408 results about "Cloud detection" patented technology

In an embodiment, a system, device and method for detecting a malicious attack is described. Herein, the system includes a security network device that conducts an analysis on received network traffic to detect a suspicious object associated with the network traffic and determine an identifier associated with a source of the suspicious object. Both information associated with the suspicious object and ancillary data, including information that identifies a return path for analysis results to a customer, are uploaded to a detection cloud. The detection cloud includes provisioning logic and one or more virtual machines that are provisioned by the provisioning logic in accordance with at least a portion of the ancillary data. The provisioning logic to customize functionality of the detection cloud for a specific customer.

A computerized aircraft system, such as an unmanned aircraft system (UAS) is provided with a cloud detection system. The UAS includes a monocular electro-optic or infra-red camera which acquires consecutively, in real time, a plurality of images within a field of view of the camera. The system identifies feature points in each of the consecutive images, and generates macro representations of cloud formations (3D representations of the clouds) based on tracking of the feature points across the plurality of images. A cloud avoidance system takes in nominal own-ship waypoints, compares those waypoints to the 3D cloud representations and outputs modified waypoints to avoid the detected clouds.

A system for detecting clouds and cloud shadows is described. In one approach, clouds and cloud shadows within a remote sensing image are detected through a three step process. In the first stage a high-precision low-recall classifier is used to identify cloud seed pixels within the image. In the second stage, a low-precision high-recall classifier is used to identify potential cloud pixels within the image. Additionally, in the second stage, the cloud seed pixels are grown into the potential cloud pixels to identify clusters of pixels which have a high likelihood of representing clouds. In the third stage, a geometric technique is used to determine pixels which likely represent shadows cast by the clouds identified in the second stage. The clouds identified in the second stage and the shadows identified in the third stage are then exported as a cloud mask and shadow mask of the remote sensing image.

The invention relates to an intelligent cloud-detection service system and an intelligent cloud-detection service method for vehicle conditions. The intelligent cloud-detection service system comprises a cloud server and an on-board terminal; the onboard terminal is used for acquiring vehicle basic blow-off parameters and vehicle component running state parameters through multiple OBD(on-board diagnostics) sensors, acquiring vehicle location information through a GPS (global positioning system) module and sending the information to the cloud server; the cloud server is used for receiving the vehicle basic blow-off parameters, the vehicle component running state parameters and the vehicle location information, performing comparison according to stored reference data of vehicles in different types, sending abnormal signals when judging that the vehicles are in abnormal running, generating corresponding fault guide information according to the location information of the vehicles and stored information of maps and garages, and releasing the information to the on-board terminal finally. The on-board terminal is used for acquiring data of the vehicle conditions and uploading the data to the cloud server, the cloud server generates the abnormal signals and the fault guide information to the on-board terminal to remind users when detecting the abnormal vehicle conditions, and thus, the users can do analysis to vehicles in different types and make response in time.

The invention discloses a retrieval method for an aerosol optical thickness based on high resolution satellite image data. The retrieval method specifically comprises the following steps: 1) establishing a lookup table according to a 6S radiation transfer model; 2) carrying out high resolution data preprocessing, comprising radiometric calibration, geometric correction and cloud detection, acquiring original apparent reflectance and observation angle information, and acquiring atmospheric parameters according to the observation angle information and the lookup table; 3) calculating the normalized differential vegetation index of each pixel, and determining a red-blue wave band relation corresponding to each pixel according to the vegetation index and priori knowledge provided by the invention; and 4) inverting the aerosol optical thickness according to the satellite observed apparent reflectance, the atmospheric parameters and the red-blue wave band relation. According to the remote sensing retrieval method for the aerosol optical thickness disclosed by the invention, aerosol monitoring can be carried out on high solution satellites effectively, and a data source can be provided for regional and urban atmospheric environment and pollution.

The present invention provides an automatic cloud detection method and system for a multi-spectral remote sensing satellite image. The method comprises: preparing data; roughly extracting clouds; extracting texture information on an image intensity information channel by combining histogram equalization and bilateral filtering; segmenting a texture information map by using a two-dimensional Otsu threshold; removing an error from a rough detection result by using a binary detail map after segmentation; using intensity information of a raw image as a guide map; and based on the rough detection result with the error being removed, performing accurate extraction on the clouds through edge seed expansion. The technical scheme actually realizes automatic, fast, and accurate detection of cloud.

A system for detecting clouds and cloud shadows is described. In one approach, clouds and cloud shadows within a remote sensing image are detected through a three step process. In the first stage a high-precision low-recall classifier is used to identify cloud seed pixels within the image. In the second stage, a low-precision high-recall classifier is used to identify potential cloud pixels within the image. Additionally, in the second stage, the cloud seed pixels are grown into the potential cloud pixels to identify clusters of pixels which have a high likelihood of representing clouds. In the third stage, a geometric technique is used to determine pixels which likely represent shadows cast by the clouds identified in the second stage. The clouds identified in the second stage and the shadows identified in the third stage are then exported as a cloud mask and shadow mask of the remote sensing image.

The invention discloses a remote sensing image cloud detection method based on a convolution nerve network, comprising steps of establishing a training sample set, generating a convolution nerve network classification model, extracting a super-resolution sub-area, generating a cloud probability graph, performing rough detection on a cloud area, and performing fine detection on the cloud area. Through the above arrangement, the remote sensing image cloud detection method can accurately detect the cloud area in the remote sensing image, and, for the remote sensing image having the complex background or the semitransparent cloud, can obtain a better detection result. As a result, the remote sensing image cloud detection method can solve problems of false determination and analysis which are caused by the cloud, and can facilitate the follow-up processing and analysis. The remote sensing image cloud detection method enables the cloud area in the cloud detection result to have a better rim, to have better robustness in a complex environment and can obtain a better detection result.

The invention discloses a high-spectrum automatic cloud detection method based on space and spectral information, which can be applied to automatic cloud judgment of aerospace and aviation hyperspectral remote sensing images, is capable of reducing storage cost of hyperspectral remote sensing data and saving transmission bandwidth. The high-spectrum automatic cloud detection method comprises the following steps of: carrying out preprocessing and waveband selection according to spectral samples of cloud, snow, water and the like and then carrying out characteristic extraction; carrying out sample training by adopting a classifier to obtain a cloud spectral classifying model; in a hyperspectral image cloud detection stage, classifying each pixel of hyper-spectrums through preprocessing, waveband selection and characteristic extraction which are same in a training stage; and checking consistency of pixels and neighborhood pixels, finally determining whether the pixels are cloud pixels, and working out the proportion of the cloud pixels and giving a cloud judgment result. By the high-spectrum automatic cloud detection method, in conjunction with image segmentation, target classifying identification and machine learning technologies, the problem of hyperspectral cloud judgment is solved and the defect of low detection rate caused by only utilizing textural information or spectral information can be avoided.

A foundation cloud measuring method combining infrared and lasers comprises the following steps that (1) atmosphere downward infrared radiation data are obtained through an uncooled infrared focal planar array sensor, zenith backward extinction coefficient profile data are obtained through a laser sensor, and the obtaining time of the atmosphere downward infrared radiation data is synchronous with the obtaining time of the zenith backward extinction coefficient profile data; (2) water vapor and aerosol radiation under cloud are estimated by combining the data, clear sky threshold values calculated through a radiation transmission pattern are used for conducting initial cloud detection, it is assumed that the cloud is a black body, and the cloud base height is obtained through inversion; (3) sequence analysis is conducted on infrared radiation images with high time resolution, the clear sky threshold values are combined to conduct further cloud detection, and the cloud cover is calculated; (4) proportionality coefficients between the cloud base height obtained through the infrared radiation inversion and the cloud base height obtained through laser measurement are fitted; (5) the cloud base height of a whole view field is corrected, and the typical cloud base heights of every ten minutes are obtained through calculation.

The invention relates to a day and night cloud detection method based on static satellite multichannel data. The day and night cloud detection method comprises the steps: S1, preprocessing data, and generating throughout-the-year month-by-month clear sky background traced drawing data; S2, performing day and night judgment on a current image one-by-one pixel, and carrying out detection by a corresponding detection algorithm. By a multi-step cloud detection algorithm, visible light and thermal infrared band information are comprehensively used, so that the probability of mis-judgment is reduced; cloud detection can be quickly, accurately and stably realized on the earth surface of which the underlying surface is covered by ice snow, desert and vegetations, and high adaptability is achieved. The invention also provides a day and night cloud detection device based on static satellite multichannel data.

The invention discloses a remote sensing image cloud detection method based on a multi-scale fusion semantic segmentation network, and belongs to the technical field of remote sensing image cloud detection. According to the invention, the problem of low cloud detection precision of an existing method for carrying out cloud detection by manually extracting features is solved. The method comprises the following steps of extracting shallow features by using the first three levels of sub-networks; extracting deep features by using the last two stages of sub-networks; fusing the extracted deep features with the shallow features; thus, fully using rich detail information contained in shallow features and rich semantic information contained in deep feature. Therefore, the advantages of the deepfeature boundary and the shallow feature boundary are fused. Segmentation of the deep feature boundary is finer. The best cloud detection effect is achieved by optimizing the proportion of the deep feature to the shallow feature, and the cloud area detection error is smaller than 1%. The method can be applied to the technical field of remote sensing image cloud detection.

According to an example, an address of a web page to be identified is obtained, data of the web page from the address of the web page is crawled, the data of the web page is parsed and data for identification is obtained. The web page determined as malicious information according to the data for the identification, and the malicious information is intercepted.

The invention provides a cloud detection method of an optic remote sensing image, which comprises the following steps of: 1) diving an optic remote sensing image into basic processing units; 2) diving the basic processing units into two types which are possible to be cloud or not to be cloud according to a gray threshold; 3) diving the basic processing units which are possible to be the cloud according to fractal dimension; and 4) judging an undetermined unit in a fractal dimension dividing result to be a cloud layer or an earth object material according to angle second moment. The method combines with three judging characteristic parameters according to a reasonable order, and the different characteristic parameters have different functions when detecting, thereby not only being capable of obtaining higher resolution precision, but also being capable of obviously improving the running efficiency thereof in average meaning.

The invention discloses a ground terahertz radar system for detecting a cloud. The system comprises a terahertz transmitting module, a terahertz receiving module, a terahertz transmitting-and-receiving antenna module, a terahertz signal processing module and an upper computer module; the center frequency of a terahertz signal transmitted by the terahertz transmitting module is 220 GHz, the work bandwidth is 5 GHz, the transmitting power is 200 mW, the pulse width is adjustable ranging from 100ns to 3mus and the adjusted step length is 100ns, and the pulse repletion frequency is adjustable ranging from 1KHz to 10KHz and the adjusted step length is 1KHz. Compared with a laser radar and a millimeter wave radar, the ground terahertz radar system for detecting the cloud utilizes a set of parameters applicable to the cloud detection and is capable of penetrating into a thin cloud and an extremely thin cloud to carry out the three-dimensional structure detection for the cloud, and therefore not only a macrostructure such as the cloud thickness, the cloud height, the number of cloud layers, the vertical section variance of the cloud can be obtained, but also a microstructure such as the size, the shape, and the ice water content of a cloud particle can be obtained.

The invention relates to an intelligent information extraction method and system based on remote sensing image. Firstly, the remote sensing big data GPU computing cluster based on Hadoop is constructed, then the decompression of remote sensing image is designed, high-precision cloud detection, panchromatic multispectral image automatic fusion, RPC image correction, intelligent information extraction method and process for intelligent extraction of ground object information and vectorization of geographic element information, in which the intelligent information extraction platform adopts Caffedeep learning framework, a high-precision cloud mask product of remote sensing image can be obtained through the above process, panchromatic multi-spectral band fusion products, RPC ortho correctionproducts, intelligent extraction products of ground object information and geographic element information vectorization products realize the goal of automatically converting 1A-level original remote sensing images into 2A-level products, which greatly shortens the time from satellite standard data products to information products.

The invention provides a method and a system for the security detection and repair of a wireless network. The method for the security detection and repair of the wireless network comprises the following steps: detecting the network configuration of the wireless network and sending a security detection request to a cloud detection side server by a client-side, wherein the detection result of the network configuration is carried in the security detection request; determining the security grade corresponding to the wireless network of the client-side according to the detection result and set security grade judgment rules and sending the determined security grade to the client-side by the cloud detection side server, wherein the security grade judgment rules comprise: if a DNS (Domain Name Server) conforms with a first DNS security rule, the security grade of the DNS is dangerous; if the DNS conforms with a second DNS security rule, the security grade of the DNS is secure; if the DNS conforms with a third DNS security rule, the security grade of the DNS is warning; repairing the network configuration of which the determined security grade is dangerous or warning by the client-side. Through the method and the system, the security risk of the DNS is inhibited and changed.

The present invention discloses a satellite remote sensing image cloud amount calculation method on the basis of random forest. The satellite remote sensing image cloud amount calculation method on the basis of random forest comprises six steps: sample acquisition, feature extraction, image classifier training, segmentation of image to be measured, image classification, cloud amount calculation and the like. Through adoption of the method provided by the invention, multiple detections may be performed after training just once, an image classifier is obtained through a large number of image trainings, and the image classifier may be used again when cloud detection is performed. The random forest algorithm is low in time complexity at the prediction classification stage, and the cloud zone detection may be rapidly carried out. Through the test, the method provided by the invention is applicable to panchromatic images (ten-dimensional characteristic vector) and also applicable to n-channel multispectral images (10n-dimensional characteristic vector), and has been applied to an actual quality control system of satellite image products, so that the cloud detection of remote sensing images of multiple domestic satellites such as the resource satellite-3, mapping satellite-1, GF-1 and the like are performed, wherein the accuracies reach, respectively, 91%, 88% and 92.4%.

The invention discloses a cloud and aerial total cloud amount detection method and system. The system comprises an image obtaining device, a sky type confirming module, a cloud detection module and an aerial total cloud amount computing module, wherein the image obtaining device is used for obtaining an aerial cloud picture at a preset moment, the sky type confirming module is used for confirming the type of the sky at the preset moment, the cloud in the cloud picture is detected through the cloud detection module according to partition threshold values, and the aerial total cloud amount computing module is used for computing the aerial total cloud amount according to the ratio of the cloud in the aerial cloud picture to the whole aerial cloud picture. The cloud in the cloud picture is detected through the aerial cloud picture partition threshold values corresponding to the different sky types, the influences of different weather conditions on the detection result of the aerial cloud picture are taken into full consideration, and the accuracy of the cloud detection is made to be higher.

The invention relates to a cloud detection method of virus and malware of a mobile phone based on a communication network, comprising the following steps: step (10), acquiring the flow rate of a to-be-detected mobile phone of a mobile phone user; step (20), analyzing the inflow rate by an active cloud detection module and judging whether the inflow rate conforms to a recognizable flow rate mode; step (30), transferring unrecognizable flow rate to a cloud gathering end module in real time, then transferring the unrecognizable flow rate to a cloud analysis engine module which utilizes virus library of a mobile phone virus centralized management system for analyzing; step (40), feeding back an analysis result to the active cloud detection module by the cloud analysis engine module, and storing the analysis result in a processing database module through the active cloud detection module; step (50), acquiring outflow rate of the mobile user to be detected; and step (60), analyzing the outflow rate according to a real-time infection user monitoring module, and then storing an analysis result in the processing database module.

One embodiment relates to an apparatus for in-the-cloud identification of spam and / or malware. The apparatus includes computer-readable code configured to be executed by the processor so as to receive queries, the queries including hash values embedded therein. The apparatus further includes computer-readable code configured to be executed by the processor so as to detect a group of hash codes which are similar and to identify the group as corresponding to an undesirable network outbreak. Another embodiment relates to an apparatus for in-the-cloud detection of spam and / or malware. The apparatus includes computer-readable code configured to be executed by the processor so as to receive an electronic message, calculate a locality-sensitive hash based on the message, embed the locality-sensitive hash into a query, and send the query to a central analysis system via a network interface. Other embodiments, aspects and features are also disclosed.

The invention provides a deep learning remote sensing cloud detection method based on Gabor transformation and an attention mechanism, and solves the problem of insufficient feature extraction in remote sensing image cloud detection. The method comprises the following implementation steps: establishing a remote sensing image database and a corresponding mask map; constructing a convolutional neural network comprising a Gabor transformation module and an attention module; determining a loss function of the network; inputting a training sample in the training image library into the convolutionalneural network, and iteratively updating the loss function through a gradient descent method until the loss function converges to obtain a trained convolutional neural network; and inputting the datain the test database into a convolutional neural network to obtain a detection result of the cloud area. According to the invention, the image feature extraction technology based on Gabor transformation and an attention mechanism is adopted, a deep learning method is used for cloud detection of the remote sensing image, feature extraction is sufficient, detection precision is high, and the methodis used for the preprocessing process of the remote sensing image.

The invention relates to an aerosol optical thickness inversion method based on remote sensing data. The aerosol optical thickness inversion is conducted by the dark-object method and a 6S radiation transfer model. The aerosol optical thickness inversion method comprises data acquisition, data synthesis, angle data synthesis, cloud detection, aerosol inversion, aerosol type determination, surfacereflectivity determination, distribution map production based on AOD of the inversion, and relationship between AOD and PM2.5 establishment. MODIS AOD data obtained based on the method can be used asan effective supplementary means for ground monitoring of PM2.5 concentration.

A wearable lower limb movement correcting system based on cloud detection comprises a lower limb movement state acquiring module, a data transmission module, a movement state information visualizationand three-dimensional human body posture reappearance module arranged on a mobile terminal and a data processing module including a cloud platform, wherein the lower limb movement state acquiring module is connected with the data transmission module through a bus and transmits sensor signals, the data transmission module receives the sensor signals, sorts, integrates and packs formats, then is connected with the movement state information visualization and three-dimensional human body posture reappearance module in a wireless way and transmits movement postures and muscle force state data, the movement state information visualization and three-dimensional human body posture reappearance module transmits the data to a cloud platform through a network in real time so as to perform big datatraining and storage based on a database, and the data processing module transmits trained and processed three-dimensional human body posture and gait analysis data back to the mobile terminal througha wireless network so as to display action correcting information.

The invention is suitable for the technical field of cloud detection and provides a method, device and system for task operation processing. The method comprises the steps of submitting task operation in a cloud detection system; detecting task types of task operation, and enabling the task types to comprise a cluster task type and a trans-cluster task type; if the task type is the cluster task type, utilizing a preset cluster scheduler in the cloud detection system to process the task operation with the task type being the cluster task type; and if the task type is the trans-cluster task type, utilizing a preset trans-cluster scheduler in the cloud detection system to process the task operation with the task type being the trans-cluster task type. The cluster task type is a type of utilizing one cluster to process the task operation, and the trans-cluster task type is a type of utilizing at least two clusters to process the task operation. The conditions that the system collapses easily are avoided, and system stability and task processing efficiency are improved.

The invention relates to the field of remote sensing detection, in particular to a remote sensing image cloud detection method and device based on a full convolutional neural network. The method comprises the steps of selecting an RGB waveband of a wind cloud meteorological satellite remote sensing image to construct a data set, and obtaining a training set in the data set; constructing an SP-HRNet network model, wherein the network model comprises a continuous and parallel multi-resolution sub-network, a repeated multi-scale fusion module and a depth separable convolution combination module;inputting the training set into a network model for training to obtain parameters of the network model, and forming a network parameter model; and performing remote sensing image cloud detection by using the network parameter model. According to the method and the device, the sub-networks with multiple resolutions can be kept all the time, so that information is not lost in the feature extractionprocess of the image, the network depth is deepened, the depth separable convolution is combined, the feature extraction capability of the network is improved, the detail information of a detection result is enriched, and the cloud detection precision is improved.

The embodiment of the invention discloses a point cloud detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring multiple frames of point clouds and multiple frames of original image data which face the same visual range and are acquired at the same time; respectively projecting the multiple frames of point clouds onto the multiple frames of original image data to obtain multiple frames of target image data; performing semantic segmentation on point clouds and pixel points in the target image data according to the time sequence relationship among the multiple frames of target image data so as to identify the semantic information of the pixel points for the obstacle; and endowing the semantic information of the pixel points with point clouds corresponding to the pixel points. The visual features of the image data are combined with the spatial features of the point cloud, the target image data not only contains rich color features and texture features, but also contains the coordinates of the point cloud, the laser intensity and other features, the dimensionality of the features is greatly enriched, and semantic segmentation is carried out by considering the time sequence between frames, so that the accuracy of semantic information of an obstacle is improved.

The invention discloses a cloud determination method and a system for remote sensing satellite images. The method includes: receiving remote sensing satellite image data; performing format-removing processing of the remote sensing satellite image data; according to a preset data sharding rule, partitioning the remote sensing satellite image data after format-removing processing, and obtaining a plurality of sub-image data; and with the combination of texture features of visible light images, conducting cloud detection of each sub-image data by employing a classifier of a support vector machine in order to recognize a cloud mask in the remote sensing satellite image data. According to the method and the system, compared with cloud mask recognition of multi-spectrum images in the remote sensing satellite images in the prior art, cloud mask recognition is realized by employing the classifier of the support vector machine with the combination of the remote sensing satellite images and the texture features of the visible light images, the accuracy of the scheme can be effectively guaranteed via a general and engineering design, the cloud mask and other target substances such as snow and sand are effectively distinguished and classified, and the recognition rate can be high.

The invention belongs to the technical field of atmospheric remote sensing, and discloses a method for estimating a near-surface atmospheric temperature by using thermal infrared data of a geostationary meteorological satellite. The satellite is used for observing brightness temperature, meteorological station and numerical prediction model data to obtain a representative thermal infrared observation brightness temperature and near-surface atmospheric temperature; satellite cloud detection products are used for obtaining matched data sets for the observation brightness temperature, the stationactually measured temperature and auxiliary data under cloudless conditions; based on a stepwise regression method, the relationship between the radiation temperature of satellite observation, atmospheric pressure, relative humidity, a satellite observation angle, Julian daily parameters and the like and near-surface atmospheric temperature is analyzed, and key factors used for estimating the atmospheric temperature are determined; and a inversion model of near-surface temperature estimation is constructed by using a neural network technology. The method can realize the purpose of inversion of the near-surface atmospheric temperature under the clear sky condition of the thermal infrared data of the stationary meteorological satellite.