1580 results about "False detection" patented technology

The invention relates to the technical field of artificial intelligence, and discloses an AI-based composite insulator internal defect ultrasonic detection method, which comprises a multi-mode ultrasonic probe array module, a signal preprocessing module, an AI defect analysis module, a dynamic parameter optimization module, an edge calculation module and a visual report module, the method comprises the following steps: acquiring a full-dimensional signal through a multi-modal ultrasonic probe array, and inputting the full-dimensional signal into a deep space-time convolutional neural network for defect recognition after adaptive noise reduction and feature fusion; the detection precision is improved by combining dynamic waveform matching and multi-physics coupling analysis; model lightweight and real-time processing are realized by adopting transfer learning and edge calculation. The system integrates the functions of parameter adaptive optimization, three-dimensional visualization and Internet of Things cooperation, solves the problems of low efficiency and high false detection rate of a traditional detection method, and improves the intelligent level and engineering applicability of composite insulator defect detection.

The invention relates to the field of insulator nondestructive testing, and discloses an insulator product surface defect nondestructive testing method based on AI identification, and the method comprises a data acquisition module, a preprocessing module, an AI analysis module, a decision output module, a self-optimization module, and an edge calculation node. Through multi-modal data fusion and a deep convolutional neural network technology, accurate detection of surface defects such as cracks, dirt and damage is realized, the omission ratio and the false detection rate are reduced, and the detection precision is improved compared with the traditional manual inspection efficiency; visible light, infrared thermal imaging, ultrasonic waves and hyperspectral data are combined, the surface and internal defects of the insulator are comprehensively covered, the detection rate of tiny cracks and hidden dirt is increased, and the technical limitation of a single sensor is broken through.

The invention provides an end-to-end tiny target detection method, and aims to solve the problems of missing detection and false detection of tiny targets caused by interference of sparse features, halo, noise and the like. According to the method, a TINYDETR model is constructed, and the TINYDETR model is composed of an HGNetv2 backbone network, an LGFSI module, an SO-CSFF module and a decoder with an auxiliary prediction head. Wherein the LGFSI module realizes global-local information interaction through joint modeling of a frequency domain and a spatial domain, and background interference is effectively suppressed; the SO-CSFF module enhances the fusion of shallow details and deep semantics through a bidirectional feature flow mechanism, and enhances the feature expression of a tiny target. After the model is trained and optimized, high-precision detection of a tiny target can be realized.

The invention discloses an intelligent data query system and method based on natural language processing, and relates to the technical field of natural language processing and database query. According to the method, natural language input and database mode information are received, a historical query log is combined to construct mode knowledge representation, a query skeleton is generated on the basis, a fine-tuned large language model is called to generate candidate SQL statements, error detection and ambiguity recognition are carried out on the candidate statements, and the query result is obtained. And if necessary, triggering interaction clarification and updating a query result according to user feedback. And meanwhile, the wrong clauses are locally repaired through a gating mechanism, and the clauses are returned and regenerated when multiple times of repair fails, so that the correctness of the query statement is ensured. And finally, after the SQL is executed in the database, a result is fed back to the user. Besides, the system records generation and repair tracks in the operation process, and continuously optimizes the model based on reward shaping, comparative learning and self-game training, so as to improve the generalization ability in different business scenes.

The invention discloses a burn wound image detection method based on an attention-enhanced convolutional neural network, and belongs to the field of medical image artificial intelligence target detection. The method comprises the following steps: establishing and marking a burn wound skin image data set, introducing a Swin Transform and an LSKA attention module in series behind a spatial pyramid pooling fast module (SPPF) at a backbone part of a YOLOv11 network, forming an enhanced Backbone of SPPF-Swin-LSKA, and realizing collaborative optimization of global modeling and local detail perception; and cross-layer feature routing and multi-scale prediction layer configuration are redesigned at a Head end so as to improve the detection capability of a small target and the recognition performance under a complex background. The method can effectively reduce missing detection and false detection, improves the detection stability and robustness, and has good real-time performance and clinical application value.

The invention relates to the technical field of target detection, in particular to a search and rescue task-oriented unmanned aerial vehicle thermal imaging visual target detection method, which comprises the following steps of: acquiring multiple frames of thermal imaging images of an unmanned aerial vehicle, extracting regional thermal difference characteristics according to a window, marking a non-background region to generate a candidate set, and fitting and reconstructing a suspected thermal target contour. And analyzing the track and the thermal change rate, screening background interference, identifying jump abnormity, positioning the gravity center, and generating a target repositioning signal. According to the method, the heat value range and variance index sequence in the image area is constructed, the thermal anomaly area is judged in combination with the temperature baseline difference, background disturbance comparison is executed in combination with the direction vector of the coordinate trajectory in the multi-frame image and the thermal change parameter, the false detection probability caused by background noise is reduced, and the detection accuracy is improved. The target jump identification is carried out according to the inter-frame heat value and area change rate in linkage with the thermal isoline closure degree, the target discrimination accuracy in a shielding scene is improved, and the robustness of thermal target extraction in a complex search and rescue environment is integrally improved.

The invention provides PCB deviation detection equipment and a detection method, and relates to the technical field of PCB detection, a feeding arm and a carrying arm are matched with a partition adsorption and pressing assembly to be matched with a detection platform and a feeding platform, so that the problem of uneven adsorption of an FPC is effectively avoided; the detection platform adopts the adsorption assembly with adjustable spacing, and the levelness is accurately regulated and controlled by combining with the jackscrew adjusting piece, so that the detection platform can adapt to the layout of components on the back of the PCB to avoid interference, and can guarantee the bearing stability and eliminate the positioning deviation. Meanwhile, the detection method supports the combination of PCBs and FPCs with different characteristics in a terminal area, and by calculating X and Y bidirectional deviation values, the adaptive range is widened, the detection precision is improved, and the missing detection and false detection rate is reduced.

The invention discloses an equipment fault prediction method based on industrial causal logic. The method comprises the following steps: acquiring an unbalanced equipment monitoring data set; missing value processing is carried out on the unbalanced equipment monitoring data set, and a causal relation graph is established; quantifying a causal relationship and calculating a causal weight matrix; constructing a causal constraint generative adversarial network, taking a causal weight matrix as an attention weight to generate a synthetic fault sample, combining the synthetic fault sample with an original fault sample to form a balanced fault sample set, and finally combining the balanced fault sample set with a normal sample set to form a balanced data set; and training a classifier based on the balanced data set and outputting a fault prediction result. According to the method, by identifying and utilizing the physical causal relationship in the equipment data, it is ensured that the generated synthetic equipment state sample strictly follows the engineering logic, unreasonable engineering samples generated by a traditional method are avoided, the accuracy of equipment fault prediction is remarkably improved, and therefore the equipment shutdown loss caused by false detection and missing detection is reduced.

The invention provides a target frame detection optimization method based on a millimeter wave radar, a medium and electronic equipment. The method comprises the following steps: acquiring an initial target frame set generated based on the millimeter wave radar; calculating an overlapping area ratio of any two target frames in the initial target frame set; and determining an output target frame according to the overlapping area proportion and updating the initial target frame set. The method effectively solves the problem of frame size estimation deviation caused by point cloud sparsity in a traditional method, improves the precision and reliability of target detection, achieves the adaptive processing of a complex road scene, effectively reduces the false detection rate, improves the accuracy and stability of a detection result, and improves the detection efficiency. And the perception performance of the automatic driving system can be effectively improved.

Techniques for applying a generative artificial intelligence (AI) model to identify and correct anomalies in remediation records are disclosed. A system trains and applies a generative AI model to displayed datasets to predict remediation record anomalies. If the system detects the generation of a remediation record in a dataset to reconcile the displayed datasets, the system generates a generative AI prompt that includes the remediation record. The generative AI model generates an output that identifies anomalies in the remediation record and the datasets being reconciled. The generative AI model further generates recommendations for remediating errors in the remediation record.

The invention belongs to the technical field of intelligent detection of new energy equipment, and particularly relates to a solar panel defect detection method and system, computer equipment and a storage medium, and the method comprises the following steps: a lightweight defect preliminary screening and adaptive shooting step: carrying out the recognition and image collection of a solar panel array through a lightweight model at the edge end of an unmanned aerial vehicle; a defect segmentation and type identification step: performing accurate segmentation on the solar panel and the defects through a neural network model, and judging the types and grades of the defects in combination with a feature extraction and classification model; a defect enhancement optimization step: enhancing the defects through an adversarial network; a detection performance evaluation step: quantitatively evaluating the overall performance of the system through a multi-dimensional index; mSAN-Net network segmentation is adopted, so that the defect detection precision is improved; and in combination with a GAN defect enhancement technology, the omission ratio and the false detection rate of weak defects are reduced, so that the fine operation and maintenance requirements of the solar panel are met.

The invention belongs to the technical field of intelligent manufacturing, and particularly relates to a paperboard sorting and self-adaptive indentation intelligent control system based on machine vision, which comprises an indentation operation component, a sorting visual identification component, a finished product transportation line and a defective product transportation line, and further comprises a self-adaptive indentation control system, an integrated thin film pressure sensor is mounted in the indentation cutter in the indentation machine; an image acquisition and processing unit, a time-illumination association unit, an adaptive shooting adjustment unit, an optimal frame selection strategy unit, a motion control and cooperation unit, a regular verification unit and a pressure adjustment unit are arranged in the adaptive indentation control system. Visual inspection is introduced, reflection interference can be eliminated, the problem of false detection caused by reflection of the film-coated paperboard in traditional single-light-source shooting is solved, the image recognition capacity is excellent, the screening efficiency is high, technological parameter backtracking and optimization are supported, and the yield only has small deviation due to seasonal fluctuation.

The invention relates to the technical field of pipe network detection, in particular to a target detection method, system and device based on image recognition and a medium, and the method comprises the following steps: obtaining a data packet in a mechanical mining process; preprocessing the data packet to obtain a target point cloud; performing target positioning of the underground pipe network according to the preprocessed data to obtain a target area; a baseline database of the underground pipe network in the target area is obtained, target detection is conducted on the change trend of the baseline database along with the time sequence, and health data are obtained; according to the acquired health data and the data packet, acquiring detection data of the target area; through time synchronization packaging and semantic fusion of heterogeneous sensor data, a target point cloud containing space-time correlation characteristics is constructed, and progressive monitoring of the cable health state is realized in combination with time sequence analysis of a dynamic baseline database. The problems of leak detection and false detection of cable detection in a complex environment are effectively solved.

Techniques are provided for artificial intelligence (AI) based application error detection and resolution. Extensive amounts of time and resources are consumed by service providers when attempting to resolve application errors experienced by customers. Unfortunately, a service provider may spend tedious amounts of manual effort to evaluate and solve an error that is already known or already solved. The techniques provided herein reduce the amount of time and resources involved in detecting and resolving errors associated with applications. In particular, an error mapping is generated for a current troubleshooting case to resolve for an application. The error mapping is compared to error mappings of previously resolved troubleshooting cases. If a match is found, then a troubleshooting action associated with a previously resolved troubleshooting case is suggested or executed. Otherwise, a service ticket is created for solving the current troubleshooting cases.

The invention discloses a complex scene target detection method based on a model dynamic joint mechanism, and the method comprises the steps: carrying out the preliminary detection through an RT-DETR model, retaining more potential targets through dynamic threshold adjustment, and projecting a generated detection frame to a feature space of an improved YOLOv12 model through dual-mode feature mapping; the improved YOLOv12 model integrates an SEAM attention module and a rejection loss function so as to enhance feature representation and positioning compactness of an occluded target. Then, a model joint mechanism is adopted to process preliminary results of the two models; through difficult case mining and online learning, missing detection targets are supplemented, and the RT-DETR model is optimized; and intelligently fusing the detection results of the two models through dynamic weight distribution based on scene complexity and hierarchical fusion of a decision tree. And finally, post-processing is carried out by using an improved non-maximum suppression algorithm, and mistaken deletion is reduced. According to the method, the problems of missing detection, false detection and inaccurate positioning of the target in a complex scene are effectively solved, and the recall rate and the accuracy rate of detection are remarkably improved.

The invention discloses a pavement crack identification method and system based on YOLOv8-Seg, and belongs to the technical field of road engineering pavement maintenance. The method comprises the following steps: identifying a pavement crack slice image by using a trained YOLOv8-Seg segmentation model, and generating a mask area of a crack; extracting attribute information of the crack, wherein the attribute information comprises a center point coordinate, a bounding box, a crack area and a mask binary image; performing space-time continuity analysis on a plurality of images continuously acquired in the same road range, and judging whether cracks with similar forms and similar positions exist or not; and if cracks with similar forms and similar positions exist in the images of the at least two different point positions, determining that the cracks are real cracks, and outputting an identification result. According to the method, crack pixel-level segmentation and attribute extraction are realized, cross-image space-time continuity analysis is combined, crack authenticity is judged, the false detection rate is effectively reduced, and the identification accuracy and engineering applicability are improved.

The invention particularly relates to a bituminous pavement crack multi-scale segmentation method based on image recognition, which relates to the technical field of crossing of computer vision and road engineering, and comprises the following steps: extracting multi-scale features from shallow details to deep semantics, balancing feature expression capability and vehicle-mounted real-time processing requirements, and providing a multi-level feature source for feature fusion; a channel and space double-branch attention architecture is constructed, features of each coding stage are dynamically screened, noise is suppressed, and refining features are generated through dynamic residual fusion. In the feature fusion stage, a channel and space double-branch attention architecture is adopted, useful features are dynamically screened, details and semantics are balanced through a dynamic threshold correction mechanism, and segmentation imbalance caused by low-quality input is avoided; in the post-processing stage, background false detection, crack breakpoints and edge sawteeth are eliminated through a three-step progressive process, and multi-index comprehensive evaluation such as intersection-to-union ratio and F1-score is combined to ensure that a segmentation result meets the requirements of pavement maintenance engineering on precision and stability.

The invention relates to the technical field of visual positioning, and discloses a visual positioning method, device, equipment and system. The method comprises the steps of obtaining a current image frame; extracting a first candidate frame similar to the current image frame from a map database; checking the continuity between the current image frame and the first candidate frame according to the current image frame and the first candidate frame to obtain a second candidate frame adjacent to or connected with the timestamp of the current image frame; obtaining an initial pose of the current image frame relative to the second candidate frame, and calculating a pose of the current image frame in a map according to the initial pose; checking whether the current image frame is a false detection frame or not according to the pose; and when the detection result is not the false detection frame, performing visual positioning according to the pose. According to the method and the device, the accuracy and the precision of visual positioning are improved, the retrieval efficiency is improved when the key frame is searched, the recall rate is relatively high for a mismatching condition, and the probability of missed detection is reduced.

The invention relates to the technical field of automatic quality inspection of textiles, in particular to a flexible textile quality inspection system and device based on deep learning. The quality inspection system provided by the invention comprises a detection module which collects data and applies the data to machine training and machine quality inspection, a reasoning module which is in communication connection with the detection module and performs reasoning judgment by using the data collected by the detection module and determines a defect type, and a verification module which manually samples and rechecks a reasoning judgment result of the reasoning module, and the learning module feeds back a manual sampling rechecking result of the checking module to the reasoning module for optimization training learning. The multi-modal sensing and deep learning reasoning module is utilized to realize efficient automatic identification of multiple types of defects on the surface and in the fabric, the detection precision is improved, the missing detection rate and the false detection rate are remarkably reduced, and dynamic optimization of the model is realized through man-machine collaborative sampling inspection of the verification module and in combination with feedback correction and a continuous self-learning mechanism of the learning module. And the system detection capability is continuously improved along with use.

The invention relates to a circuit board defect identification method and system based on multi-dimensional image data, and belongs to the technical field of data identification processing, and the method comprises the following steps: obtaining synchronous image data of a circuit board to be detected in a plurality of imaging modes; performing space-spectrum joint registration on each modal image to generate a multi-dimensional image cube with a unified coordinate system and pixel alignment; inputting the multi-dimensional image cube into a pre-trained multi-branch heterogeneous fusion neural network; generating a pixel-level defect probability graph by utilizing a defect sensing context decoder, and performing geometric constraint optimization on the probability graph by combining prior information of a circuit board design layout; outputting defect types, positions and confidence coefficients, and establishing an interpretable defect fingerprint database according to the multi-dimensional response characteristics of the defects; the method has the beneficial effects that false defect signals generated by image noise and circuit board surface texture interference can be effectively inhibited, the omission ratio and the false detection ratio are greatly reduced, and pixel-level accurate defect positioning is realized.

An information processing apparatus causes a quantum computer to perform a first gate operation in accordance with an ancilla state generation circuit representing a procedure of generating a code including a logical qubit representing an ancilla state and a gauge qubit representing a redundant degree of freedom other than the ancilla state. Next, the information processing apparatus causes the quantum computer to perform a second gate operation in accordance with an error detection circuit representing a procedure of detecting an error occurring in a plurality of physical qubits constituting the code generated by the first gate operation. Then, the information processing apparatus determines the presence or absence of the error on the basis of a measurement value obtained by the second gate operation, the measurement value indicating the state of the gauge qubit.

The invention discloses a bridge disease detection method based on a diffusion model and a bitter fish optimization algorithm, and relates to the technical field of bridge detection. The method comprises the following steps: fixing a visual angle and a distance at an easy-to-peel or crack position of a bridge, and collecting and aligning visible light and near-infrared images; carrying out multi-scale downsampling on the image, and carrying out wavelet denoising, brightness correction and texture smoothing; inputting the preprocessing result into an improved diffusion model, weighting the edge during forward diffusion, and reversely generating and applying texture and contour smoothing; the multi-source feature channel and the reconstructed image are combined and input into a deep segmentation network, shadow and stain are eliminated by using a local difference function, and global search is performed on a segmentation threshold, a noise coefficient and the like based on a disease detection rate, a false detection rate and the like by using a bitter fish algorithm; training and correcting the high-noise area again according to the optimal parameters; and uniformly marking disease areas. According to the method, the recognition recall rate of tiny spalling and irregular cracks in an extreme environment can be greatly improved, and the intelligent level and the practical effect of bridge disease detection are improved.

The invention discloses a document proofreading system and method based on artificial intelligence, and relates to the technical field of natural language processing, and the method comprises the steps: analyzing a document, dividing semantic units, and obtaining a document with a context label based on context type library labeling; performing initial error detection by using the corresponding rule set, and comparing the format of the document and the text quality characteristics with a standard sample vector space to obtain an initial error set; constructing a defect conduction chain network, and locating root cause error nodes causing a plurality of secondary errors by tracing the defect conduction chain network; generating an intelligent proofreading report; receiving a new-version document revised by the user, comparing the new-version document with the original-version document, positioning a change area, and analyzing a quality difference of the change area on a related quality dimension; based on the quality difference, an incremental proofreading report is output, and the incremental proofreading report comprises newly introduced errors and unsolved root cause errors.

According to the voice transliteration text error correction method and device, the storage medium and the computer equipment, after the voice transliteration text is received in real time, the text is subjected to primary error detection, and the first error confidence coefficient is obtained; when the first error confidence coefficient is smaller than a fast error correction threshold value, the voice transcription text is directly output, and unnecessary error correction is avoided; otherwise, performing word-level rapid error correction on the voice transcription text to obtain a rapid error correction text, and performing secondary error detection on the rapid error correction text to obtain a second error confidence coefficient. Judging whether the second error confidence is smaller than a depth error correction threshold value or not; if yes, the rapid error correction text is directly output, and if not, semantic-level deep error correction is conducted on the rapid error correction text through a deep error correction model, and a deep error correction text is obtained and then output. Through a hierarchical error correction processing strategy, the method can be adapted to different service scenes, and meanwhile, dynamic balance between quality and efficiency of different service scenes can be realized by adjusting two error correction thresholds.

The invention relates to the technical field of image recognition, and discloses a glass fiber board production quality detection method and system, and the method comprises the steps: collecting a continuous infrared thermal image sequence through an infrared thermal imaging device; constructing a temperature difference image set; identifying a primitive region with an abnormal diffusion characteristic; further performing fitting enhancement and significance detection on the abnormal primitive region; and performing defect classification and quality judgment based on the regional feature vector. Compared with the prior art, the technical problems that in the prior art, high-precision parting judgment cannot be achieved under the conditions that the surface texture of a glass fiber board is complex, hot-pressing disturbance exists, particularly, hot diffusion behaviors of dry filaments, degumming and cavitation bubble defects are similar, and the false detection rate of a conventional algorithm is high are solved. Due to the fact that a multi-channel thermal diffusion consistency analysis mechanism and parallel discrimination logic based on feature vectors are introduced, infrared primitive anomaly enhancement detection and defect classification recognition under the complex background are achieved, and the accuracy of glass fiber board production quality detection is improved.

The invention relates to a sensor data anomaly detection method and a storage medium, and the method comprises the steps: obtaining the target time sequence data of a target sensor, and obtaining the adjacent time sequence data of an adjacent sensor; the spatial distance between the adjacent sensor and the target sensor is within a preset distance range; calculating a reference confidence interval according to the target time sequence data and the adjacent time sequence data; inputting the target time sequence data into the trained time sequence prediction model for multiple times of forward propagation, and outputting a plurality of reconstruction results; calculating a model uncertainty sequence by using the plurality of reconstruction results; adjusting the reference confidence interval based on the model uncertainty sequence to obtain a dynamic confidence interval; and detecting whether the target time sequence data falls outside the dynamic confidence interval, and generating a first anomaly detection result. According to the method and the device, the problem that detection of different types of anomalies has relatively high omission ratio and false detection rate is solved.

The invention relates to the technical field of semiconductor detection, and discloses a method and a system for detecting chips on the surface of a semiconductor wafer. The method comprises the following steps: acquiring a high-resolution image of the surface of a wafer, and separating a defect candidate region set from a reference background region through noise filtering and contrast equalization processing; extracting defect areas to be identified one by one, and accessing the defect knowledge graph to obtain potential defect types; performing multi-feature fusion on the potential defect type and the reference background region, generating a defect semantic feature vector through a context sensing encoder, and analyzing the vector to judge the actual defect type; and processing all the candidate areas and then outputting a defect detection report. According to the method, the distinction degree of defects and backgrounds is enhanced, the defect judgment range is narrowed, similar defects are accurately recognized, missing detection and false detection are reduced, the detection efficiency and accuracy are improved, and reliable technical support is provided for wafer production quality control.

The invention discloses a remote sensing burned area semantic segmentation method based on multi-scale fusion and an attention mechanism, a terminal and a storage medium, and belongs to the technical field of remote sensing image semantic segmentation, and the method comprises the steps: obtaining a target remote sensing image, coding the target remote sensing image, and obtaining a multi-scale feature map; extracting local features of the multi-scale feature map to obtain a local multi-scale feature map; extracting global features of the multi-scale feature map to obtain a global multi-scale feature map; performing gating weighted fusion on the local multi-scale feature map and the global multi-scale feature map to obtain a target fusion feature; enhancing the target fusion feature to obtain a target enhanced feature map; and segmenting the target remote sensing image based on the target enhanced feature map to obtain a target segmented image. According to the method, the problems of fuzzy boundaries, complex backgrounds and various scales can be better solved, the contour of a segmentation result is more fit with an actual target area, and the missing detection rate and the false detection rate are remarkably reduced.

The invention discloses a cable sheath microcrack image identification method based on deep learning. The method comprises the following steps: acquiring a cable sheath image and executing image preprocessing operation; inputting to an improved MAE model, and generating a background reconstruction image and a crack reconstruction image; pixel-level residual fusion is carried out to generate a background shielding image; performing pixel-level fusion on the background shielding image and the preprocessed image to generate a background suppression image; micro-crack recognition operation is executed, and a preliminary crack response heat map set is output through image feature extraction and crack region judgment; executing a heat map accumulative analysis operation, and constructing a multi-scale accumulative heat map; judging a pseudo response risk area according to the local response change rate; response value retraction operation is executed based on the corresponding local area, and a crack heat map after pseudo response suppression is generated; and extracting a high-confidence crack region to obtain a cable sheath microcrack identification result. According to the invention, the precision and robustness of microcrack detection are improved, and the background interference and false detection risk are reduced.

The invention discloses a building detection data processing method for building engineering, which relates to the technical field of data processing, and is characterized in that an acquired to-be-detected abnormal building image is preprocessed through binarization operation and a non-abnormal feature removal algorithm to obtain an abnormal building image, so that the interference of complicated backgrounds such as shadows and seams is effectively inhibited. The method comprises the following steps: optimizing an Inception-ResNet convolutional neural network by using structure adaptive offset and cross connection operation, and performing feature extraction on an abnormal building image by using the optimized Inception-ResNet convolutional neural network to generate a multi-scale feature map; and carrying out segmentation processing on the multi-scale feature map through a feature pyramid network, and outputting a building image analysis result. According to the method, the precision and robustness of crack detection are improved through a multi-scale feature fusion mechanism, the continuity and integrity of a crack structure are guaranteed, crack forms with different thicknesses can be detected at the same time, and the false detection rate and the omission ratio are reduced.