belonging to that pixel is obtained for foreign object detection. This eliminates the limitation on the number of components contained in the sample, thereby avoiding false alarms and missed alarms caused by the inability to accurately identify foods containing three or more components simultaneously, thus improving the accuracy of foreign object detection.

The utility model provides a kind of canning line foreign matter detection tank turning mechanism, it is related to canning production line technical field, including workbench one and workbench two, workbench two is equipped with mounting pedestal, a pair of installation side frames is installed on mounting pedestal, installation top plate is installed on the pair of installation side frames, link is movably installed in the bottom of installation top plate, the bottom of link is equipped with several knock balls, collection groove is equipped with suction air inlet in the bottom end in the pair of installation side frames between on mounting pedestal, workbench one and workbench two are all equipped with a pair of side plates, conveyor is installed between the pair of side plates, workbench one is installed with turnover machine in the one end of mounting pedestal, the bottom end of turnover machine is connected with the pair of installation side frames.This device is knocked to the top of the tank body by knock ball, is favorable to the granular matter inside tank body drop, is convenient for tank body foreign matter removal, improves tank body production efficiency and quality.

This invention discloses a method and system for detecting foreign objects in food based on dynamic routing with information entropy and graph convolution, belonging to the field of food detection technology. This invention generates a corresponding two-dimensional information entropy feature map by calculating the discrete data of a multi-scale basic feature tensor. This map is then input into a routing gating network to generate a spatial routing mask. The spatial routing mask is used to partition the multi-scale basic feature tensor into high-entropy and low-entropy feature streams, which are then subjected to topological and convolutional processing to generate first and second discriminative features. These features are then fused with the spatial routing mask to generate a full-graph fusion feature tensor, which is then input into an evidence decision network. The network outputs category judgment confidence and cognitive uncertainty, which are then compared to determine whether to generate a physical interception command and output a foreign object rejection result. This reduces the false detection rate of foreign objects in food detection and solves the problem of increased false detection rates in existing technologies.

This invention provides a method, apparatus, electronic device, and storage medium for detecting in-mold foreign objects, belonging to the field of intelligent manufacturing technology. The method includes: acquiring an image of the mold to be detected in response to a detection trigger signal; extracting an image of the region of interest and comparing it with a template image to obtain a difference region; acquiring image texture feature parameters of the difference region; determining, based on the parameters, whether the difference region is a false difference caused by ambient light interference or a real difference caused by a physical foreign object; if it is a false difference, updating the image to the template image set as a comparison benchmark; if it is a real difference, outputting an abnormal signal. This invention analyzes image texture features to deeply determine the physical attributes of the difference, effectively distinguishing between light interference and real foreign objects, achieving adaptive template updates under changing ambient light, overcoming the shortcomings of traditional visual detection that is easily affected by lighting, significantly reducing false alarm rates and manual maintenance costs, and improving the detection accuracy of the system.

The application provides a kind of multi-modal track foreign matter detection method and system for large language model, it is related to track foreign matter detection technical field, method includes: obtaining the multi-modal data of track scene, multi-modal data includes visible light image and thermal imaging image, multiple modal characteristics are obtained by parallel inputing multi-modal data into multi-branch fusion network;The multiple modal characteristics obtained are respectively adaptively weighted and fused by dynamic gate fusion module to output multiple fusion characteristics, and the comprehensive characteristics are obtained by channel splicing to multiple fusion characteristics;The channel compression processing is carried out to comprehensive characteristics by light channel dimension reduction network, and the final detection feature is obtained by combining double residual connection mechanism, and the track foreign matter detection result is output by the neck network and detection head to realize track foreign matter detection, and the detection result includes foreign matter position coordinates and class confidence degree.The application also has the intelligent research and judgment ability to foreign matter attribute and threat level.

This invention discloses a method for detecting foreign objects on power transmission lines that integrates edge perception and multi-scale feature fusion. The method includes the following steps: scaling and normalizing images to obtain batch tensor data; the backbone network performs spatial compression and channel expansion of features through hierarchical convolutional downsampling, extracts multi-directional edge gradients in parallel using multi-directional Sobel convolutional kernels, filters effective edge information through directional attention mechanisms, and achieves dynamic balance between edge features and semantic features through dual-branch gating fusion to generate a multi-scale basic feature map; the neck network transforms the multi-scale basic feature map into a multi-scale fused feature map through dynamic alignment, background noise suppression, and multi-scale feature aggregation; and the head network obtains the detection result by performing target detection and redundant box filtering on the multi-scale fused feature map. This invention improves the detection accuracy and environmental adaptability for various types of foreign objects on power transmission lines while maintaining real-time performance.

The present application relates to the field of railway safety monitoring and computer vision, and specifically discloses a railway catenary foreign matter detection method based on improved YOLOv11, which comprises the following steps: collecting and labeling catenary scene images containing floating objects and bird nests and other foreign matter targets, constructing a catenary foreign matter detection dataset through data enhancement; taking YOLOv11 as the basis of the detection network, introducing a re-parameterized hollow convolution feature enhancement structure into the backbone network, introducing a multi-scale guided fusion and background suppression mechanism in the feature fusion stage, and introducing a multi-scale adaptive task collaborative detection structure in the detection head; training and optimizing the model using the dataset, inputting the image to be detected into the trained model, and outputting the foreign matter category, target position and confidence result. The present application can improve the precision and stability of railway catenary foreign matter detection.

The application provides a simulation platform system for runway foreign object detection system joint debugging test, comprising: a detection device control module for simulating all detection devices in the runway foreign object detection system; a foreign object reporting and graphic evidence obtaining module for verifying a radar foreign object discovery process and a camera photographing evidence obtaining process in the runway foreign object detection system; a target fusion module for multi-device discovery for verifying the accuracy of a target fusion method used when one foreign object is simultaneously detected by multiple detectors in the runway foreign object detection system; and a mobile terminal module for simulating the operation of a mobile terminal. Through the simulation platform system, the deployment, joint debugging and test of the management system service can be carried out without accessing an actual deployment environment, and the function of the runway foreign object detection management system can be quickly verified and tested.

This invention discloses a fully automated quality control method for knee joint DR radiographs based on multi-task deep learning and geometric quantization. The method includes: using DICOM format knee joint DR images as input data and performing data preprocessing; constructing a multi-task model architecture comprising a knee joint anteroposterior and lateral bone segmentation model, a knee joint anteroposterior and lateral keypoint detection model, a foreign object detection model, and a left / right marker detection model, defining the network infrastructure and input / output of each model; calculating quality control-related indicators based on the bone mask, keypoints, foreign object detection results, and left / right marker detection results output by the four models; formulating scoring rules to score the quality of knee joint DR images, and performing automatic quality control of knee joint DR images. This invention achieves objective, efficient, and quantifiable knee joint DR image quality assessment by automatically extracting anatomical structures, calculating geometric parameters, and executing scoring rules, providing a reusable technical paradigm.

The present disclosure relates to a kind of deep learning-based belt conveyor multi-operation state detection method and device, method includes: real-time acquisition conveyor operation monitoring image;The feature of monitoring image is extracted using feature extraction network, and the feature is respectively input into segmentation network and prediction network;Monitoring image is carried out semantic segmentation using segmentation network, and the material load area and the edge line of both sides of conveyor belt are obtained;According to material load area, detect load, according to the edge line of both sides of conveyor belt, judge the deviation state of conveyor belt;Through prediction network, obtain the detection frame for multi-class target;According to the detection frame of multi-class target, obtain the detection result of conveying foreign matter, conveyor belt damage, conveyor belt water accumulation, conveying along line material scattering, conveying area smoke, conveying area fire.The above method makes single network model can simultaneously realize the multi-task of including load detection, conveyor belt deviation state detection, large block conveying foreign matter detection, conveyor belt damage detection and so on, provides support data for the safety control in the process of material transportation.

To provide a foreign object inspection device that is advantageous for foreign object inspection. [Solution] A foreign object inspection device for inspecting foreign objects on an object, comprising: a first light source for inspecting foreign objects in a first region of the object; and a second light source having higher directivity than the first light source and for inspecting foreign objects in a second region of the object different from the first region, wherein the inspection of foreign objects in the first region and the inspection of foreign objects in the second region are performed in parallel.

This invention provides a method, apparatus, and electronic device for detecting foreign objects (FOOs) on airport runways. The method involves acquiring first laser point cloud data of the airport runway using each lidar sensor; dividing the first laser point cloud data into ground point cloud data and non-ground point cloud data; if at least one potential FEO is detected based on the non-ground point cloud data, each potential FEO is then screened; if a target FEO is detected from the at least one potential FEO, the target FEO is located to determine its position information. This method divides the first laser point cloud data acquired by multiple lidar sensors into non-ground point cloud data, detects potential FEOs based on the non-ground point cloud data, and then further screens and detects the target FEO, thereby improving the efficiency and accuracy of FEO detection on airport runways.

This invention relates to the field of rice noodle cake processing equipment, and in particular to a foreign object detection device for rice noodle cakes. The device includes a frame, a conveyor belt, and a detection box mounted on the frame. The detection box has an inlet on one side and an outlet on the other. The conveyor belt passes through the inlet and outlet of the detection box, and an image acquisition module is installed inside the detection box. A rejection device is mounted on the frame, comprising a blower mechanism, a material cutting mechanism, and a material receiving box. The blower mechanism and the material receiving box are located on opposite sides of the conveyor belt. The material cutting mechanism is located on the upper side of the conveyor belt and can cut off the material on the conveyor belt. The air outlet of the blower mechanism is located on the upper side of the conveyor belt and on the side of the material cutting mechanism closest to the detection box. The blower mechanism blows air towards the material receiving box. By adopting the above technical solution, unqualified rice noodle cakes can be accurately rejected, thus improving the work efficiency of the staff and the accuracy of foreign object detection.

This invention relates to the field of battery technology, and in particular to a washing device for the surface of a cylinder and a method for detecting magnetic materials. The washing device includes: 1) a mechanical rotation system; 2) a fluid supply system; 3) a water collection and recovery system; and 4) a central control system. The washing device for the cylindrical surface of this invention achieves complete control of washing elements, including washing angle, washing speed, washing flow rate, and washing time, through electromechanical and fluid control. This fundamentally eliminates the uncertainty of manual operation and ensures high consistency and repeatability of batch cleaning results.