318 results about "Image segmentation algorithm" patented technology

The invention provides an electromagnetic interference suppression method and system for a chip, and relates to the technical field of intelligent chips, and the method comprises the steps: obtaining layout data of a target chip, and based on the layout data, extracting structure parameters and device parameters through an image segmentation algorithm, and constructing a multi-physics field coupling simulation model; the method comprises the following steps: determining an optimal excitation source corresponding to a target chip through a machine learning algorithm, calculating to obtain transient multi-physical field distribution by adopting a time domain finite element method and through an adaptive time step control strategy, extracting time-frequency domain multi-scale distribution characteristics, and constructing a spectrum fingerprint database of electromagnetic interference by utilizing a deep convolutional neural network. Generating an electromagnetic interference identification result; and based on an electromagnetic interference identification result, determining an optimal suppression circuit topology through a suppression topology search algorithm, determining optimal suppression device parameters through a multi-objective optimization algorithm in combination with electromagnetic compatibility index constraints, and generating an electromagnetic interference suppression strategy.

The invention provides a textile defect positioning method, which comprises the following steps: according to an extracted defect feature map, fusing feature maps of different scales, extracting multi-scale defect features, and comprehensively depicting space distribution and combination information of defects; aiming at the condition that multiple flaws exist at the same time, a multi-task learning model is constructed, flaw detection, classification and positioning tasks are carried out at the same time, and a back propagation algorithm is adopted to optimize the multi-task learning model; positioning the defect area by adopting an image segmentation algorithm, obtaining the contour of the defect area according to the positioning result of the defect area and by adopting a Canny edge detection algorithm, and calculating the area and position information of the defect; and based on an evaluation result, a dynamic threshold adjustment algorithm is adopted, a defect judgment threshold is adjusted according to a production batch and a product type, and a threshold parameter is dynamically updated by analyzing historical data and a current production condition.

The invention provides a division method and system for a forest pest control area, and relates to the technical field of data processing, and the method comprises the steps: building a forest pest control database through collecting pest data and environment data of a control area; and training a pest risk prediction model based on historical data to generate a risk distribution map. And then, in combination with a GIS technology and a deep learning image segmentation algorithm, intelligent division is performed on the target area, and it is ensured that the unmanned aerial vehicle efficiently covers the prevention and control unit. According to the method, the optimal spraying route can be planned by adopting a path optimization algorithm based on the flight capability of the unmanned aerial vehicle, the pesticide carrying capacity and the environmental conditions, spraying parameters are dynamically adjusted by monitoring the wind speed, obstacle information and the like in real time, precise pesticide application is ensured, the pest control efficiency can be improved, repeated spraying and spraying blind areas are reduced, the pesticide use amount is reduced, and the pesticide application cost is reduced. Intelligent and precise forest pest control is achieved, and the method is suitable for large-scale unmanned aerial vehicle autonomous operation scenes.

The invention discloses an efficient 3D Gaussian scene reconstruction method based on multi-modal depth distribution supervision, and compared with the prior art, pixel-level depth dense point clouds are directly extracted in a Gaussian initialization stage, a multi-modal depth distribution map is generated, random initialization of dense Gaussian positions according to COLMAP sparse point clouds is effectively avoided, and the reconstruction efficiency is improved. The problems that under the condition of few views, point clouds obtained by COLMAP are too sparse, provided geometric constraints are insufficient, and meanwhile randomly initialized Gaussian blocks the point clouds to move to the correct position due to the local minimum value are solved. According to the method, an image segmentation algorithm based on edge detection is applied to the image frame, a large number of Gaussian primitives which are far away from edge points and are similar in depth are fused, the 3D Gaussian number is effectively pruned, and memory consumption of a GPU is saved. According to the method, extra isotropic regularization loss is introduced into global gauss, so that the problem of Gaussian distribution in which artifacts are generated along the line-of-sight direction and the height is lengthened is avoided.

The invention belongs to the field of disaster early warning, and provides a disaster early warning method and system based on key target detection and image segmentation, and the method comprises the steps: obtaining the real-time image data of a site, and carrying out the preprocessing of an image; processing the preprocessed image through a YOLOv5 target detection algorithm, detecting a key target in a disaster site, and outputting a category label and a bounding box of the target; performing pixel-by-pixel segmentation processing on a bounding box region output by target detection by using a U-Net image segmentation algorithm to generate an accurate segmentation mask of the target; and inputting the image segmentation mask, historical disaster data, meteorological data and geographic information system data into an LSTM prediction model, carrying out multi-source data fusion and time sequence analysis, and outputting dynamic prediction information and early warning levels of disasters. According to the invention, real-time monitoring and early warning of disasters are realized, the response speed of the early warning system is obviously improved, more comprehensive disaster early warning information is provided, high precision of disaster prediction is ensured, and the phenomena of false alarm and missing alarm are reduced.

The invention discloses a power transmission image defect detection and defect duplicate removal method and system based on a deep learning image segmentation algorithm, and belongs to the technical field of intelligent inspection of power equipment. According to the method, real-time tower identification and adaptive shooting are realized through a lightweight YOLO model deployed at the edge end of an unmanned aerial vehicle; pixel-level segmentation is carried out on the infrared image by using an MSAN-Net network, the network integrates a ResNet encoder, a cross-scale attention mechanism and a multi-level feature pyramid, and boundary learning is enhanced by using a composite loss function; based on a multi-view three-dimensional reconstruction technology, two-dimensional defects are mapped into space rays through feature point matching and pose estimation, and defect de-weighting is achieved through ray intersection judgment. Through the MSAN-Net network, the segmentation precision of the infrared component under a complex background is remarkably improved through an attention mechanism and multi-scale feature fusion, and the problem of repeated defect detection in multi-view inspection is effectively solved in combination with a three-dimensional space mapping method.

The invention discloses an intelligent track foreign matter detection system and method based on image recognition, and particularly relates to the technical field of image recognition. A real-time image is acquired, an area-of-interest is extracted in combination with an image segmentation algorithm, and potential foreign matters are identified; the space-time consistency of the detection result is verified by analyzing the space-time data of the track foreign matter so as to judge the real threat; extracting multi-dimensional features such as shape, texture, color and size from a real threat target, and outputting classification confidence to evaluate model classification stability; the detection accuracy is evaluated by combining the space-time consistency and the classification stability, the detection results are divided into different categories, the abnormal degree of subsequent detection is predicted for the incomplete accuracy detection result, and the image acquisition resolution or frame rate is dynamically adjusted to improve the detection definition. The problems of missing detection and frequent false alarm of small and medium-sized foreign matters in the prior art are solved, the accuracy and reliability of track foreign matter detection are greatly improved, and the running safety of a high-speed train is guaranteed.

The invention relates to the technical field of image discrimination, and further relates to a restoration supervision evaluation method based on mine ecological image discrimination, and the method comprises the steps: 1, carrying out the preprocessing of an obtained remote sensing multispectral image of a target mine region, and obtaining a preprocessed image; fusing the standard vegetation index, the bare soil area and the reflectivity ratio to obtain a vegetation recovery index; 2, dividing the preprocessed image into a plurality of ecological patches by using an image segmentation algorithm; calculating to obtain a slope stability index in combination with the crushing degree; 3, evaluating a hydrological recovery index corresponding to the water body area in the preprocessed image through the combination of short-wave infrared and near-infrared bands; and calculating a comprehensive restoration index of the target mine area in combination with the vegetation restoration index, the slope stability index and the hydrological restoration index. The method has the advantages of being high in adaptability, wide in monitoring range and the like, and the supervision efficiency and scientificity of mine repair engineering can be remarkably improved.

The invention discloses a dual-decoder integrated indication image segmentation algorithm and a dual-decoder integrated indication image segmentation device based on SAM (Secure Anything Model) completion, a novel dual-branch decoder framework is introduced, and the SAM (Secure Anything Model) is combined to be used for RIS (Remote Information System). According to the framework, an MLP decoder and a KAN decoder are combined, and a multi-scale feature fusion module is added, so that the capability of identifying fine details in an image by a model is enhanced. Through an ensemble learning strategy, the robustness of the framework is further enhanced, and the insight of MLP and KAN decoder branches is integrated. More importantly, edge coordinates and bounding box coordinate information of the segmented target are used as input prompts of the SAM model. According to the strategy, the zero sample learning capability of the SAM is utilized to perfect and optimize the segmentation result. According to the method disclosed by the invention, the effectiveness of the method is proved on the basis of experimental results of widely accepted RefCOCO, RefCOCO + and RefCOCOg data sets. The result not only reaches the most advanced level in segmentation performance, but also is supported by ablation studies, which highlight the contribution of each component to the improvement of the overall performance.

The invention discloses an interactive image segmentation algorithm based on an algorithm computer, and belongs to the technical field of computer image segmentation. The interactive image segmentation algorithm comprises the following steps: S1, image uploading and preprocessing, S2, construction of a bidirectional interactive propagation mechanism, S3, adaptive image segmentation, and S4, image detection after segmentation. The interactive image segmentation algorithm is combined with lightweight semantic propagation, adaptive segmentation and a user feedback closed loop, the user interaction frequency is remarkably reduced while the precision is ensured, and compared with a pure deep learning scheme, the interactive image segmentation algorithm is more suitable for small sample scenes and is suitable for scenes with double requirements on precision and efficiency, such as medical images and industrial quality inspection; the algorithm can quickly adapt to a new field, a new category or an unknown object, reduces dependence on a large amount of training data in a specific field, minimizes user interaction times and complexity on the premise of ensuring high segmentation precision, can improve user experience, and has the characteristics of extremely simple interaction, ultrahigh precision, superstrong robustness and real-time response.

The invention discloses a cleaning method and a control system of a semiconductor wafer cleaning system in the technical field of information, and the control method of the semiconductor wafer cleaning system comprises the following steps: obtaining a wafer surface image, and processing the wafer surface image by adopting an image segmentation algorithm to obtain a wafer surface image; identifying a polluted area and a non-polluted area in the wafer surface image, and judging the pollution degree and the pollution type of the wafer surface according to the area, the form and the gray scale characteristics of the polluted area; cleaning process data of each batch of wafers is recorded, the cleaning process data comprises a cleaning formula, cleaning parameters, cleaning time, cleaning agent dosage, pollution removal rate and surface damage conditions, a big data analysis technology is applied, optimal cleaning processes of different types of wafers are mined, the cleaning formula database is dynamically updated and optimized, and the optimal cleaning process is updated and optimized. Therefore, the cleaning efficiency and the yield are improved.

The invention provides a concrete strength prediction method based on deep learning, and the method comprises the steps: obtaining a coarse aggregate surface image through employing a three-dimensional scanning method, recognizing the surface roughness of the coarse aggregate, and extracting the pore distribution characteristics of the surface of the coarse aggregate through combining with an image segmentation algorithm; carrying out feature extraction on the interface transition area by adopting wavelet transform to obtain local features of the interface transition area, and carrying out weighted calculation on the local features in combination with an adaptive weighted fusion algorithm to obtain enhanced local feature representation; fusing the marked microstructure parameters with the macroparameters of the whole concrete, constructing a concrete strength prediction model, and outputting a predicted value of the whole strength of the concrete; and predicting the weights of the regions corresponding to different intensities through an adaptive weighted fusion algorithm to obtain local features contributed to the target intensity.

The invention discloses a blasting fragmentation prediction method suitable for a complex terrain mine, and the method is based on high-precision muck pile three-dimensional reconstruction, is combined with an image segmentation algorithm, and enables the calculated overall fragmentation error to be small through the correction of a spatial distribution model. Meanwhile, the overall lumpiness distribution obtained through the method is closer to actual lumpiness distribution, and through boulder rate comparison evaluation, a scientific basis can be provided for mine blasting effect evaluation and production management, blasting parameters can be optimized, and production efficiency can be improved.

The invention relates to the technical field of photovoltaic power generation, in particular to a photovoltaic power station ultra-short-term power prediction method based on double foundation cloud atlas, which comprises the following steps: collecting real-time foundation cloud atlas of two imagers of a photovoltaic power station, and carrying out image preprocessing; dividing the preprocessed foundation cloud picture into different cloud cluster areas by using an image segmentation algorithm; according to a binocular vision principle, calculating cloud bottom height and horizontal distance of each cloud cluster relative to an observation point; and simulating the ground cloud shadow coverage condition of the photovoltaic power station, obtaining an attenuation coefficient, correcting the irradiation intensity by using the attenuation coefficient, and inputting into the power prediction model to obtain an ultra-short-term power prediction value. Through the prediction method, the shielding condition of the cloud layer projection on each area of the photovoltaic power station can be accurately judged, and the ultra-short-term power prediction precision and accuracy of the large-scale photovoltaic power station under the cloudy weather condition are improved.

The invention discloses a medical image segmentation algorithm and system based on Mama, and a storage medium. The method comprises the following steps: processing medical image features through a multi-path convolution attention mixer MCAM; the VSS Block captures global information through a state space model to enhance the coding capability; the COC module extracts features through channel projection, vertical offset and horizontal offset; the up-sampling features and the features output by the MCAM are fused, the resolution of the image is gradually recovered through inverse operation, and the number of channels is adjusted to the proportion required by the segmentation task; inputting the feature maps after multiple complete coding and down-sampling into an up-sampling and visual state space module, and decoding the feature maps together with the corresponding feature maps of multiple coding cross offset connection operations; medical image segmentation is carried out, and key anatomical features and subtle pathological changes are accurately distinguished. By improving downsampling and U-Net jump connection based on Mama, the feature extraction capability and the capability of capturing complex semantic information are enhanced.

The invention relates to the field of engineering geology, in particular to a tunnel face surrounding rock lithology identification method and equipment. The method comprises the following steps: cutting a to-be-identified tunnel face surrounding rock image according to a preset size, and outputting a sub-image set; sequentially inputting the sub-image set into a pre-constructed lithology identification model, and outputting an identification result corresponding to each sub-image; and the identification result corresponding to each sub-image is synthesized to obtain a corresponding lithology condition identification graph. According to the method, tunnel face surrounding rock is segmented from a whole image through an image segmentation algorithm (mainly, a tunnel lining area outside a tunnel face is cut off), the segmented tunnel face is cut into a plurality of sub-images with the same size, and a data set is constructed through the sub-images; lithology analysis is carried out through a pre-constructed lithology identification model; and comprehensively analyzing the tunnel face image based on the proposed partition identification comprehensive evaluation method, thereby realizing efficient and accurate identification of lithology of the tunnel face surrounding rock image.

A warehouse goods intelligent identification and positioning management system based on an image segmentation algorithm comprises an image acquisition and preprocessing module, an image segmentation algorithm module, a goods positioning and feedback module, an inventory management module, a data communication and integration module and a user interaction and management module. The image segmentation algorithm module is used for segmenting and extracting image information. The cargo identification and positioning module is used for identifying and positioning cargoes. The position feedback and alarm module is used for feeding back cargo positions and giving an alarm. The inventory management module is used for managing and maintaining cargo information. The data communication and integration module is used for transmitting information in real time. According to the warehouse goods intelligent identification and positioning management system based on the image segmentation algorithm, the warehouse image segmentation algorithm based on deep learning is put forward to classify goods, and the goods identification and positioning algorithm based on improved label template matching is put forward to intelligently position the goods.

The invention relates to the technical field of image detection, in particular to a target object detection method, device and system and a computer readable storage medium. According to the method, the deep learning model and the image segmentation algorithm are combined, the detection results obtained through detection in two modes are preliminarily screened, the detection results with high accuracy are subjected to cross-linking processing, the first detection result and the second detection result are fused according to the cross-linking comparison, and the detection result for the target object is generated. Through the mode, the characteristic of high accuracy of the recognition result of the deep learning model and the characteristic of high recall rate of the image segmentation algorithm are combined, targets with similar shapes can be accurately recognized through the deep learning model, and the defect of low precision of the image segmentation algorithm is overcome; the majority of targets in the image can be detected through the image segmentation algorithm, the problem that a deep learning model is inaccurate in small target recognition is solved, and the accuracy of target object detection can be greatly improved through combination of the two.

The embodiment of the invention discloses a rice processing precision detection method, electronic equipment and a storage medium, and relates to the technical field of image processing. The method comprises the steps that an outer surface image of undyed rice is acquired, and the outer surface image comprises a front image and / or other surface images; segmenting a seed coat area, an endosperm area and a rice complete area in the outer surface image by using an image segmentation algorithm; and determining the rice processing precision by utilizing the areas of the seed coat area, the endosperm area and the rice complete area. The embodiment of the invention provides a dyeing-free rice processing precision detection method.

The invention belongs to the field of rockfill material grading detection, and relates to a rockfill material grading detection method and device based on an image segmentation algorithm, and the method comprises the steps: 1) obtaining an image after paving of stone particles; 2) preprocessing the stone image; 3) inputting the preprocessed image into an instance segmentation model to obtain mask information of stone particles; 4) extracting mask quantitative indexes and shape characteristic parameters in the mask information of the stone particles, and performing particle size and stone total volume conversion in each particle size range on the mask quantitative indexes and the shape characteristic parameters; (5) converting the obtained stone particle size and volume into three-dimensional stone particle gradation, and drawing a stone particle apparent gradation curve; 6, the obtained stone particle apparent grading curve is corrected through the data fusion model.The final stone particle three-dimensional overall grading curve is obtained.The method has the advantages of being high in adaptability, free of a special detection environment and high in detection precision.

The invention discloses a plant extraction method and system based on image processing, and relates to the technical field of image processing. The method comprises the following steps: acquiring and standardizing a plant raw material image; extracting feature vectors of the images by using a neural network convolutional layer algorithm, comparing the feature vectors with a plant raw material standard feature database, and screening out qualified images of the plant raw materials; qualified images are processed through multispectral image analysis and an image segmentation algorithm, and an effective component spatial distribution diagram is obtained; constructing a partial least squares regression linear model, extracting spectral feature vectors of the effective components, inputting the spectral feature vectors into the model to obtain concentration values, and calculating quantitative data of the effective components; establishing an extraction process rule base, selecting a process parameter combination according to a spatial distribution diagram and quantitative data, and extracting to obtain a primary extracting solution and plant residues; and calculating an effective component residual error rate by matching and mapping to a qualified image coordinate, and if the effective component residual error rate is greater than a preset threshold, performing secondary extraction to obtain a secondary extracting solution. And quantitative basis is provided for extracting process parameters through the spatial distribution diagram of the effective components.

The invention discloses an artificial intelligence-based automatic qualitative and quantitative analysis method for freshwater phytoplankton. The method comprises the following steps: data acquisition: capturing an algae image in a water sample by using high-resolution image acquisition equipment; image preprocessing: denoising, contrast enhancement and binarization preprocessing are carried out on the acquired image so as to improve the image quality and make preparations for subsequent analysis; image segmentation: using an image segmentation algorithm to distinguish algal cells and a background, and extracting an image area of the algal cells; feature extraction: extracting features of algae cells from the segmented image for subsequent identification and classification; the method has the beneficial effects that the artificial intelligence technology automatically recognizes algae species, and compared with a traditional artificial microscopic examination recognition method, the working efficiency can be greatly improved; and a user can create and store a personalized analysis template, so that reuse in similar projects is facilitated, and the working efficiency is improved.

The invention discloses an agricultural insurance data acquisition and management system based on satellite remote sensing. The system comprises a data acquisition module, a preprocessing module, a verification module and a management module. The data acquisition module covers basic, universal and vector data acquisition according to data types; the preprocessing module improves the quality of collected data; the verification module verifies a cultivated land vector and insured user information, and data accuracy and reliability are enhanced; the management module builds two libraries, and constructs an agricultural insurance data large model by utilizing knowledge graph modeling. In the technical application, on the basis of satellite remote sensing and A I, large-user plot data is collected by means of an image segmentation algorithm, and the cost is reduced. A full-coverage model is constructed through abstract materialization, and business application is supported. Technical means such as satellite remote sensing, weight dispatch data superposition and AI image recognition are used for verifying data, manual operation is reduced, verification accuracy is guaranteed, data value is mined, and the agricultural insurance data management level is improved.

The invention discloses a coal mine image segmentation algorithm based on Swinin-UMama, and relates to the technical field of computer vision. According to the method, the design of double-branch dark light enhancement, self-adaptive multi-scale feature extraction of a Swindow-UMama framework and three-channel parallel processing (wavelet module, spatial pyramid and channel attention) is combined, and comprehensive optimization of a multi-loss function is supplemented, so that a coal mine image segmentation model is obtained; the provided coal mine image segmentation model shows excellent performance in an image segmentation task in a coal mine low-light environment, and the method not only significantly improves the segmentation accuracy and boundary definition, but also enhances the adaptability and robustness of the model in a complex environment. And powerful technical support is provided for coal mine safety monitoring and management.

The invention discloses a lightweight 3D heart MRI segmentation algorithm based on 3D efficient partial attention and three-dimensional sparse MLP, and the algorithm obtains an MRI pixel block with a detailed target region feature through a 3D efficient deformable attention module EDA, and fits the edge distribution of a segmented region with lower calculation complexity through reference point translation. Efficient attention calculation ensures feature information extraction and greatly reduces resource consumption; the method comprises the following steps: constructing a cross-shaped receptive field at extremely low cost through information in transverse, longitudinal and depth directions of a three-dimensional sparse MLP module (triSMLP) mixed voxel block, and outputting a fine characteristic spectrum with a global receptive field through three-time superposition; the feature maps output by the EDA and the triSMLP recover down-sampling lost detail features at an encoder through a partial convolution feature fusion decoder. Compared with most of the leading edge 3D segmentation algorithms at present, the method has the advantage that a better segmentation effect is obtained with extremely small computing resources.

The invention discloses a screen display content and background light collaborative optimization method, and relates to the technical field of screen display adjustment, and the method comprises the steps: collecting the image content currently displayed by a display screen, dividing the image content into a plurality of sub-regions through an image segmentation algorithm, and calculating the average brightness value of each sub-region; a background light intensity measurement value of each sub-region is obtained, a background light intensity distribution curve is formed through cubic spline interpolation, the distribution curve is inquired according to the center position of the sub-region, and the background light intensity is obtained; and constructing an adaptive mapping function based on the ratio of the average brightness value to the background light intensity of the sub-regions, dividing a dynamic adjustment interval, and dynamically adjusting the display parameters of each sub-region according to the adaptive mapping function to complete collaborative optimization of the screen display content and the background light. According to the invention, the visual performance of the display device under different ambient light is improved, the display effect is optimized in a targeted manner under different background light conditions, and the method has a wide application prospect.

The invention is suitable for the technical field of building model data processing, and provides an intelligent building texture repairing and beautifying method fusing a deep learning model, and the method comprises the steps: firstly, carrying out the recombination of the texture of a three-dimensional building model, and generating a to-be-processed wall surface and roof texture picture; a to-be-repaired area, needing to be repaired, of the building texture is extracted by combining low-rank matrix decomposition and an SAM image segmentation algorithm, and then whether an LAMA image repair model or a PatchMatch image repair algorithm is used for texture processing is determined according to the proportion of the to-be-repaired area in a whole texture image so as to achieve the maximum repair effect. And finally, carrying out texture distortion repair and material beautification by using an image diffusion model, a ControlNet control chart and cue words, and outputting beautified wall surface and roof textures. The problems of texture shielding, garland, noise, window distortion and the like can be solved at the same time, automatic detection and automatic texture repairing and beautifying of the texture shielding garland area are achieved, and the time consumption of texture editing processing in the building monotonized modeling process is remarkably shortened.

The invention discloses a retroreflection brightness coefficient determination method, which comprises the steps that a first image and a second image corresponding to a detected position in marking detection are acquired, the first image is an image acquired under the condition of single-wavelength laser projection, and the second image is an image acquired under the condition of single-wavelength laser non-projection; identifying a first marking area in the first image by using a given image segmentation algorithm; identifying a second marking area in the second image by using a given image segmentation algorithm; extracting a first gray value of a first marking area in the first image; extracting a second gray value of a second marking area in the second image; and according to the first gray value, the second gray value and a given retro-reflection brightness coefficient standard value, calculating the retro-reflection brightness coefficient of the marked line at the detected position. The invention further discloses a retroreflection brightness coefficient detection and evaluation device, electronic equipment and a program product.

The invention provides an image processing system and device of an intelligent water affair inspection robot, relates to the technical field of water affair inspection, and solves the technical problems of poor light reflection restoration effect, difficulty in floating object feature extraction and relatively high water quality abnormity judgment misjudgment rate in the prior art. The system comprises an image processing module, and an acquisition module and an image analysis module which are connected with the image processing module, the acquisition module is used for acquiring an original image of a water body area acquired by the inspection robot; the image processing module is used for performing reflection restoration on a reflection area in the original image through pixel restoration to obtain a restored image; performing water body and surrounding environment segmentation on the restored image through an image segmentation algorithm to obtain a water body image; performing feature extraction on the water body image through edge detection to obtain water quality features; and the image analysis module is used for carrying out abnormity judgment on the water body area according to the water quality characteristics and generating an abnormal signal. The method is used in the water affair inspection process.

Systems and methods for detecting artificial intelligence generated images are provided. The system accepts an input image (e.g., a digital still image, or a frame from a digital video file or image stream) and subdivides the input image into a set of patches using a patch partitioning algorithm. The system then processes each patch and produces a feature embedding for each patch within a high dimension space. The system then utilizes these patches with further processing as input to machine learning models, which allows the system to achieve image, patch-level, and video-frame generated image classification and localization alongside identification of the generative model used to synthesize the image.