Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

63results about How to "Improve Change Detection Accuracy" patented technology

Method for carrying out change detection on multi-level segmented remote sensing image

ActiveCN102254319ASpectral properties are stableEfficient removalImage analysisPattern recognitionChange detection
The invention discloses a method for carrying out change detection on a multi-level segmented remote sensing image, and is characterized in that the method comprises nine steps, and in the method, after carrying out denoising and smoothing and the like on the image, through merging patch objects, a change detection result of the remote sensing image is obtained finally. In the method, the patch objects subjected to segmentation are compared by using a direct comparison method firstly, if the patch objects are changed, the patch objects are subjected to secondary segmentation by using an algorithm, then characteristic values are extracted and compared. By using the method disclosed by the invention, the pseudo change information can be removed effectively, and the change detection accuracy can be improved; and compared with the existing methods, by using the method disclosed by the invention, a more detailed and complex change result can be obtained, thereby realizing the change detection on sub-patch objects.
Owner:GEOVIS CO LTD

Object-level high-resolution remote sensing image change detection method based on multi-scale fusion

The invention discloses an object-level high-resolution remote sensing image change detection method based on multi-scale fusion. A color texture segmentation algorithm JSEG is introduced to change detection and multi-scale feature extraction and analysis on an object is realized based on a J-image image sequence generated in the segmentation process of the JSEG algorithm. The algorithm makes comprehensive use of the shape, the size and the spectral and texture features of the object, introduces two different multi-scale fusion strategies based on a D-S evidence theory and weighted data fusion and further improves divisibility of changing categories and non-changing categories so as to construct a complete set of object-level change detection frames based on multi-scale fusion. The feasibility and effectiveness of the method are verified by respectively carrying out experiment on a high-resolution aerial remote sensing DOM image and an SPOT5 satellite remote sensing image and comparing detection effects of change detection methods of different object levels and pixel levels.
Owner:HOHAI UNIV

High-resolution remote sensing image change detection method based on twin convolutional neural network

The invention belongs to the technical field of optical remote sensing image change detection, and particularly relates to a high-resolution remote sensing image change detection method based on a twin convolutional neural network. The method comprises the following steps: 1, making a sample data set; 2, constructing a twin convolutional neural network model; 3, training a twin convolutional neural network model; 4, model prediction is carried out, and a change detection initial result is output; and 5, carrying out post-processing on the initial result to obtain a final change detection result. According to the method, the convolutional neural network technology is applied to the field of high-resolution remote sensing image change detection, and the twin convolutional neural network fusing high-dimensional features and low-dimensional features is constructed to train and autonomously extract the features layer by layer, so that the problem of information omission possibly occurring in manual calculation and feature selection processes is avoided, and the change detection precision is improved.
Owner:BEIJING RES INST OF URANIUM GEOLOGY

Geospatial image change detecting system with environmental enhancement and associated methods

An image change detecting system may include an image processor cooperating with the database for generating a reference geospatial image corresponding to the collected geospatial image, an image enhancer for enhancing at least one of the reference geospatial image and the collected geospatial image based upon at least one environmental condition, and a change detector cooperating with the image processor and the image enhancer. The change detector may detect a change between the collected geospatial image and the reference geospatial image with at least one thereof enhanced by the image enhancer based upon the at least one environmental condition. The environmental condition may include a weather condition, a time of day, or a time of year. The environmental condition may be typically associated with the collected geospatial image.
Owner:HARRIS CORP

SAR image change detection method based on pyramid pooling twin network

ActiveCN110533631AReduce usageOvercome the problem that change detection results are affected by the difference mapImage enhancementImage analysisTest sampleDifference-map algorithm
The invention provides an SAR (Synthetic Aperture Radar) image change detection method based on a pyramid pooling twinning network, which mainly solves the problem of inaccurate result caused by the fact that the change detection precision depends on a difference graph in the traditional method. The method comprises the following steps: 1) generating a training sample, a test sample and a sample label; 2) constructing a deep pyramid pooling twin network; 3) constructing a classification network; 4) training the deep pyramid pooling twin network and the classification network by using the training samples and the sample labels to obtain a trained model. According to the method, the use of a difference graph can be avoided, the influence of the difference graph on the change detection resultis effectively solved, the accuracy of change detection is improved, and the method can be used for environmental detection and disaster detection.
Owner:XIDIAN UNIV

Remote sensing image change detection method and system based on mask classification

InactiveCN104834942AStrong anti-noise interferenceIncrease amplitudeCharacter and pattern recognitionWave bandCluster result
The invention provides a remote sensing image change detection method and system based on mask classification, and the method comprises the steps: 1, the preprocessing of a multiband remote sensing image; 2, the single-band separation of the multiband remote sensing image after preprocessing; 3, the constructing of a single-band difference image of two-phase single-band remote sensing images; 4, the construction of a change mask difference image, and cutting the change mask difference image based on an Otsu method; 5, the multiplication fusion of a change mask with one of the two-phase single-band remote sensing images, thereby obtaining a change region; 6, the clustering of the change region through a fuzzy C mean value method; and 7, determining the change type of the change region through combination of the prior knowledge of the ground object type of the other one of the two-phase single-band remote sensing images according to the clustering results of the change region. The method and system are resistant to nose interference, can alleviate local optimum effectively, can consider the qualitative and quantitative description of an image change process, and is high in change detection precision and reliability.
Owner:WUHAN UNIV

Remote-sensing image variation detecting method based on slow characteristic analysis

ActiveCN103632155ASuppression of spectral differencesHighlight real changesCharacter and pattern recognitionState variationData set
The invention discloses a remote-sensing image variation detecting method based on slow characteristic analysis. A slow characteristic analysis approach is introduced in the detection of multi-temporal remote-sensing image variations; in the slow characteristic analysis approach, the space corresponding relation between the multi-temporal remote-sensing images is completely taken into account, and the original theory aiming at continuous signal analysis is developed into a variation detecting algorithm based on a discrete data set. By utilizing the slow characteristic analysis approach, invariant characteristics can be extracted from a multi-temporal remote-sensing image data set to serve as a characteristic space; in the characteristic space, the spectrum difference between the multi-temporal remote-sensing images is restrained, and true variation is highlighted, so that the variation detection accuracy can be enhanced. The slow characteristic analysis approach is simple to perform and high in arithmetic speed.
Owner:WUHAN UNIV

GPS spatial-temporal trajectory-based road network topological change automatic detection method and system

The invention discloses a GPS spatial-temporal trajectory-based road network topological change automatic detection method and system, and the method comprises the steps: step 1, establishing a local spatial-temporal trajectory vector based on a GPS spatial-temporal trajectory; step 2, establishing a local road topological vector based on road network data and the GPS spatial-temporal trajectory; step 3, measuring the similarity of the local spatial-temporal trajectory vector and the local road topological vector; step 4, extracting changed trajectory points and establishing a road topological relation of a local range of the changed trajectory points; step 5, comparing the road topological relation of the local range of the changed trajectory points with an original road network, thus obtaining the road network topological change. The method can automatically detect the topological and graph change of an urban road network, and realizes the change detection of a road network topology and a road network graph while improving the change detection precision of the road network; in addition, the invention has the advantages of low cost and efficiency.
Owner:WUHAN UNIV

Wave band correction change detection method of remote sensing image fuzzy clustering and system thereof

The invention provides a wave band correction change detection method of remote sensing image fuzzy clustering and a system thereof. The method comprises the following steps: step1, carrying out pretreatment of a multi-band remote sensing image, which means filtering and enhancement processing of the multi-band remote sensing image; step 2, carrying out single band separation on the multi-band remote sensing image after the pretreatment and acquiring a single-band remote sensing image; step 3, constructing a single band difference image of two time-phase single-band remote sensing images; step 4, constructing a multi-band combined image based on two time-phase multi-band remote sensing images after the pretreatment and acquiring a mutual neighborhood information content of each pixel of the multi-band combined image; step 5, correcting the mutual neighborhood information content of the pixels of the multi-band combined image and acquiring a correction image; step 6, using a fuzzy C-means method to carry out change detection on the correction image. By using the method and the system of the invention, detection precision is high, an anti-noise interference ability is good and an automation degree is high.
Owner:WUHAN UNIV

SAR (Synthetic Aperture Radar) image change detection method based on mixing model

The invention discloses an SAR (Synthetic Aperture Radar) image change detection method based on a mixing model, which mainly solves the problems of single mode structure, poor matching degree and poorer speckle noise suppression of the traditional SAR image change detection technology. The SAR image change detection method comprises the following steps of: (1) implementing geometric registration and radiation correction for two images with different time phrases in a same area; (2) inputting images to be matched and corrected; (3) preprocessing the input image; (4) extracting difference images for the pre-processed images ; (5) constructing a mixing model of the difference images; (6) constructing an evaluation function and a penalty function in the mixing model; (7) solving the evaluation function to obtain an optimal threshold value; and (8) outputting a result image according to the optimal threshold value. According to the SAR image change detection method based on the mixing model, the mixing model is modeled according to the extracted different images, the problem that the pixel distribution of the SAR image cannot be perfectly matched in a single model is solved, the false change information is reduced, and a better detection result is obtained.
Owner:XIDIAN UNIV

Method for detecting two-time-phase remote sensing image change

ActiveCN103426158AEfficient use ofOvercome the disadvantages of effective useImage analysisComputer scienceRandom field ising model
The invention discloses a method for detecting two-time-phase remote sensing image change. In the method for detecting two-time-phase remote sensing image change, a gaussian process classifier is combined with a Markov random field model, effective utilization of image space information is reinforced, and change detecting precision is improved.
Owner:济钢防务技术有限公司

Unsupervised SAR image change detection method

The invention provides an unsupervised SAR image change detection method which is used for solving the technical problem existing in the prior art that detection accuracy and calculation efficiency are relatively low. The implementation steps include: filtering registered SAR images of two time phases; generating an initial difference diagram; performing saliency detection on the initial difference diagram to obtain a saliency difference diagram; utilizing a fuzzy C-means clustering algorithm to pre-classify the saliency difference diagram to obtain candidate training samples and uncertain samples; performing equalization processing on the candidate training sample set to obtain training samples; utilizing a PCA filter to extract characteristics of the training samples and characteristicsof the uncertain samples; and utilizing the characteristics of the training samples to train a support vector machine, and utilizing the trained support vector machine to classify the uncertain samples to obtain a change detection result. The unsupervised SAR image change detection method provided by the invention can reduce operation time while improving detection accuracy, and can be used for disaster assessment, disaster development tendency prediction, target detection, land covering and utilization monitoring and the like.
Owner:XIDIAN UNIV

SAR image change detection method based on stack semi-supervised adaptive denoising auto-encoder

The invention discloses an SAR image change detection method based on a stack semi-supervised adaptive denoising auto-encoder, and aims at solving the problem that in an existing method, the precision of detection on coherent speckle noise points and change areas of many edges is low. The method comprises the steps that a multi-scale difference guide diagram is generated; a first time phase image is taken as the input to train an SDAE; the multi-scale difference guide diagram, the first time phase image and a second time phase image are taken as the input to train the SSADAE, and weights obtained in SDAE training are used in an SSADAE self-adaption error function; the feature vector of the first time phase image and the feature vector of the second time phase image are calculated by the SSADAE; and the feature vector of the first time phase image and the feature vector of the second time phase image are subtracted to obtain a difference vector, an FCM classification is conducted on the difference vector to obtain a change detection result diagram. According to the method, the multi-scale difference guide diagram is proposed firstly and can highlight the change areas in the difference diagram; and the SSADAE proposed later can improve the change detection accuracy by utilizing a small quantity of mark samples in the image.
Owner:XIDIAN UNIV

SAR image change detection method based on context salience detection and SAE

An SAR image change detection method based on context salience detection and SAR image change detection is disclosed. Two phase SAR images of the same region are input; logarithmic ratio difference chart is calculated; significance Region of Difference Map Based on Context significance detection algorithm is extracted; according to the salient area mask of the difference map, the background of thetwo temporal SAR images is masked, and the SAR image after the masking is obtained; based on fuzzy C-means clustering, the change region of SAR image after the mask is extracted, and the training samples of pseudo-label are obtained; multi-layer sparse automatic encoder is trained by using masked SAR images and pseudo-label training samples; the final SAR image change region is extracted by the trained network. The invention can effectively overcome the influence of the speckle noise on the SAR image change detection, meanwhile, a multi-layer sparse automatic encoder is designed, the effective change characteristics of the SAR image are extracted, the accuracy of the change detection can be improved, and the invention can be used in the technical fields of multi-temporal SAR image changedetection and the like.
Owner:DALIAN UNIV OF TECH +3

SAR image change detection method based on hyper pixel saliency analysis

The invention discloses an SAR image change detection method based on hyper pixel saliency analysis, for mainly solving the problem of low detection precision of the traditional technology. The scheme is as follows: 1) inputting images of the same scenes at two different moments to obtain a log ratio graph of the images; performing guide filtering on the log ratio graph to obtain a filtering graph; 2) performing hyper pixel segmentation on the filtering graph to obtain segmented graphs; 3) calculating the segmented graphs by using a saliency method to obtain saliency graphs; performing threshold processing on the saliency graphs, and combing the two images at different moments to obtain a differential graph; and 4) clustering the differential graph by using a fuzzy local information C mean clustering method to obtain a change graph. According to the SAR image change detection method, hyper pixel segmentation and guide filtering are imported, thereby not only reducing the noise of SAR images, but also effectively improving the accuracy of the SAR images by the obtained saliency graphs, and the SAR image change detection method can be used for detecting change areas.
Owner:XIDIAN UNIV

Geospatial image change detecting system with environmental enhancement and associated methods

An image change detecting system may include an image processor cooperating with the database for generating a reference geospatial image corresponding to the collected geospatial image, an image enhancer for enhancing at least one of the reference geospatial image and the collected geospatial image based upon at least one environmental condition, and a change detector cooperating with the image processor and the image enhancer. The change detector may detect a change between the collected geospatial image and the reference geospatial image with at least one thereof enhanced by the image enhancer based upon the at least one environmental condition. The environmental condition may include a weather condition, a time of day, or a time of year. The environmental condition may be typically associated with the collected geospatial image.
Owner:HARRIS CORP

Non-local wavelet information based remote sensing image change detection method

ActiveCN104200472AOvercome the problem of rapid deterioration of change detection results and poor anti-noise performanceImprove robustnessImage enhancementImage analysisImage denoisingWavelet decomposition
The invention discloses a non-local wavelet information based remote sensing image change detection method. The non-local wavelet information based remote sensing image change detection method mainly solves the problem that the remote sensing image change detection method is low in detection accuracy. Achieving steps of the non-local wavelet information based remote sensing image change detection method comprise (1) reading data; (2) constructing a difference chart; (3) performing wavelet decomposition; (4) denoising a high-frequency portion through a non-local information based method; (5) performing inverse transformation; (6) cutting through a local fuzzy C-mean clustering method. According to the non-local wavelet information based remote sensing image change detection method, the low-frequency information integrity is protected and noise is effectively removed due to the facts that the noise is mainly distributed on a high-frequency detail information portion and accordingly image denoising is performed on a high-frequency detail portion and a self-structure of the image is protected and the image robustness to the noise is improved due to the fact that a single pixel is processed in combination with vectors of neighborhood information.
Owner:XIDIAN UNIV

Remote sensing image change detection method based on Treelet and direction adaptive filtering

The present invention discloses a remote sensing image change detection method based on Treelet and direction adaptive filtering, which comprises the following realizing steps of: (1) reading in data; (2) constructing a difference image; (3) direction adaptive filtering; (4) fusion of Treelets; (5) adaptive threshold value classification; and (6) post-processing. With the remote sensing image change detection method based on Treelet and direction adaptive filtering, marginal information of changing areas can be better kept and residual information of change detection results can be reduced as well. The method, having sound change detection accuracy, can be applied to fields such as dynamic monitoring of water levels of lakes, crop growth situation, urban planning, and military reconnaissance.
Owner:XIDIAN UNIV

Remote sensing image change detection method based on neural network structure search

PendingCN114187530AAvoid the defects of insufficient extraction of remote sensing image featuresImprove Change Detection AccuracyScene recognitionNeural architecturesPattern recognitionTest sample
The invention provides a remote sensing image change detection method based on neural network structure search. The remote sensing image change detection method comprises the implementation steps of obtaining training, verification and test sample sets; constructing a super neural network model; performing iterative training on the super neural network model; searching the trained super-neural network model by adopting a genetic algorithm to obtain structure search parameters; constructing a remote sensing image change detection model based on structure search parameters; performing iterative training on the remote sensing image change detection model; and acquiring a change detection result of the remote sensing image. The genetic algorithm is adopted to search the trained super-network neural model, the structure of the remote sensing image change detection model is determined through the searched structure search parameters, the structure of the remote sensing image change detection model can be highly matched with the characteristics of the remote sensing image, the remote sensing image characteristics are extracted more sufficiently, and the detection accuracy is improved. And the change detection precision of the remote sensing image is effectively improved.
Owner:XIDIAN UNIV

Remote sensing image binary change detection method based on feature deviation alignment

ActiveCN113378727ASolve the problem of false alarms in change detectionImprove detection accuracyImage enhancementImage analysisData setAngle of view
The invention discloses a remote sensing image binary change detection method based on feature deviation alignment. The method comprises the following steps: 1, constructing a dual-time-phase remote sensing image binary change detection data set and carrying out preprocessing; 2, constructing a binary change detection model based on feature deviation alignment, and giving a dual-temporal remote sensing image to obtain a change region prediction result and a change region auxiliary prediction map; 3, respectively calculating a main loss function and an auxiliary loss function by using a real change area label result, a prediction change area result and a change area auxiliary prediction map, carrying out back propagation on a gradient according to loss to update a model, stopping training until a loss value converges, and storing a model structure and a model weight; and 4, predicting test set data by using the model weight trained in the step 3. According to the invention, the false detection phenomenon of the change area of the dual-time-phase remote sensing image caused by factors such as multi-view shooting, too many high-rise buildings or large topographic relief can be effectively solved.
Owner:WUHAN UNIV +1

Change detection method based on image texture features and DSM

The invention provides a change detection method based on image texture features and DSM. The method comprises the steps that surface features are divided into a plurality of types of surface features; according to the characteristics of each surface feature type, the elevation change threshold range corresponding to each type of surface feature is set; statistical analysis is carried out on texture features corresponding to each type of surface feature; for each sub-region, the corresponding texture features set in the first step and the corresponding elevation change threshold range are retrieved according to the surface feature type corresponding to the sub-region; the texture features and the elevation change threshold range corresponding to the surface feature type are used to further determine a preliminary change detection result; and whether the preliminary change detection result is correct is determined. The change detection method provided by the invention has the advantages that the texture features and the DSM information are integrated into a change detection process with different surface feature thresholds, and the change detection precision is effectively improved.
Owner:MAPUNI TECH CO LTD

Multi-temporal remote sensing image change detection method based on joint dictionary learning

ActiveCN105989595AImprove Change Detection AccuracyOvercoming the Difficulty of Manual LabelingImage analysisDictionary learningComputer science
The multi-temporal remote sensing image change detection method based on joint dictionary learning includes: 1) extracting a large number of unchanged samples from the multi-temporal remote sensing image, and performing joint dictionary learning on the samples to obtain the basis of the unchanged samples; 2) combining step 1) The remaining multi-temporal samples that are not selected are used as test set samples; the test set samples are sparsely reconstructed with the base of the unchanged sample; the difference between the test set samples and the reconstructed test set samples is obtained; 3) from the multi-temporal remote sensing image Select a small number of changed samples; use the basis of unchanged samples to sparsely reconstruct the changed samples of different time phases; use the difference between the reconstructed images of different time phase changed samples, and obtain the change threshold of the changed samples through pooling operation; 4 ) to identify the change area of ​​the multi-temporal remote sensing image by combining the difference image and the change threshold of the change sample, and count the detection rate. The invention can greatly reduce the use of marked samples, does not need to manually select the change threshold, and can improve the detection rate of remote sensing image changes.
Owner:XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI

Transform-based remote sensing VHR image change detection method

The invention discloses a remote sensing VHR image change detection method based on Transform, and the method comprises the steps: 1, constructing a preprocessing module, inputting dual-time-phase remote sensing VHR input images I1 and I2, and outputting the dual-time-phase remote sensing VHR input images I1-1 and I2-1; 2, a Transform module is constructed, input data are the feature maps I1-1 and I2-1 output in the step 1, and output is extracted feature maps O1 and O2; 3, a change detection module is constructed, input data are the feature maps O1 and O2 output in the step 2, and an output image subjected to binarization processing after change detection and a binary image with the size being H * W are output. According to the method, based on the combination of the latest Transform model and the change detection task, the most advanced performance is obtained in the tasks of image classification, target detection, semantic segmentation and the like, and the method is applied to the change detection task to improve the change detection accuracy.
Owner:XIAN UNIV OF TECH

SAR image change detection method based on sparse representation and capsule network

The invention provides an SAR image change detection method based on sparse representation and a capsule network, and the method comprises the steps: (1) selecting two multi-temporal SAR images X1 andX2, and obtaining a differential image through a neighborhood logarithm ratio operator; (2) extracting sparse features on the differential image through a sparse representation method, and generatinga feature image; (3) obtaining pseudo tags of initial classification through a fuzzy clustering method FCM, and selecting proper samples from the feature image to make a sample set by adopting a selection principle of high-confidence samples; (4) constructing an improved capsule network, inputting the feature image extracted through sparse representation, and training an optimization network; and(5) testing the network and generating a change detection image. According to the SAR image change detection method, spatial neighborhood information of the SAR images is fully considered, and sparserepresentation is combined with a capsule network, so that the influence of speckle noise is reduced, deep features of the images are extracted, and the precision and speed of SAR image change detection are improved.
Owner:TIANJIN POLYTECHNIC UNIV

Hyperspectral image change detection method based on spatio-temporal joint graph attention mechanism

The invention discloses a hyper-spectral remote sensing image change detection method based on a spatio-temporal joint graph attention mechanism, which introduces the spatio-temporal joint graph attention mechanism, utilizes the relevance between different time phase earth surface coverage to spread earth surface coverage information, and effectively makes up for the deficiency when a traditional convolutional neural network is used for extracting features. Meanwhile, the attention mechanism of the space-time joint graph performs feature propagation in a semi-supervised manner, so that the dependency of the network on the number of marked samples can be reduced to a certain extent. Besides, a network framework of a super-pixel-level branch and a pixel-level branch is introduced, the super-pixel-level feature and the pixel-level feature of the hyperspectral image are extracted respectively, the two branches cooperatively work in a complementary mode, and the change detection precision is effectively improved. Experimental results show that the overall precision of the method on three data sets of driver, farm and USA reaches 96.91%, 98.40% and 96.87% respectively, and the Kappa coefficients are 79.57%, 96.14% and 90.99% respectively.
Owner:LIAONING NORMAL UNIVERSITY

Bilateral depth feature domain heterogeneous remote sensing image change detection method

PendingCN111310678AGood effectOvercome uneven lightingScene recognitionNeural architecturesSymmetric convolutionIterative refinement
The invention discloses a bilateral depth feature domain heterogeneous remote sensing image change detection method. The method comprises the following steps: constructing a bilateral input symmetricconvolutional neural network; establishing a feature domain constrained probability model; iteratively optimizing the probability model, and solving a difference probability graph; and thresholding the difference probability graph, and outputting a binary change graph. According to the bilateral symmetric convolutional neural network, unsupervised feature automatic extraction of two heterogeneousimages can be realized, the probability of change is measured in a feature domain, the change detection false alarm rate caused by non-uniform illumination, small particle noise and the like can be overcome, the effect of a heterogeneous image difference graph is enhanced, and the change detection accuracy is improved.
Owner:NANJING UNIV OF SCI & TECH

Global land vegetation biomass change monitoring method

The invention relates to a global land vegetation biomass change monitoring method which can be applied to remote sensing application departments of climatic change research, environment monitoring, land management, agricultural condition monitoring, disaster monitoring and the like. The method includes the three steps that first, certain processing and spatial interpolation processing are performed on original data, and then the spatial average of GPP / NPP products of an MODIS on a Terra satellite is calculated through the formula 1; second, the global or regional vegetation average biomass condition is calculated; third, the global or regional vegetation biomass change trend is further calculated through the global or regional vegetation average biomass calculated in the second step, and spatial and temporal change analysis is performed on the global or regional vegetation biomass change. Global analysis shows that the global biomass has a decreasing trend as a whole.
Owner:INST OF AGRI RESOURCES & REGIONAL PLANNING CHINESE ACADEMY OF AGRI SCI +7

SAR image change detection method based on FPGA

The invention discloses an SAR (Synthetic Aperture Radar) image change detection method based on an FPGA (Field Programmable Gate Array), which mainly solves the problems that the prior art is easilyinfluenced by noise and the detection speed is low. The method comprises the following implementation steps of: 1) reading in two SAR images at different periods; 2) carrying out parallel Lee filtering on the two SAR images; 3) generating two difference graphs with different characteristics according to the filtered image, namely a direct difference graph and a logarithm ratio difference graph; 4)transforming the difference image into a frequency domain by adopting parallel wavelet transformation, and performing fusion and parallel wavelet inverse transformation in the frequency domain to obtain a fused difference image; 5) using a parallel difference K-means method to perform two clustering on a fusion difference map to obtain a change detection result. The invention adopts a method of FPGA parallel acceleration and difference graph fusion, has the advantages of fast detection speed and good anti-noise performance, and can be used for fast and accurate SAR image change detection in complex environments.
Owner:XIDIAN UNIV

Remote sensing image change detection method

The invention discloses a remote sensing image change detection method. The method comprises the following steps: acquiring a first remote sensing image and a second remote sensing image shot at the same position at different moments; respectively marking the first remote sensing image and the second remote sensing image to form unlabeled sample data and labeled sample data; performing vector format conversion on the unlabeled sample data and the labeled sample data to form unlabeled sample vector data and labeled sample vector data; performing network structure search by using an evolutionary algorithm to obtain a plurality of target ladder grid models; performing semi-supervised and unsupervised training on each target ladder network model to determine an intermediate optimal ladder network model; and performing semi-supervised and unsupervised training on the middle optimal ladder network model to obtain a target optimal ladder network model, wherein an output result corresponding to the target optimal ladder network model is a detection result. The detection method is higher in universality, and a better remote sensing image change detection result can be obtained.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Multispectral Image Change Detection Method Based on Generative Adversarial Network

The invention discloses a multi-spectral image change detection method based on a generative confrontation network, which solves the problems of low detection accuracy and sensitivity to noise in the prior method. The implementation steps are: 1) setting the structure and objective function of the discriminative classification network D and the generating network G, and the distance coefficient λ between the image generated by the generating network G and the real image; 2) obtaining the difference map of two images in different phases I D ; 3) for I D Divide and obtain the initial change detection result, and according to the result, divide the two different phases into labeled and unlabeled data to form a training set; 4) Use the discriminative classification network D and the generation network G to form a classification network W, and use The training set is trained on it, and the trained discriminant classification network D' is obtained; 5) Two different phase images are input into the discriminative classification network D' to obtain the final change detection result. The invention has the advantages of high detection accuracy and strong robustness, and can be applied to image understanding or pattern recognition.
Owner:XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products