1255 results about "Optical image" patented technology

The invention provides an underwater target identification method and system based on multi-source sensor data fusion. The method comprises the following steps: firstly, synchronously acquiring an original sound wave reflection signal and original optical image data of a target underwater area, then carrying out acoustic compensation processing on the original sound wave reflection signal to generate a target sound wave reflection signal, and meanwhile, carrying out optical compensation processing on the original optical image data to generate target optical image data; performing dynamic weighted fusion on the reliability measurement of the target sound wave reflection signal and the reliability measurement of the target optical image data through an adaptive fusion module to generate an enhanced multi-modal data set; and finally identifying the specific category of the underwater target through a multi-modal feature matching and decision-making mechanism. According to the technical scheme provided by the invention, the limitation of a single sensing mode is overcome, the quality of collected information is improved, the direct confirmation efficiency of common target recognition is also improved, and high accuracy and data reliability of target category recognition in a complex scene are ensured.

The invention discloses an electrostatic induction and optical imaging principle-fused online monitoring device and method for wear particles of a water-lubricated bearing, and belongs to the field of state monitoring of mechanical equipment. The device comprises a square insulation detection cavity, a detection electrode array, an electromagnetic shielding shell, a high-speed optical imaging module and a signal processing unit, the square insulation detection cavity is installed in a bearing lubrication water loop. The detection electrode array is fixed to the outer wall of the cavity and used for capturing electrostatic signals generated when the abrasion particles pass through. The electromagnetic shielding shell wraps the detection cavity and is grounded through a wire to eliminate environmental electromagnetic interference. The high-speed optical imaging module integrates a high-magnification microscope lens and a CMOS sensor, is coaxially mounted with the detection cavity, and obtains the morphology characteristics of the wear particles in real time; and the signal processing unit performs multi-modal data fusion analysis on the electrostatic signal and the optical image. Through cooperative detection of electrostatic induction and optical imaging, the monitoring precision and reliability of the wear particles of the water-lubricated bearing are remarkably improved.

The invention belongs to the technical field of geological disaster monitoring and early warning, and relates to a rainfall type landslide-debris flow chain disaster intelligent dynamic monitoring and early warning method, which comprises the following steps: data acquisition: generating multi-source data including an optical image, an SAR image, an unmanned aerial vehicle image and ground data; preprocessing the multi-source data; performing space-time registration, data format and organization on the multi-source data after data processing; key characteristic parameters are calculated, and data fusion is carried out; constructing a multi-dimensional feature vector, and generating a multi-dimensional feature image; constructing a risk assessment model by using a deep learning model, and performing real-time prediction; dynamically determining the total risk level of each area according to a preset comprehensive research and judgment rule by integrating the real-time prediction result; and when the total risk level reaches a'high risk 'or'extremely high risk' threshold value, generating early warning information, and performing early warning release. According to the invention, comprehensive, whole-process three-dimensional perception, dynamic and self-adaptive intelligent evaluation and disaster prediction are realized.

The invention belongs to the technical field of remote sensing image analysis, and provides a multi-source remote sensing building extraction method based on hybrid experts, electronic equipment and a storage medium. The method comprises the steps of basic model construction, two-way structure model construction, optical feature extraction, earth surface feature extraction, two-way feature fusion, ViT coding, feature injection and extraction and semantic alignment step-by-step up-sampling. According to the invention, a dual-path structure is adopted to assist the multi-scale encoder and the bidirectional attention fusion module, and DSM data and optical images are used for feature fusion, so that the capability of distinguishing buildings from backgrounds is improved; the hybrid expert LoRA structure is introduced into the ViT encoder, parameters of the feedforward neural network are dynamically adjusted, the adaptability and flexibility of the model to input features are further enhanced, and the calculation complexity is reduced.

The invention relates to the technical field of industrial vision, in particular to an aviation part crack detection and repair method which comprises the following steps: acquiring an aviation part optical image at a reference time point and an aviation part optical image at a to-be-detected time point; according to the method, logarithmic polar coordinate transformation is carried out on different time point images, rotation, scaling and translation parameters are extracted, an image registration relation is established, the structural consistency of time sequence images in a local area is enhanced, a structural tensor is constructed for each pixel neighborhood, the change characteristics of the dual-time-phase tensor are compared, a structural change saliency map is generated, and the structural change saliency map is obtained. Sensitive capture of a tiny deformation area is achieved, the responsiveness to an initial crack is improved, then a crack propagation interval is further refined into a main crack path in a self-adaptive threshold segmentation and skeleton extraction mode, the tip acutance of the crack is calculated in combination with tip contour information of a geometric boundary of the crack, and the initial crack is obtained. And quantitative support is provided for the crack danger degree.

The invention provides an injection molding part surface flaw detection method and device based on double-model collaboration, and the method comprises the steps: carrying out the local abnormal reflection feature analysis of a multi-view optical image collected on the surface of an injection molding part based on a first detection model, and obtaining a candidate flaw region; performing spatial positioning in the multi-view optical image based on the candidate flaw area to obtain a multi-view candidate image segment; performing surface geometric continuity analysis on the multi-view candidate image segments based on a second detection model to obtain a three-dimensional surface geometric consistency result; carrying out authenticity discrimination on the candidate flaw area based on a three-dimensional surface geometric consistency result to obtain a real flaw area; wherein the first detection model is used for capturing an optical response model of local abnormal reflection characteristics; the second detection model is a stereoscopic vision model for analyzing the geometric continuity of the multi-view lower surface. According to the invention, the false alarm rate of surface defect detection of the injection molded part under a complex surface condition is reduced.

The invention provides a tunnel three-dimensional geologic body modeling method and system based on in-hole camera shooting and while-drilling lithology perception, and relates to the technical field of tunnel and underground engineering and intelligent geological information processing.The method comprises the steps that firstly, a drill hole wall optical image sequence and while-drilling engineering parameters are synchronously collected and preprocessed respectively; then establishing a depth-time mapping relation to realize accurate alignment of the multi-source data in a depth domain; then fracture intelligent identification and parameter extraction are realized through an improved U-Net network, and lithology classification is completed by using an XGBoost model; feature level and decision level fusion is carried out on the fracture features and the lithologic features, and rock mass quality grades are generated; and finally, constructing an integrated geologic model fusing lithologic distribution and a three-dimensional fracture network by adopting an implicit modeling and discrete fracture network technology. According to the method, the problem of splitting of in-hole visual information and while-drilling physical information is solved, automation and precision of geological recognition are improved, and reliable geological information support is provided for tunnel construction safety and support design.

The invention discloses a comprehensive remote sensing recognition system for hidden danger of ice lake outburst. The system comprises a data acquisition and preprocessing module, an ice lake extraction module, an ice dam stability evaluation module, a risk calculation module and a visualization and early warning module. According to the system, optical images, SAR images, LiDAR point cloud and meteorological data are utilized, firstly, a glacial lake boundary is extracted through a water body index, the area and the volume are calculated, then the water level rising rate is monitored in combination with multi-temporal data, the dam body stability is evaluated by utilizing three-dimensional terrain and deformation parameters, and the dam body stability is evaluated by combining the temperature melting corrosion rate and triggering factors such as rainfall, earthquakes and inflow. And constructing a multi-factor outburst risk index model, and finally carrying out visualization and graded early warning on a result in a GIS platform. The method can achieve the quick, comprehensive and intelligent recognition of the hidden danger of ice lake outburst, has the advantages of being high in monitoring precision, high in automation degree, high in early warning timeliness and the like compared with a traditional single data or experience judgment method, and can be widely applied to the disaster prevention and control work of dense ice lake areas such as the Qinghai-Tibet Plateau and the Himalaya mountain.

The invention relates to the technical field of underwater target detection, in particular to a multi-modal underwater target detection method and system based on layered feature alignment. The method comprises the following steps: acquiring an underwater sonar image and an optical image; sonar and optical features are extracted through a double-flow backbone network; background noise is suppressed and key features are enhanced through a local enhancement module; decomposing the features into low-frequency and high-frequency components through a hierarchical alignment module, and establishing a cross-modal feature corresponding relation by using deformable convolution; multi-modal fusion features are generated through a fusion module; and target detection is carried out through the detection head. According to the method, the problem of feature misalignment caused by the difference between the underwater sonar and the optical image due to the imaging principle is solved, adaptive cross-modal feature alignment and efficient fusion are realized, and the precision and robustness of underwater target detection are remarkably improved.

The invention relates to the technical field of lithium battery cell online nondestructive testing, and discloses a lithium battery cell lamination process online quality detection method, which is used for solving the problems of high difficulty in real-time online identification of hidden defects in a lithium battery cell lamination process and high omission ratio in a traditional method. The method comprises the following steps: firstly, synchronously acquiring an optical image of the surface of a pole piece and an X-ray perspective image of an internal structure on a lamination production line to obtain a multi-modal image sequence, carrying out time sequence registration and space alignment fusion on the two types of images, and extracting a pole piece layer, a diaphragm layer boundary and a density abnormal region; according to the method, an S-shaped deformation template and an internal foreign matter template are combined to carry out mode comparison, three-dimensional coordinate positioning, density grading and severity marking are carried out on an abnormal area, a structured abnormal catalogue is fed back to a production line control system, technological parameters are adjusted in a linkage mode, online nondestructive testing and closed-loop regulation and control of hidden defects are achieved, and the production efficiency is improved. The omission ratio is reduced; and the consistency and the safety of the lamination process are improved.

The invention discloses an island shoreline erosion monitoring method and system based on image recognition, and the method comprises the steps: processing an optical image through meteorological data, obtaining a clear optical image, carrying out the multi-source feature fusion of the clear optical image and an SAR image, and obtaining a preliminary shoreline probability graph; carrying out fine extraction and image recognition on the initial shoreline probability graph according to the instantaneous tide level to obtain an island shoreline planar graph, carrying out image registration and constructing an island shoreline digital surface model, calculating a three-dimensional deviation field and quantifying an erosion index, calculating a driving factor, and determining a dynamic monitoring threshold according to the driving factor and a standard monitoring threshold. And carrying out island shoreline erosion early warning according to the erosion index and the dynamic monitoring threshold. The method not only can improve the efficiency and accuracy of island shoreline erosion monitoring, but also has good interpretability, and can be directly applied to an island shoreline erosion monitoring system.

The invention provides an optical image and LIBS detection area registration method and device, a medium and a program product, and the method comprises the steps: collecting an optical image, three-dimensional shape data and spectrum detection data of a to-be-detected sample, and building a sample space coordinate system based on the optical image and the three-dimensional shape data, the spectrum detection data is collected from a preset spectrum detection area on the surface of the to-be-detected sample; establishing a mapping relation between optical image pixel coordinates and LIBS laser focus coordinates in the sample space coordinate system; extracting image features of the optical image and spectral features of the spectral detection data, and fusing and updating the mapping relation based on the image features and the spectral features to obtain a registration result of the optical image and the spectral detection area; and performing superposition display on the optical image and the spectrum detection result aligned based on the registration result in a visual interface. According to the method, the influence caused by mechanical positioning errors, manual calibration deviations and sample morphology differences is effectively reduced, and the registration precision and robustness are improved.

The invention discloses a cutter state real-time monitoring and compensating method, system and equipment and a medium, and relates to numerical control precision machining. In the method, a cutting edge optical image, an acoustic emission signal time domain waveform, a vibration acceleration parameter and real-time temperature data of a cutting area of a cutter in the machining process are collected; measuring the maximum width and depth of a wear belt through an image to form a wear characteristic quantized value, and judging a wear over-limit state; judging the damage state based on the continuous ultralimit time of the instantaneous mutation rate of the acoustic emission signal; judging the abnormal vibration grade and state through vibration spectrum analysis; and inputting the vibration spectrum and the temperature data into a prediction model to obtain a position offset prediction quantity. And calculating a size deviation value according to a wear / damage state, calculating a coordinate offset according to vibration abnormity, generating a cutter geometric compensation instruction or a motion trail compensation instruction, and completing real-time compensation operation. According to the scheme, the fine abnormal change of the cutter in the machining process can be captured in time, and compensation is conducted according to the fine abnormal change.

The invention discloses a star map registration method based on a remote optical image, relates to the technical field of image processing, and solves the problems that the existing method is multi-oriented to a single telescope, most of the single telescope is aligned at a star point level, and the robustness is insufficient when parallax, distortion, optical difference and background pollution exist in remote multi-station imaging. The method comprises the following steps: acquiring a remote star map and extracting a star point centroid; angular distance calculation and triangle construction; registering the centroids of the star points in the whole image; performing similarity transformation and homography estimation; and carrying out sub-pixel refinement and full image registration. According to the invention, dual registration of star point centroids and pixel coordinates can be realized for star maps shot by a plurality of telescopes in different places, and meanwhile, a high-quality registration reference can be provided for subsequent three-dimensional information acquisition of a space target and identification and positioning of the space target.

The invention provides a degassing-free transformer oil monitoring device and method. A transparent accommodating pipe is used for being communicated with an external transformer oil supply device; the laser detection assembly is arranged on one side of the transparent accommodating tube; the voltage regulation and control unit is connected with the transparent accommodating tube; the imaging assembly is arranged on one side of the transparent accommodating tube and is used for acquiring optical image data of the Tyndall phenomenon in the transformer oil sample under different voltage conditions; the data processing unit is used for setting a segmentation point in the middle position of a Tyndall light pillar based on the Tyndall light pillar in the image data collected by the imaging assembly, determining a standard deviation according to the ratio of the total number of gray pixels on the left side and the right side of the Tyndall light pillar, and determining a threshold value of the Tyndall light pillar according to the relation between the standard deviation and a preset threshold value range. And judging the existence state and distribution characteristics of the gas in the transformer oil sample. Degassing treatment is not needed, the process is simplified, sample pollution is avoided, and the monitoring accuracy and stability of the gas in the transformer oil are remarkably improved.

According to the method, firstly, SAR data are mapped to an optical image domain by using a conditional diffusion model, pseudo-optical images with consistent spatial spectrums are generated, and fusion distortion caused by difference of SAR imaging mechanisms in a traditional method is overcome; secondly, a refined cloud region detection mechanism of a Fmask cloud mask is introduced, a cloud pollution region and a cloudless region are dynamically distinguished in combination with an adversarial training strategy, and the problem that the cloudless region is mistakenly changed in the reconstruction process of an existing method is effectively solved; besides, a multi-source integrated sample data set is constructed in stages, and a training normal form of multi-index joint optimization of PSNR, SSIM and the like is adopted, so that texture detail recovery and spectrum fidelity of a thick cloud coverage area are realized in a complex scene. In downstream application tasks such as land utilization classification and disaster dynamic monitoring, the visual quality and the quantitative index of the cloud removal result have good effects, and reliable technical support is provided for high-precision reconstruction of remote sensing information of a multi-cloud area.

The invention relates to the technical field of underwater target detection, in particular to a target recognition method and system based on a sonar image assisting an optical image. The method comprises the following steps: acquiring an underwater optical image and a sonar image, inputting the underwater optical image and the sonar image into a double-flow multi-scale feature extraction backbone network, and generating an optical multi-scale feature map and a sonar multi-scale feature map; processing the multi-scale feature map through an optical-sonar adaptive feature fusion module to generate enhanced multi-modal fusion features; inputting the multi-modal fusion features into a detection head, and outputting an underwater target detection result; according to the method, the problems of optical-sonar image modal isomerism and space mismatch are effectively solved, and the precision and robustness of underwater target detection are remarkably improved.

The invention relates to the technical field of semiconductor wafer defect detection, and discloses a semiconductor wafer defect detection method and system, and the method comprises the steps: generating a spatial staggered excitation pattern, and projecting the spatial staggered excitation pattern to the surface of a semiconductor wafer, the spatial staggered excitation pattern comprising an excited region and an unexcited region; capturing an optical image of the surface of the semiconductor wafer; according to the optical image, calculating the difference between the optical signal intensity of the excited area and the optical signal intensity of the adjacent non-excited area in the optical image; according to the difference, carrying out background deduction on the optical image so as to display a potential defect signal; and identifying the manifested potential defect signal. Therefore, the method can significantly improve the sensitivity, accuracy and efficiency of semiconductor wafer defect detection, thereby effectively improving the yield and reliability of semiconductor products, and reducing the production cost.

The invention discloses a crop harvesting progress monitoring method and system based on multi-source remote sensing data fusion and depth time sequence analysis, and the method comprises the steps: obtaining multi-source remote sensing image data of a to-be-monitored region, carrying out the standardization processing of the multi-source remote sensing image data, and obtaining the processed remote sensing image data; constructing a fusion cloud removal network, and performing fusion cloud removal on the processed remote sensing image data to obtain cloudless image data; performing space-time fusion on the cloudless image data by using an enhanced space-time adaptive reflectivity fusion model to obtain a continuous cloudless optical image sequence; constructing a depth time sequence classification model based on a convolutional neural network and a long-short term memory network, and inputting the continuous cloudless optical image sequence into the depth time sequence classification model to obtain a crop harvesting monitoring result; and performing spatial superposition on the crop harvesting monitoring result and the field piece vector boundary data of the to-be-monitored area to obtain a harvesting progress diagram of the to-be-monitored area.

The invention relates to the technical field of fault identification, in particular to a three-dimensional fault occurrence intelligent identification method and system based on multi-source remote sensing, and the method comprises the steps: obtaining a high-resolution optical image, a penetrating radar profile and gravity gradient data of a target region, and generating a three-dimensional geological response body fusing earth surface and underground information; inputting the three-dimensional geological response body into a vertical adaptive enhancement module, and constructing a unified structured fault feature tensor; and inputting the fault feature tensor into a dynamic curvature constrained curved surface reconstruction module to generate a fault space curved surface, and resolving trend, tendency and dip angle change functions of the curved surface at different depths. According to the three-dimensional fault occurrence intelligent identification method based on multi-source remote sensing, the high-resolution optical image, the penetrating radar profile and the gravity gradient data are fused, a structured three-dimensional geological response body is constructed, the cooperative expression ability of earth surface-underground fault information is remarkably improved, and the fault occurrence identification accuracy is improved. And high-fidelity modeling of complex fault bending and abrupt change areas is realized.

The invention discloses a high and cold slope disaster body segmentation method fusing optical and SAR images, and the method comprises the following steps: 1, carrying out the snow coverage normalization processing based on the visible light green light wave band and the short wave infrared wave band of an optical image, and generating an ice and snow mask through an expectation maximization algorithm and a Gaussian mixture model; 2, preprocessing the optical image and the SAR image; step 3, constructing a high and cold slope disaster body segmentation model based on a Transform network; 4, training the segmentation model by using Dice loss and cross entropy loss in a combined manner, and freezing parameters of an image encoder in the training process; and step 5, inputting the high and cold slope remote sensing image into the trained segmentation model, and outputting a segmentation result of the slope disaster body by the segmentation model. According to the method, the problems of large ice and snow interference and poor multi-source data collaboration in high and cold slope disaster body segmentation are solved, and the segmentation precision and the engineering applicability are improved.

The invention provides a geological disaster early warning method and system based on a multi-temporal remote sensing image, and relates to the technical field of geological disaster monitoring, and the method comprises the steps: collecting a multi-temporal SAR image and a multi-temporal multispectral optical image of a target region, and carrying out the standardization processing; performing super-resolution reconstruction and registration on the standardized image to generate a multi-modal remote sensing data cube; inputting the multi-modal remote sensing data cube into a pre-trained deep learning model, performing inversion and outputting a physical parameter diagram; dynamically calibrating parameters and boundary conditions of a three-dimensional geomechanical model pre-constructed for the target area based on the physical parameter map, and predicting and generating a spatio-temporal evolution diagram and critical instability time by using the dynamically calibrated three-dimensional geomechanical model; and performing uncertainty fusion analysis on the physical parameter diagram, the spatio-temporal evolution diagram and the critical instability time, and generating dynamic grading early warning information according to a fusion analysis result, thereby realizing more accurate and timely geological disaster early warning.

The invention discloses a modal fusion method of camera-sonar equipment under the condition of unknown external parameters, and relates to the field of underwater multi-sensor data fusion. The method comprises the following steps: firstly, acquiring synchronous underwater optical images and sonar images, and converting sonar polar coordinate imaging data into a three-dimensional point cloud under a sonar coordinate system through a geometric model; then, under the condition that camera-sonar external parameters do not need to be calibrated in advance, a spatial transformation matrix between a camera coordinate system and a sonar coordinate system is automatically estimated and calibrated through the corresponding relation between images and target features in point clouds, and alignment fusion of two kinds of modal data is achieved. According to the method, optical and acoustic information can be effectively fused in a severe water quality environment, the sensing limitation of a single sensor is made up, the robustness and accuracy of underwater dam crack and other target detection are improved, and the method has the advantages of no need of manual calibration and high adaptability.

The invention belongs to the technical field of a method for automatically extracting a specific target in a complex landscape, and particularly relates to a method for automatically extracting a specific target in a complex landscape based on multi-source remote sensing time series data, which comprises the following steps of: acquiring multi-source remote sensing time series data, preprocessing the multi-source remote sensing time series data, and constructing a Pheno-ViT model; the Pheno-ViT model comprises a backbone network, a phenology sensing module and a feature fusion module, the backbone network adopts a SwinTransform architecture, the SwinTransform architecture comprises four feature extraction stages, multi-scale spatial feature extraction is sequentially executed in each stage, the phenology sensing module adopts a bidirectional GRU network and is used for dynamically generating attention weights of all time steps to model crop growth time sequence features, and the feature fusion module adopts a cross-modal attention mechanism and is used for carrying out feature extraction on the crop growth time sequence features. The image fusion module is used for fusing the Sentinel-2 optical image features and the Sentinel-1 SAR image features, and the decoder adopts four up-sampling stages and is used for realizing spatial resolution reconstruction and outputting a non-grain crop feature map.

The invention discloses a visual tactile sensor based on a magnetic imaging principle. The visual tactile sensor comprises a shell, an image acquisition module, a magnetic pole display film, an elastic body and a magnetic film, the magnetic pole display film, the elastic body and the magnetic thin film are arranged in the shell from top to bottom, and the image acquisition module is located above the magnetic pole display film and used for acquiring an image of the magnetic pole display film; when the sensor is used for pressure sensing, the position with the maximum gray level variation of the magnetic pole display film image is the pressure acting position, and the pressure is equal to the result that the gray level variation of the magnetic pole display film image is divided by the magneto-optical conversion coefficient of the magnetic pole display film and the product thereof. The magnetic induction intensity in the center range of the surface of the magnetic film, the initial distance between the magnetic film and the magnetic pole display film and the equivalent elastic coefficient of the magnetic film and the elastic body are related. The sensor converts a mechanical signal into a magnetic field signal and then converts the magnetic field signal into an optical image, high-sensitivity sensing of tiny pressure is achieved, and meanwhile the sensor has the higher signal-to-noise ratio, stability and anti-interference capacity.

The invention relates to the technical field of underwater target detection, in particular to an underwater image target detection method and system based on multi-modal fusion. The method comprises the following steps: acquiring an underwater optical image and sonar image pair and a trained underwater multi-mode target detection network; inputting an image pair into the network, and respectively extracting multi-scale features of an optical mode and a sonar mode through a double-branch backbone network; a cross-modal feature offset is calculated by using an attention mechanism and a confidence mask through a multi-modal feature alignment module, and spatial adaptive alignment of acousto-optic features is realized; a multi-head zoom dot product attention and parallel double-gating structure is adopted through a cross-modal feature fusion module, bimodal complementary features are adaptively screened and fused, and target feature representation is enhanced; and the fused features are sent to the detected neck and head to complete target classification and positioning. According to the method, the problems of underwater acousto-optic mode space dislocation and imaging difference are solved, and the precision and robustness of target detection in a complex underwater environment are improved.

The invention relates to the technical field of image detection, and discloses an industrial part defect detection method based on multi-scale feature fusion, which comprises the following steps of: dividing a surface optical image into a plurality of image blocks which are not overlapped with each other by taking the geometric center of a part as a reference; performing feature upsampling on the deep feature map of each image block to obtain a semantic enhancement feature map, and performing channel re-calibration on the semantic enhancement feature map based on the channel attention weight of the middle-layer feature map to generate a semantic guidance feature map; performing multi-scale fusion on the deep-layer feature map, the semantic guidance feature map and the middle-layer feature map; analyzing the rotation direction between the fusion feature map of each image block and the defect prior feature vector, and executing multi-angle rotation alignment operation with the center of the industrial part to be detected as the circle center on each image block; and fusing the defect detection results of all the image blocks to obtain a pixel-level defect classification and positioning map of the part. The industrial part defect detection accuracy can be improved.

An actuator arrangement for use in a camera is disclosed. The camera comprises two or more camera elements including an image sensor and one or more optical elements for forming, or aiding forming of, an image of an object on the image sensor. The actuator arrangement comprises: a first part defining a first axis; a first actuator for providing a first type of movement of one or more of the camera elements relative to the first part; a second actuator for providing a second, different type of movement of one or more of the camera elements relative to the first part; a controller configured to (a) cause the first actuator to move one or more of the camera elements so as to provide a first optical image stabilisation (OIS) effect, and (b) cause the second actuator to move one or more of the camera elements so as to provide a second OIS effect. The first and second OIS effects combine to provide an overall OIS effect that is greater than either of the first and second OIS effects.

The invention provides a forest carbon reserve prediction method, device and equipment based on forestry carbon sink monitoring, and relates to the technical field of data analysis. According to the method, firstly, a forest optical image and climate-related data are acquired, and the forest optical image at least comprises a red light band and a near-infrared band; secondly, extracting an optical global semantic vector from the forest optical image, and performing semantic constraint on the optical global semantic vector based on growth condition semantic information in the forest optical image to form an optical growth semantic vector; then, a climate global semantic vector is extracted from climate related data; thirdly, performing semantic fusion on the optical growth semantic vector and the climate global semantic vector to obtain a forest global semantic vector; and finally, performing semantic reduction based on the forest global semantic vector to form a carbon reserve prediction result. Based on the above content, the problem that the reliability of forest carbon reserve prediction is relatively low in the prior art can be improved.

The invention provides a deep learning landslide identification method and system fusing optical and SAR remote sensing data, and relates to the field of geological disaster monitoring and identification, and the method comprises the steps: obtaining an optical image and an SAR image of a target region, carrying out the registration, generating an optical-SAR image pair, and generating a corresponding binary label map for the optical-SAR image pair; constructing a to-be-trained landslide recognition model, constructing a data set by the optical-SAR image pair and the corresponding binary label graph, and training the to-be-trained landslide recognition model by using the data set to obtain a trained landslide recognition model; and inputting an optical-SAR image pair of a to-be-identified area into the trained landslide identification model, and outputting a landslide identification result graph of the to-be-identified area. According to the invention, the limitation of a single remote sensing data source in landslide identification in the prior art is overcome, and the landslide identification precision in a complex environment is improved.