264 results about "Background suppression" patented technology

The invention relates to the technical field of printed circuit board design, in particular to a printed circuit board defect detection method and system based on image recognition. The method comprises the following steps: carrying out image preprocessing on an original PCB image to obtain a preprocessed PCB image; performing scale feature fusion on the preprocessed PCB image to obtain a multi-scale feature map; performing background texture feature learning on the multi-scale feature map to obtain a background suppression feature map; performing background texture suppression according to the background suppression feature map to obtain a significant defect map; and performing local statistical feature calculation according to the pre-processed PCB image and the saliency defect graph to obtain a local statistical feature graph. Through a series of technical means of multi-scale feature fusion, background texture feature learning and suppression, adaptive threshold segmentation and morphological optimization, the problem of complex background texture interference is effectively solved, and the accuracy and robustness of PCB defect detection are improved.

The invention relates to the field of plastic waste detection, in particular to a plastic waste detection method, device and equipment and a storage medium. The method comprises the following steps: acquiring a multi-angle image of a to-be-detected area; performing multi-scale detail reconstruction on the multi-angle image of the region to be detected, and performing region background feature interference suppression so as to construct a background suppression optimization image; performing in-region target visual detection on the background suppression optimization image, and performing object material component mining so as to generate a material component feature of each object; deep semantic segmentation is carried out based on the material component features of each object, image impurity removal processing is carried out, and a non-plastic impurity removal optimized image is constructed; and performing plastic waste visual inspection on the non-plastic impurity removal optimized image, and performing bounding box instance division processing so as to extract a bounding box image of each plastic waste. According to the invention, efficient and accurate plastic waste detection and identification are realized.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as agent autonomous decision making, financial science and technology and medical health, and discloses a task processing method and device based on visual attention enhancement, equipment and a medium. Visual hierarchical features are extracted, a double fovea attention module processes and fuses high-level visual features, a side suppression network obtains enhanced visual features, and a cross-modal fusion module generates fusion features by taking the enhanced visual features as query vectors and taking language components and action components as key and value vectors; and fusing the feature input decision network to generate target category and position information, generating feedback information based on actual label difference, and updating module parameters to complete a target task. According to the invention, through combination of a bionic vision mechanism and multi-modal attention fusion, the visual feature extraction and background suppression capability is improved, and the target capture efficiency and recognition precision in a complex scene can be improved.

The invention provides a door and window glass defect feedback control method and device, electronic equipment and a storage medium, and relates to the technical field of door and window glass defect detection. The method comprises the steps of collecting a first image after a polarized light imaging detection device is adjusted to suppress reflected light on the surface of glass and enhance scattered light of bubbles in the glass; after the polarized light imaging detection device is adjusted to enhance reflected light on the glass surface, a second image is collected; calculating an adaptive weight group by analyzing local characteristics of the second image; weighting the first image according to the self-adaptive weight group, and subtracting the weighted first image from the second image to obtain a difference image; and extracting bubble defect information in the glass by analyzing the differential image. According to the method, interference caused by non-uniformity of glass surface reflection is overcome, the adaptability of image differential processing to surface reflection background suppression is improved, and therefore image features of internal bubble defects are extracted more effectively and more accurately.

The invention belongs to the technical field of image processing, and discloses an infrared polarization noise suppression and edge enhancement method based on gradient vector analysis, which comprises the following steps of: according to spatial distribution similarity in a polarized image, performing preliminary highlight noise suppression on a polarization degree image based on a double-offset spatial neighborhood gradient weighting method; bidirectional feature coherence suppression is provided by using the difference of polarization characteristics of a small target in a sky background to obtain a significant target; the problem of excessive suppression of target edge information in the background suppression process is prevented, and target edge information enhancement is performed based on a gradient vector field connectivity statistical analysis method. According to the infrared polarization noise suppression and edge enhancement method based on gradient vector analysis, background highlight point noise of a polarization degree image is preliminarily suppressed based on a double-offset space neighborhood gradient weighting method; a saliency target is effectively obtained based on bidirectional feature coherence suppression; the shape information of the target is enhanced based on a gradient vector field connectivity statistical analysis method.

The invention provides a segmentation-detection cascade photovoltaic hot spot detection method and system, and particularly relates to the technical field of photovoltaic equipment fault detection in the field of computer vision, and the method comprises the steps: segmenting an input infrared image through a photovoltaic panel region segmentation network, generating a photovoltaic panel region mask image, and multiplying the photovoltaic panel region mask image with an original image pixel level, thereby obtaining a detection result; and obtaining a target area image after background suppression. Thirdly, extracting a multi-scale feature map of the target area by utilizing a detection network comprising a deformable convolution module, and then performing weight distribution and fusion on the multi-scale feature map by adopting a self-adaptive spatial feature fusion strategy to generate an optimized feature map; and finally, outputting a hot spot position and category detection result based on the optimized feature map. According to the method, complex background interference is effectively inhibited, the multi-scale hot spot detection precision is improved, the false detection rate is reduced, and the real-time inspection requirement of the photovoltaic power station is met.

The invention relates to a multi-scale twin hyperspectral target detection method and system, and belongs to the technical field of deep learning. The method comprises the following steps: S1, preparing initial target and background data of a hyperspectral image; s2, performing adversarial sample generation on the hyperspectral remote sensing image to obtain training sample data; s3, inputting the generated sample into a multi-scale twin target detection network for training; and S4, after training is completed, performing target detection on the test sample to obtain a result. The performance of the method is superior to that of other hyperspectral image target detection methods, the method can generate more sufficient and more diversified training samples, and the method has advantages in the aspect of background suppression compared with other methods.

The invention relates to a hybrid efficient feature network method for real-time target detection of an unmanned aerial vehicle, and provides a real-time target detection framework oriented to resource-constrained platforms such as the unmanned aerial vehicle. Through collaborative optimization of four core components including a lightweight backbone network, a parallel scale internal feature interaction module, a cross-scale repeated selection connection module and a selective mixed query decoder, efficient capture and background suppression of a multi-scale target in a resource limited scene are realized, and model reasoning speed and detection precision are effectively considered; the method provided by the invention has high efficiency and robustness in real-time target detection, provides an innovative design thought and practical reference for embedded visual perception tasks of unmanned aerial vehicles and the like, and has important application value.

The invention discloses a camouflage target detection method and device based on feature enhancement, and a readable medium, and the method comprises the steps: obtaining a to-be-detected camouflage target image, inputting the to-be-detected camouflage target image into a trained camouflage target detection model, obtaining multi-scale features through a multi-scale feature extraction module in an encoder, and carrying out the detection of the camouflage target image; wherein the second-level feature, the third-level feature and the fourth-level feature respectively pass through three feature enhancement modules and a context aggregation module to obtain a second aggregation feature, a third aggregation feature and a fourth aggregation feature; performing up-sampling on the second aggregation feature, performing element-by-element addition on the second aggregation feature and the first-level feature to obtain a first addition result, and processing the first addition result through a first convolution module to obtain a first mask; the first mask, the second aggregation feature, the third aggregation feature and the fourth aggregation feature are input into a feature decoupling module to obtain a second background suppression feature; and obtaining a corresponding prediction detection result based on the second background suppression feature, and solving the problem of high similarity of the foreground and the background.

The utility model discloses a background suppression photoelectric sensor realized based on double PD. The background suppression photoelectric sensor comprises an MCU control circuit, an LED drive circuit, an acquisition module, a target object, a differential amplification circuit, a voltage comparison circuit and a self-adaptive output circuit. The acquisition module is used for receiving reflected light signals of a target object and converting the reflected light signals, then the differential amplification circuit amplifies and converts PD signals received by the acquired signals, and then analog quantity signals are converted into pulse signals through the voltage comparison circuit, so that the MCU control circuit can be used for processing logic signals and modulating PWM signals. The LED driving circuit is arranged to drive the LED diode D6 to work; the background suppression photoelectric sensor realized by a photodiode PD1, a photodiode PD2, a differential amplification circuit, a voltage comparison circuit and an MCU control circuit adopts an automatic frequency conversion technology to solve the problem of optical crosstalk among multiple sensors, and is suitable for background suppression photoelectric sensing.

The invention discloses a remote sensing small target detection network and method based on frequency domain and space domain adaptive enhancement, and belongs to the technical field of artificial intelligence. The network is based on an FCOS lightweight detection framework, through cooperative extraction, adaptive enhancement and fusion of spatial domain and frequency domain features, the parameter quantity and the calculation complexity are greatly reduced, the small target detection precision and efficiency are significantly improved, and finally the balance of lightweight deployment and high-precision detection is realized. According to the invention, through the space-frequency feature adaptive enhancement network, space context modeling and frequency detail recovery can be completed in a single-stage detection framework at the same time, and an adaptive enhancement unit is introduced to dynamically adjust the enhancement strength according to the local signal-to-noise ratio, so that significant improvement and background suppression of a tiny target signal are realized.

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 method for estimating the area of an irregular-shaped fire scene using an optoelectronic pod in the present invention belongs to the technical fields of navigation control algorithms and infrared image processing, and includes: S101: Preprocessing and background suppression are performed on the infrared thermal image, and the fire scene area in the image is identified according to the gray value of the image and the set temperature threshold; S102: Determine the slant range information of the fire scene area aligned with the optical axis of the pod; S103: Place the infrared thermal image in a rectangular coordinate system with the alignment point of the pod optical axis as the origin, and the fire scene area forms an irregular area in the rectangular coordinate system; S104: Calculate the area projected onto the actual ground for each pixel in the fire scene area according to the optical axis attitude, geographical location information, and slant range information, and add up the projected areas of each pixel to obtain the fire scene area on the actual ground. It can greatly improve the efficiency of forest fire prevention emergency rescue and the accuracy and real-time nature of fire situation reports, thereby achieving rapid analysis of forest fire situations and providing strong information support for forest fire fighting and emergency command.

The invention relates to the field of computer vision, artificial intelligence and intelligent fitness, and particularly discloses a fitness action recognition, counting and quality evaluation method based on machine vision, which comprises the following steps of: extracting video frames and standardizing the video frames, realizing background suppression and human body region enhancement through a semantic segmentation or inter-frame difference method, and outputting a standardized image sequence; detecting key joint points by adopting a pre-training model, and outputting a stable skeleton sequence and candidate action stage data through time sequence consistency filtering; reconstructing a feature tensor, fusing spatio-temporal features through double-branch attention collaboration, and outputting action categories and time sequence compensation parameters in a classified manner; a dynamic threshold method accumulates the number of actions, action qualification is judged in combination with biomechanical constraints, the confidence coefficient is optimized, and a structured result is output; bone rendering, error highlighting, voice generation and personalized training suggestions. According to the method, wearable equipment is not needed, the problems of instable identification, miscounting and the like in a complex scene are solved, and real-time accurate analysis is realized.

The invention discloses a gas leakage detection imaging device and method based on a single photon detection technology, and belongs to the technical field of gas detection and imaging. Aiming at the limitation problems of the existing gas leakage detection technology in the aspects of sensitivity, response speed, space imaging capability and anti-interference capability, nanosecond modulation control and synchronous photon counting are realized by utilizing an FPGA (Field Programmable Gate Array) through a visual gas detection imaging device combining an SPAD (Single Program Amplifier) array detector and a WMS modulation-demodulation mechanism; and the second harmonic of the absorption signal is further extracted by combining digital phase-locked amplification, so that gas leakage three-dimensional imaging with high spatial resolution, ppb-level sensitivity, strong background suppression capability and high time response is realized. The system has the advantages of high detection sensitivity, real-time imaging capability with high spatial resolution, high background light interference resistance and high signal-to-noise ratio, the demodulation method is novel, and the modular design has multi-gas compatibility and system expansibility.

The invention relates to the technical field of air-ground target tracking, in particular to an air-ground target tracking performance evaluation method based on visual saliency. Comprising the following steps: calculating a center positioning error between a target labeling frame and a prediction frame center point; calculating an adaptive center positioning error threshold based on the width and height of the target labeling box; calculating a precision index by using the threshold value; obtaining a saliency map of the target annotation box through a Bayesian framework, and calculating the weight of the target annotation box in combination with pixel saliency; the overlapping ratio under background suppression is calculated based on the overlapping region by using the significance weight, and pixel weight distribution of a real positive example, a false negative example and a false positive example is comprehensively considered in the overlapping ratio; and finally, drawing a success rate curve by setting different overlapping rate thresholds, and calculating an area under the curve as a model performance evaluation index. According to the method, the visual saliency and the adaptive threshold are combined, so that the accuracy and reliability of target tracking performance evaluation are effectively improved.

The invention relates to a self-supervised meta transfer learning hyperspectral target detection method and system, and belongs to the technical field of deep learning. The method comprises the following steps: S1, preparing data of an initial source domain and a target domain of a hyperspectral image; s2, carrying out self-supervision pre-training on the GLSL network by utilizing the source data; s3, migrating the GLSL to a target detection data set to carry out spectrum similarity detection; and S4, performing learning constraint by using a spatial constraint module to obtain a target detection result. The performance of the method is superior to that of other hyperspectral image target detection methods, the method can be effectively migrated to different target detection tasks, and the method has advantages in the aspect of background suppression compared with other methods.

The invention provides a satellite video target tracking method and device based on fine positioning, equipment and a medium, and the method comprises the steps: obtaining a satellite video image, and extracting feature images of a template region and a search region in the satellite video image through a pre-trained target tracking model; background suppression is carried out on the feature images of the template area and the search area through a target tracking model, and a template feature map and a search feature map after background suppression are obtained; performing matching operation between the template feature map and the search feature map to obtain a response map; and based on the response diagram, positioning a target in the satellite video image by using an enhanced head network in the target tracking model.

The invention discloses an AI real-time small target detection method based on attention, and relates to the technical field of computer vision and deep learning. The AI real-time small target detection method based on attention comprises a small target feature enhancement layer, a dynamic background suppression layer, a lightweight detection optimization layer and an edge deployment adaptation layer. The small target feature enhancement layer is used for enhancing small target features and making up feature loss, and the dynamic background suppression layer is used for accurately filtering background interference. According to the AI real-time small target detection method based on attention, through a feature enhancement layer and loss optimization, on a VisDrone2022 data set, small target detection mAP (at) 0.5 reaches 72.3%, the mAP (at) is improved by 18.2% compared with a YOLOv5 basic version (54.1%), and the mAP (at) is improved by 25.5% compared with a Faster R-CNN (46.8%); the detection mAP of the ultra-small target (the pixel proportion is less than 2%) reaches 65.7%, and the index of the traditional algorithm is generally lower than 40%.

The invention discloses an aerial target detection method based on dynamic attention and double-frequency feature enhancement. The method comprises the following steps: 1) extracting multi-scale features by using a backbone network in combination with a low-light feature fusion module, and enhancing detail expression in a low-light and low-contrast scene; 2) sparse modeling is carried out on deep features through a dynamic sparse attention module, key attention connection is reserved, and the global semantic ability is improved while the calculation amount is reduced; 3) inputting the deep enhanced features and the shallow features into a double-frequency feature enhancement module, and respectively modeling low-frequency background and high-frequency details to realize foreground highlighting and background suppression; according to the unmanned aerial vehicle aerial image target detection method, the problems of low illumination, complex background and small target detection are effectively solved, and the precision and robustness of unmanned aerial vehicle aerial image target detection are remarkably improved.

The invention provides a target detection method and system based on computer vision, and the method comprises the steps: carrying out the preprocessing of a to-be-detected target image, so as to obtain a preprocessed image; performing detail enhancement and environment compensation on the preprocessed image to obtain an enhanced image; performing clustering segmentation on the enhanced image to obtain an environment image and a foreground image, performing first correction processing on the environment image, performing second correction processing on the foreground image to obtain a first corrected image and a second corrected image, and combining the first corrected image and the second corrected image to obtain a final corrected image; performing denoising and background suppression on the final corrected image to obtain a denoised image; according to the target detection method and device, the template training image is obtained, the preset detection model is trained through the template training image, the de-noised image is input into the trained preset detection model for target detection, and the target detection result is output, the accuracy of target detection can be improved, and the situation of misrecognition is avoided.

The invention provides a robot grabbing detection method and device for various backgrounds, and relates to the technical field of robot intelligent control. The method comprises the following steps: acquiring a grabbed data set; preprocessing the grabbed data set to obtain a preprocessed grabbed data set; constructing a self-adaptive multi-background suppression grabbing network; according to the preprocessed capture data set, training an adaptive multi-background suppression capture network to obtain a trained adaptive multi-background suppression capture network; rGB-D image data of an object to be grabbed are obtained; rGB-D image data of an object to be grabbed are input into the trained self-adaptive multi-background suppression grabbing network, and a grabbing quality graph, a grabbing angle graph and a grabbing width graph are obtained; according to the grabbing quality graph, the grabbing angle graph and the grabbing width graph, grabbing pose data are estimated; and motion planning is carried out according to the grabbing pose data, so that the robot executes a grabbing task. According to the invention, the real-time performance and the accuracy of the grabbing operation of the robot system can be improved.

The invention provides an unmanned aerial vehicle remote sensing monitoring and evaluating method and system for field orchard diseases and insect pests, and relates to the technical field of orchard disease and insect pest monitoring and evaluating. The interference of complex background noise is effectively eliminated by constructing a ternary separation index integrating feature enhancement, background suppression and brightness normalization; a threshold value is determined based on the exponential distribution, pixels are accurately divided into a non-canopy background, a shadow canopy and an illumination canopy, and fine segmentation of an unstructured scene is achieved; constructing a gain compensation item by using a local illumination reference mean value, correcting a shadow canopy reflectivity curve, and eliminating illumination non-uniform interference; selecting a local high quantile to establish a health reference basis, coupling a discriminant item and an attenuation item, and resolving to obtain a physiological stress index, so as to realize acute capture of early weak disease characteristics; and performing power weighted accumulation on the abnormal pixel difference value, outputting a regional hazard level index, and objectively quantifying the overall disaster risk of the region through nonlinear aggregation.

The invention provides an infrared small target detection method fusing multi-scale features and background suppression, and belongs to the technical field of infrared imaging. An improved encoder-decoder network structure is adopted, and the structure comprises three main parts, namely an encoder, a connecting assembly and a decoder. The encoder is responsible for extracting multi-level feature representation from an input infrared image, the connecting component is responsible for transmitting and fusing features among different levels, and the decoder is responsible for combining high-level semantic information with bottom-level detail information to finally generate a target segmentation result. According to the method, the detection precision is remarkably improved, and the omission ratio is effectively reduced; the background suppression capability is effectively enhanced, and the false detection rate is remarkably reduced; better multi-scale feature fusion is realized, and the characterization capability of the target is further improved; the robustness of the detection system is improved on the whole, and the method can adapt to complex and changeable practical application scenes.

The invention relates to an anomaly detection technology, and discloses an anomaly detection method and system for a flexible circuit board patch, and the method comprises the steps: obtaining a patch image in a preset flexible circuit board, carrying out the illumination normalization processing and background suppression processing of the patch image, and obtaining a background suppression patch image, and carrying out abnormal bending identification on the background suppression patch image based on multi-scale gradient fusion and local structure consistency analysis, judging whether the patch in the flexible circuit board has abnormal bending according to a bending identification result, if yes, judging that an abnormal detection result is abnormal bending, and if not, judging that the patch in the flexible circuit board has abnormal bending. And otherwise, calculating an offset coefficient of the normalized patch image based on double-flow alignment and differential significance enhancement, judging whether the offset coefficient is greater than a preset coefficient threshold, if so, judging that the abnormal detection result is abnormal offset, and if not, judging that the abnormal detection result is abnormal. According to the invention, the communication circuit board patch abnormity detection precision can be improved.

The invention belongs to the technical field of spaceflight on-orbit services, and particularly relates to a complex environment target recognition approaching method based on dual-band imaging under a satellite platform, which is based on three common sensors, namely an infrared camera, a visible light camera and a laser range finder, and is characterized in that an image information source adopts infrared and visible light multi-spectrum fusion; software time synchronization and an image registration mode are introduced into a synchronization mode, infrared fast mean value judgment suitable for on-satellite embedding is introduced, an earth background suppression technology and a target information enhancement scheme are added, fusion tracking and ranging cooperation of vision and a laser range finder is adopted, and meanwhile, a laser range finder start-stop strategy is designed according to on-satellite power consumption. According to the invention, the defect of insufficient robustness of a single sensor facing an earth complex background observation target in the view field change process of a satellite platform is overcome.

The invention relates to a high-real-time daytime stray light star map star point extraction method, which comprises the following steps of: firstly, carrying out stray light background suppression on a star map by adopting an improved soft morphological filtering algorithm; and removing residual single-point noise from the image subjected to stray light suppression by adopting a morphological opening operation. Secondly, bright pixels are extracted from the filtered star map, four-connected-domain judgment is carried out through a clustering method, the connected domains are ranked from high to low according to the total energy, and four stars with the highest energy are selected to carry out triangle recognition matching based on a bright star table; thirdly, postures are calculated based on the successfully matched star points, and the star points in the view field are back-projected to an original star image surface in combination with a complete star catalogue; and finally, windowing an original star map according to the calculated star point image plane coordinates, performing stray light suppression on a window image by adopting an edge pixel fitting method, and completing star point extraction by adopting adaptive threshold segmentation and a four-connected-domain judgment algorithm.

The invention belongs to laser stripe image data processing, and particularly relates to a multi-scale gradient gravity center laser center line extraction method and system, and the method comprises the steps: S1, carrying out the feature extraction and enhancement of a laser stripe image, intensifying detail branches through a space channel weight map, obtaining a bounding box positioning result based on depth separable convolution and residual connection, and obtaining a bounding box positioning result; s2, acquiring a prediction center for each column by adopting a prediction method, and searching a gray peak value in a normal adaptive window to realize coarse positioning; the method comprises the following steps: S1, building a local coordinate system and an elliptical window along the coarse center line, and constructing a multi-scale Gaussian pyramid to carry out background suppression and image enhancement, S4, generating a weighted graph through cross-scale fusion, calculating a weighted gray gravity center in each window, and carrying out image enhancement on the weighted graph. And after smoothing, a high-precision laser stripe center line is output. And the accuracy and robustness of extracting the laser center line are improved.

According to the multi-frame reverberation suppression method based on combination of the alternating direction multiplier method and the low-complexity high-order nonlinear cumulant, underwater reverberation in inter-frame low-rank slow-change components in reverberation is suppressed through the alternating direction multiplier method; water surface reverberation, volume reverberation and noise in inter-frame sparse fast-change components are suppressed by using low-complexity high-order nonlinear cumulants, and continuous moving target bright spots are enhanced, so that an angle-distance sonar two-dimensional image with lower reverberation intensity and clear continuous target bright spots is obtained. Compared with the reverberation suppression performance of an existing low-complexity high-order nonlinear cumulant and multi-frame accumulation after processing of an existing robust principal component analysis method, the multi-frame reverberation suppression method combining the alternative direction multiplier method and the low-complexity high-order nonlinear cumulant has a better reverberation background suppression effect.

The invention relates to the technical field of surface defect detection, in particular to a PE film surface electrostatic dust recognition system and method.The method comprises the steps that an image collection module collects multi-angle and multi-wavelength images of the surface of a PE film through an annular LED array and a multi-wavelength illumination system; the multi-manifold mapping background suppression module regards the surface of the PE film as a composite manifold and separates background and dust characteristics; the differential geometric feature extraction module extracts geometric features such as curvature and shape indexes, calculates a geodesic distance matrix and generates a noisy point-tiny dust probability graph; the topological feature segmentation module executes edge detection, morphological processing and topology preserving clustering, classifies image areas and determines the position of the tiny dust, and the method combines multi-manifold mapping and differential geometric features, so that the detection difficulty caused by the high-reflective surface of the PE film is effectively overcome, and the tiny dust of the level of 0.5-10 microns can be accurately identified.