94 results about "Terrain classification" patented technology

The invention relates to the technical field of land resource management, in particular to a land natural resource dynamic supervision system and method. The method comprises the following steps: carrying out multi-source data acquisition and preprocessing on a land natural resource area to obtain an initial data set; performing intelligent land classification processing according to the initial data set to obtain a land classification map; performing change detection graph extraction according to the land classification graph to obtain a change detection graph; constructing a three-dimensional land resource model according to the change detection graph to obtain the three-dimensional land resource model; and performing early warning trigger processing according to the three-dimensional land resource model and the change detection graph, and pushing resource supervision information so as to realize a dynamic supervision task of the land natural resources. According to the land natural resource dynamic supervision method based on multi-source data, deep learning, time sequence analysis and three-dimensional modeling, automation, intellectualization and dynamics of land resource supervision are achieved.

The invention belongs to the technical field of remote sensing semantic segmentation information extraction, and particularly relates to a remote sensing image land classification method based on SAM multi-order fine tuning. According to the method, remote sensing multi-classification precision and generalization ability can be improved. Firstly, a sample data set is constructed through visual interpretation based on domestic high-resolution series images; on the basis, a network is designed by utilizing the strong feature extraction capability of an SAM encoder, a domain offset adaptation module and a deep low-rank adaptation module are designed, a mask generation part of an original SAM is improved, and three-stage adaptation fine adjustment is performed on the SAM, so that the feature extraction capability of the network on a remote sensing image is enhanced, and the model performance is improved. In application, the remote sensing land utilization coverage multi-classification technology with practical value is obtained so as to practically promote application and development of a large model in remote sensing image semantic segmentation multi-classification.

The embodiment of the invention provides an AI analysis method and system applied to land resource investigation, and the method comprises the steps: obtaining the multi-source remote sensing image data of a target region, analyzing the spectrum and texture features of the multi-source remote sensing image data, generating a comprehensive land feature map, obtaining an initial land classification map through a land classification model, and obtaining the initial land classification map. And performing time sequence comparative analysis in combination with historical data to determine a dynamic area of land coverage change and generate a land resource change report. The method further comprises the functions of soil quality evaluation, change area visualization, abnormal area real-time monitoring, land classification model training, classification model adjustment according to user feedback and the like, and the efficiency and accuracy of land resource investigation are improved.

The invention discloses an SAR image and optical image deep fusion ground object classification method based on self-supervised learning, and aims to solve two challenges in remote sensing image classification: firstly, reducing dependence on a large amount of label data, and secondly, improving multi-modal data classification precision. The modal features of an SAR image and an optical image are extracted through independent network branches, deep feature extraction is performed in combination with a convolutional neural network and a double-branch structure of an attention mechanism, and unique advantages and complementary information of the two modals are fully utilized. By constructing a self-supervised learning loss function, the model is trained without label data; then, the trained feature encoder is migrated to a downstream ground feature classification task, and only a small number of marked samples are used for fine adjustment of the model; according to the method, complementary information among different modes is integrated, dependence on manual annotation of remote sensing images is reduced through a self-supervised learning method, and the precision and robustness of ground feature classification are improved.

The invention discloses a terrain classification method based on a random forest algorithm, a server and a storage medium, and belongs to the technical field of terrain classification, and the method comprises the steps: obtaining DEM data and remote sensing image data of a research area, and extracting terrain features, spectral features, index features and texture features; designing a feature combination scheme, and generating an optimal feature combination data set as input data of terrain classification; calculating an optimal parameter combination of a random forest algorithm, and generating an optimal random forest classifier; establishing a terrain classification system suitable for the research area, and constructing a terrain classification training sample set and a verification sample set; performing terrain classification by using a random forest classifier and the optimal feature combination data set to obtain a terrain classification result of the research area; and calculating and evaluating the precision of a terrain classification result by utilizing a verification sample set and a Kappa coefficient evaluation method. By adopting the method, the terrain classification refinement degree and the terrain classification calculation efficiency and classification efficiency can be improved.

The invention discloses a spectrum-space depth fusion hyperspectral image classification method oriented to a small sample condition, and the method comprises the steps: firstly carrying out the multi-scale hole convolution processing of input hyperspectral data through a range attention convolution SAC module, and extracting the multi-scale context features; then, a spatial normalization attention SNA mechanism is utilized to carry out adaptive weighting adjustment of spatial dimensions on the feature map, and spatial feature representation of the key area is enhanced; the method comprises the following steps: constructing a lightweight hybrid expert model LMOE, carrying out parallel processing and gating weighting through a multi-path expert network, carrying out efficient refining and mapping on features, finally fusing processed spectral features and spatial features, and carrying out pixel-level prediction through a classifier to obtain a terrain classification result map of a hyperspectral image. The method solves the problems that in the prior art, overfitting is prone to occurring under the small sample condition, the spectrum-space collaborative modeling capacity is insufficient, the long-range dependence obtaining efficiency is low, and the recognition precision is reduced under the class imbalance scene.

The invention provides a robot sensing terrain recognition gait control method and system, a medium and equipment, and belongs to the technical field of robot sensing. The method comprises the following steps: acquiring pitch angle data and plantar force data of the biped robot on the basis of optimal plantar force; inputting the pitch angle data and the plantar force data into a trained KNN model, and identifying the current walking terrain of the robot to obtain a terrain identification result; the training process of the KNN model comprises the steps that the biped robot is driven to pass through a rugged terrain and a flat terrain in a fixed stride frequency gait mode, pitch angle sample data and plantar force sample data passing through different terrains are collected and input into the KNN model, and the KNN model is used for conducting terrain classification; and the robot controller receives a terrain recognition result, and adjusts the stride frequency and the gait of the robot according to a preset gait control strategy based on the result. According to the method, an additional sensor does not need to be added to the robot, and the terrain can be identified only through state feedback of the robot.

The invention discloses a foot-ground contact force estimation and terrain classification method of an ostrich-imitating robot. The method comprises the steps that a foot-ground contact force mapping matrix of the ostrich-imitating robot is constructed, force-position hybrid control is carried out, foot-ground contact force is obtained according to the matrix and input torque of a plate spring to a passive joint, and terrain classification information is obtained after the ground contact state is judged; establishing a terrain classification fusion model based on a weighted voting mechanism, and training the model according to terrain classification information; and performing terrain classification according to the terrain classification information and the trained model. The foot-ground contact force is estimated through the joint corner information of the robot, no extra sensor needs to be installed, real-time and accurate foot-ground contact force estimation and contact state obtaining are achieved, the problem that the performance of an ostrich-imitating robot system is reduced or fails due to the fact that a force sensor is prone to being damaged is effectively solved, system configuration is simplified, and the system reliability is improved. Foot-ground contact force estimation and accurate terrain classification of the ostrich-imitating robot can be completed without depending on an external sensor.

The invention provides a surface deformation monitoring and classifying method based on InSAR and deep learning, which comprises the following steps: (1) collecting multi-scene time sequence SAR images and DEM data of a monitoring area, (2) carrying out registration, interference and DEM difference on the multi-scene time sequence SAR images, (3) selecting PS pixels by using amplitude deviation and a coherence coefficient threshold value, (4) linking the PS pixels to construct a spatial network, and (5) classifying the spatial network. (6) recovering deformation information of PS monitoring points; (7) performing primary classification on registered SAR images by using a random forest; (8) performing secondary classification on the SAR images by using primary classification samples and a ViT network; and (9) performing classification, statistics and cause analysis on deformation based on a multi-classification result. According to the method, the classification precision of the SAR image classification method is improved, and the InSAR deformation can be effectively classified and analyzed by using the land classification result.

The invention provides a submarine topography classification method and device, electronic equipment and a storage medium, and relates to the technical field of image processing.The submarine topography classification method comprises the steps that backscattering data and water depth data corresponding to a target submarine area are input into a first modeling network and a second modeling network respectively, extracting a context feature of the backscattering data through a first modeling network to obtain a first modal feature, and extracting a context feature of the water depth data through a second modeling network to obtain a second modal feature; fusing the first modal feature and the second modal feature through a modal shuffling network to obtain a fused feature; performing enhancement processing on the fusion features through an adjacent matrix in the graph transformer network to obtain enhanced features; performing up-sampling processing on the enhanced features through an up-sampling network to obtain target features; and determining a terrain classification result of the target seabed area according to the target features. According to the method, the classification precision of the submarine topography and landform is remarkably improved.

The invention discloses a wheeled mobile platform terrain detection method, comprising: acquiring a terrain classification data set, the data set comprising a tactile image stream corresponding to tactile sequence data collected in the traveling process of a wheeled mobile platform and pre-labeled terrain category information; training the initial classification model by using a tactile image stream in the terrain classification data set to obtain a terrain classification model; and inputting a to-be-detected tactile image flow into the terrain classification model to obtain a terrain detection result of the mobile platform. The terrain type of the wheel type mobile platform in the advancing process is effectively detected through the wheel type mobile platform terrain detection method, the trolley can avoid the terrain prone to sinking and bumping, damage is prevented, and the task success rate is increased.

This disclosure relates to automatic lane and and / or terrain detection and recognition under various ambient and driving conditions for robotic / vehicular control purposes / applications. In one aspect, a rule-based detection system is configured to perform lane recognition using optical images. Various edge detection thresholds are adaptively tuned from frame to frame using a feedback signal derived from a fuzzy logic inference mechanism. Such detection techniques may also be adapted for drivable region detection, which may be fused together with drivable region detection based on LiDAR cloud point. Such detection techniques may be further adapted for a preprocessing of optical images of road to generate preprocessed images that may then be processed by learning-based lane detection models. In another aspect, an intelligent terrain classification system may be configured to include a fusion of both a vision-based terrain classification convolutional neural network (CNN) and a parallel proprioception-based terrain classification CNN. These CNNs may be configured to process a small number of selected set of proprioceptive signals and to adaptively detect / classify the terrain as platform-independent as possible.

The invention relates to the technical field of land classification, in particular to a land utilization classification method based on a space-time fusion technology, which comprises the following steps: firstly, acquiring original remote sensing images, classifying the original remote sensing images, and then respectively creating buffer areas for the divided original remote sensing images; the method comprises the following steps of: acquiring an original remote sensing image, dividing a buffer area into buffer area groups according to the category of the original remote sensing image, carrying out space-time fusion on different buffer area groups through a space-time fusion algorithm, splicing the fused image to generate a final image, and finally carrying out land utilization classification by adopting a supervised classification method according to the final image and a historical image. According to the method and the device, an effective solution is provided for improving the land utilization classification precision by integrating the time dynamic information of the low-resolution image and the space details of the high-resolution image based on the space-time fusion technology.

The invention discloses an idle land recognition method, device and equipment and a storage medium, and belongs to the technical field of machine learning, and the method comprises the steps: obtaining a first land feature set based on the land text data of a plurality of pieces of land; screening the first land feature set to obtain a second land feature set; semi-supervised learning cooperative training is carried out on a first classifier and a second classifier based on the second land feature set, the first classifier and the second classifier are used for idle land identification, the first classifier is realized based on a rotating forest algorithm, and the second classifier is realized based on an extreme gradient lifting algorithm; wherein in the semi-supervised learning cooperative training process, the prediction labels are screened based on a preset idle land classification rule. The method can realize accurate and efficient idle land identification.

The invention relates to the technical field of point cloud data processing and application, in particular to a cross-domain small sample point cloud terrain classification method and system, and the method comprises the steps: pre-training a source domain feature extractor and a source domain classifier on a source data set; in the cross-domain transfer learning stage, point-level source domain features and target domain features from the same base class and corresponding prediction results are input into a conditional domain adversarial network to train a target feature extractor and a target classifier of a target domain teacher model, and the target domain features are obtained by using small sample data through the target feature extractor; in a class incremental learning stage in a target domain, a student model in the target domain incrementally learns features of a new class, and incremental feature semantic knowledge distillation is performed between a target extractor of a learned teacher model and a current student model; meanwhile, a semantic adversarial learning module is used for distinguishing the feature representation of the new category and the feature representation of the basic category. According to the method, the precision of point cloud cross-domain transfer learning under the small sample condition is effectively improved.

The invention provides a quadruped robot terrain classification method and system based on sound feature and IMU information fusion, and relates to the field of terrain perception, and the method specifically comprises the steps: collecting an audio signal, processing the audio signal to obtain a Mel spectrogram, collecting an IMU signal, drawing a triaxial IMU signal time domain graph, dividing the time domain graph into a plurality of IMU information graphs, and obtaining a quadruped robot terrain classification result. The feature value of each time domain graph window is calculated, an IMU information graph corresponding to the Mel-frequency spectrogram in time relation can be established, then the Mel-frequency spectrogram and the IMU information graph are spliced according to the time sequence, and the spliced Mel-frequency spectrogram and IMU information graph are input into a neural network model for terrain classification; according to the method, the classification capability of the unstructured outdoor terrain is enhanced in a mode of fusing sound perception and ontology perception, and the spliced input image not only contains audio features, but also retains IMU information, so that a neural network model can learn from two different perception sources, terrain features can be comprehensively understood, and the classification efficiency of the unstructured outdoor terrain is improved. Therefore, the recognition capability of the complex environment is improved.

The invention relates to the technical field of power transmission line terrain analysis, in particular to a power transmission line terrain analysis method and device based on grid communication and a storage medium. The method comprises the following steps: firstly, acquiring digital elevation data of a power transmission line path area, and establishing a grid network by taking a certain point in the area as a rectangular corner point; taking any point in the grid as a starting point, setting a calculation radius, extracting terrain elevation data in the range, and calculating the maximum height difference with the starting point; and dividing the discrete network according to the height difference based on engineering technical and economic definition, and determining a terrain classification result of the initial grid. And iteratively calculating the terrain classification of each grid in the path region through a preset sampling step length, and communicating the grids of the same type. And according to a preset filtering area threshold value, filtering out grids of which the area is smaller than the threshold value, and obtaining a final terrain analysis result. According to the method, terrain analysis of the long-distance and large-span power transmission line can be realized, model selection errors caused by subjective judgment or low-precision data are avoided, and the design efficiency is improved.

The invention relates to the technical field of land type classification, in particular to a land type classification method based on territorial resource data, and the method comprises the following steps: S1, data preparation; s2, determining a classification target, a classification standard and a classification range; s3, land feature extraction and analysis; s4, data preprocessing and cleaning; s5, land feature extraction and selection; s6, formulating a classification method and algorithm selection; s7, land type division and marking; s8, determining a classification method and technology; and S9, formulating a classification standard and index system. Through land feature extraction and analysis, data preprocessing and cleaning and land feature extraction and selection, land data diversity understanding and effective management can be achieved, classification precision and efficiency are improved, and it is ensured that the classification result is more accurate and reasonable through verification and precision of the classification result; the reasonable utilization and protection level of land resources is improved through result optimization, and the accuracy and applicability of land classification are improved.

The invention discloses a GIS-based land classification depth measurement method and system, relates to the technical field of land classification depth measurement, and aims to solve the problems that in traditional land depth measurement work, due to the fact that the number of measurement points is limited and distribution is lack of systematicness, the real change condition of land depth is difficult to comprehensively and accurately reflect, local depth abnormal areas are easy to omit, and the measurement accuracy is poor. According to the method, multi-source geographic data are integrated through the GIS technology, land depth information can be comprehensively and accurately reflected, and the problems that traditional measurement is low in precision, measurement point distribution is lack of systematicness, and data processing and analysis capacity is weak are solved. In the aspect of region division, the consistency of land features in the region is ensured by integrating a multi-factor consideration method, a dynamic adjustment mechanism of measurement point layout can be flexibly arranged according to the actual condition of the land, a slope calculation and depth estimation method is combined, the complex relation between geographic elements is fully considered, and estimation errors are effectively reduced.

The invention discloses an automatic classification design model for surveying and mapping and geographic information achievements, and relates to the technical field of surveying and mapping and geographic information achievement classification. According to the automatic classification design model for the surveying and mapping and geographic information achievements, a terrain classification result is generated by comprehensively analyzing a terrain area to be measured based on surface and deep terrain features, and visual display is achieved through model marking. In combination with gradient, curvature, texture and undulation degree indexes of elevation data, an initial terrain evaluation index is calculated, and a comprehensive terrain evaluation index is generated by using deep rock-soil density, field intensity, energy characteristics and ecological hydrological data, so that the classification accuracy is remarkably improved, the defect of insufficient attention to deep features in a traditional method is overcome, and the method is suitable for large-scale popularization and application. Therefore, the complex characteristics of the terrain area can be comprehensively reflected, a reliable basis is provided for scientific planning, and particularly in a complex geological environment, the high matching degree of a terrain classification result and an actual application requirement is ensured.

The invention discloses a terrain classification and self-adaptive gait switching method for a sea-turtle-imitating amphibious robot based on visual tactile perception. The method comprises the following steps: establishing a robot model carrying a pressure sensor and a waterproof camera; the method comprises the following steps: acquiring tactile time sequence data and visual images in various terrains such as broken stones and sand beaches, and constructing a training data set; establishing a multi-modal convolutional neural network, and fusing features through dual-channel feature extraction and an adaptive attention mechanism; motion energy consumption and speed under each terrain are collected, and the optimal gait is determined; and constructing a gait switching finite-state machine in combination with terrain physical attribute classification and the optimal gait. According to the method, a sensing-decision-driving closed loop is formed, the terrain is sensed through visual touch, the gait is decided through a finite-state machine, the gait driving motion is executed, and through experimental verification, the self-adaptive gait can improve the moving efficiency and speed, and the amphibious environment adaptability of the robot is enhanced.

The invention relates to an improved riverbed erosion and deposition amount calculation method and system based on terrain classification encryption and a medium, and the method comprises the steps: 1, collecting the fixed section and underwater terrain observation data of a typical river reach; step 2, cutting an encrypted section based on topographic observation data; 3, calculating the erosion and deposition amount of each level of encrypted section; and 4, determining the erosion and deposition amount of the section of the river section and calculating the encryption series. According to the method, the terrain and section observation data are adopted, the river channel scouring and silting amount deviation calculated based on the terrain and the section is reduced, the section is subjected to multi-stage encryption through the river channel terrain observation data, the control index for judging that the encryption stage number is qualified is provided, and the calculation method for obtaining the riverbed scouring and silting amount based on the river channel storage change between the sections is further optimized; the riverbed scouring and silting adjustment degree of the riverway can be reflected more accurately and truly, and a foundation support is provided for river treatment.

The invention discloses a polarized SAR terrain classification method based on hybrid convolutional neural network cross pseudo supervision in the technical field. The method comprises the following steps: 1) converting triangular elements on a polarized coherence matrix of each pixel in an image into a 6-dimensional complex vector and a 6-dimensional real number vector through real number conversion; 2) extracting an image block with the size of w * w * 6 as an input sample of the network by taking each pixel in the image as a center; 3) using random values to initialize weights in the CV-CNN and the CNN; 4) inputting the label samples and the label-free samples into the cross pseudo-supervised network, and performing optimization by using a small-batch stochastic gradient descent algorithm; and 5) after the training is finished, inputting a neighborhood block corresponding to each pixel in the image into the CV-CNN and the CNN, and fusing the prediction probability values of the two networks to complete the classification of the image, thereby solving the problem of training sample scarcity in the polarized SAR image classification problem.

The invention discloses a terrain classification method based on audio-visual information fusion. The method first controls a vehicle to travel on different terrains, uses a forward-facing camera mounted on the bottom of the vehicle to obtain a terrain image when the vehicle is traveling, and uses a sound sensor to collect sound signals of the interaction between the vehicle and the ground during the driving process; preprocesses the visual image and the sound signal; then extracts the features of the visual image and the sound signal respectively, and the extracted image features include the color histogram features and local binary features of the image; fuses the visual features with the sound features and performs feature dimension reduction; then inputs the reduced feature vector and the original image into the designed fully connected neural network classifier and residual network classifier for classification training; the final classification decision result is obtained by weighting the outputs of the two classifiers, the fully connected neural network classifier and the residual network classifier. After the model is trained, the model is used for online terrain classification.

The application provides a terrain recognition method, device and equipment for a legged robot and a medium. The method comprises the following steps: acquiring pose data collected by a body sensor of a target legged robot, and calculating state parameters of the target legged robot; inputting the pose data and the state parameters into a foot-ground contact force model to determine three-dimensional foot-ground contact force; generating a contact mask sequence representing a foot-end ground contact state of the target legged robot based on the three-dimensional foot-ground contact force, and segmenting the pose data to obtain a segmented pose data set; inputting the pose data set into a pre-trained terrain classification model to determine a confidence vector of the current ground under multiple terrain attributes, and determining a terrain category of the current ground according to multiple confidence vectors. Through the method and device, the autonomous adaptation capability and environmental perception reliability of the legged robot in complex terrain are significantly improved.

The invention discloses a power transmission line microtopography recognition method, system and device based on a multi-modal attention mechanism and a medium, and the method comprises the steps: obtaining power transmission line space corridor data and multi-source geographic information data of a target region, carrying out the preprocessing, and generating a line feature map and a multi-channel ground feature map; constructing a double-branch deep learning network model, inputting the line feature map into a topographic feature branch, inputting the multi-channel ground feature map into a line feature branch, and respectively extracting deep feature information; through a cross-branch space attention module, weighting the features extracted by the topographic feature branches by using a space attention weight generated by extracting the features by the line feature branches to obtain fusion features; and inputting the fused features into a decoder for up-sampling and feature reconstruction, and outputting a classification recognition result for the microtopography along the power transmission line corridor. According to the invention, full-process intelligent processing is realized, the identification efficiency is obviously improved, and the method is suitable for wide-range line census and risk assessment.

The invention discloses a terrain classification method and system based on a plate capacitance tomography sensor, and belongs to the technical field of robot application. The method comprises the following steps: firstly, designing a panel ECT sensor array comprising eight electrodes, and building a mobile robot body sensing data acquisition system, so as to acquire mutual capacitance data and inertial data of terrains; and secondly, performing feature extraction, fusion and classification on the capacitance data and the inertial data by building a multi-layer perceptron classification model, after the multi-layer perceptron model is trained, moving the robot to a known terrain, and completing the classification of the terrain through the multi-layer perceptron. According to the method, two kinds of modal information of inertia and capacitance are utilized, through combination of interactive vibration information of the robot and the terrains and changes of dielectric constants in the terrains, the terrains made of various different materials can be automatically recognized, and the method has high universality and practical significance.

A system and method for terrain classification is provided herein. The system includes a lidar that emits a laser pulse onto an environment and receives a reflected laser pulse off of a terrain of the environment, an analogue to digital converter that converts the reflected laser pulse into an input waveform, and a computer system that receives the input waveform. The computer system includes a correlation engine that may use a neural network. The correlation engine correlates the input waveform. The computer system includes a terrain classifier that classifies the fitted waveform in real-time to classify a property of the terrain.

This application proposes a method, device, and electronic device for acquiring fire rescue tactics. The method includes: acquiring the fire line classification features and terrain classification features of any first grid cell in a set of grid cells corresponding to the fire line; acquiring the feature vector corresponding to any first grid cell based on the first feature vector corresponding to the fire line classification features, the second feature vector corresponding to the terrain classification features, and the third feature vector corresponding to the environmental features of any first grid cell; and analyzing the feature vector corresponding to any first grid cell using a target graph convolutional neural network model and a target temporal Transformer model to acquire the fire rescue tactics corresponding to any first grid cell. This solves the technical problem in the prior art that fire relief methods cannot adapt to changes, resulting in a mismatch between the fire relief methods and the current fire situation, and poor fire extinguishing effect.

The application discloses a passability prediction method for unstructured terrain environment, and is applied to the technical field of vehicle traffic capacity prediction. The application constructs a three-dimensional grid map based on a multi-source sensor, combines semantic terrain classification and elevation structure feature extraction, and forms a geometric and semantic joint representation of the environment. By comparing the control instruction with the motion response of the vehicle in the actual terrain, a traffic capacity coefficient is constructed as a supervision signal, and a conditional variational autoencoder is trained to model the traffic capacity coefficient distribution and its uncertainty under different terrain conditions. Further, intermediate layer features are extracted from the semantic recognition network to establish a category statistical model for identifying terrain categories that do not appear in the training set. Finally, the traffic capacity confidence and terrain reliability are fused to output a grid-level traffic probability, realizing the passability prediction in the unstructured environment.