Search

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objectives: The quality of network structure is the key to obtain excellent classification performance. Most of existing deep models are designed by the trial-and-error method. When the same model processes different hyperspectral images (HSIs), different network hyperparameters need to be set artificially to adapt to the data characteristics of different images, greatly increasing the difficulty of network design. Aiming at the problem of deep learning model design in hyperspectral image classification, this paper proposes an automatic network structure search method for HSI classification. Methods: In the proposed method, the differentiable structure search technology is first used to search the network structure on the source HSI data sets, then the deep network model is constructed by stacking cells, and finally the classification performance is evaluated on the target HSIs. It should be pointed out that, the proposed method only conducts one search on the source HSI data sets, and the obtained deep model can be applied to other target HSI classification tasks, which can effectively improve the utilization rate of the model. To improve the generalization ability and classification accuracy of the model, multi-source and multi-resolution HSIs are employed to construct the precollected data set, and the partial channel connection operation is introduced to further improve the search efficiency. Results: Three HSIs inculding Houston, Chikusei and Pavia Center are selected as source data. Four HSIs including University of Pavia, Indian Pines, Salinas and Houston 2018 are selected as the target HSIs. The source data is used to determine the network model and the target HSIs are used to evaluate the classification performance. Experimental results show that the proposed method can automatically search out a universal deep network model suitable for HSI classification task, and this model can achieve better classification performance than the conventional deep learning models. The overall classification accuracies of University of Pavia, Indian Pines, Salinas and Houston 2018 are 98.15%, 98.74%, 97.30% and 74.47%, respectively. Conclusions: Compared with other deep models, the model in this paper is automatically determined by differentiable architecture search algorithm according to the data characteristics of HSIs, effectively improving the classification accuracy of target HSIs while avoiding complex network design. Extensive experiments verify the applicability and effectiveness of the proposed method in HSI classification. [ABSTRACT FROM AUTHOR]

Objectives: Flood disaster is a very destructive natural disaster. The main reasons for its generation include heavy rainfall, storm surge and dam break. When flood disaster occurs in populated areas such as cities and towns, the flood will directly threaten the safety of life and property of residents. Also it will cause paralysis of land and underground transportation, interruption of water and electricity transportation. In the process of flood rescue, quick and accurate identification of flooded roads is conducive to planning appropriate personnel transfer and material transportation routes, and reducing subsequent losses caused by floods. Aiming at the problem that roads in the flood disaster scenario cannot be automatically and correctly identified, this paper proposes an end-to-end flooded road detection method based on deep learning. Methods: The proposed method uses a three-branch encoder-decoder structure and uses strip convolution, in which the efficient extraction of linear features is realized. And the coordination dual attention mechanism can effectively guide the network, and realize the identification of road areas. The method can effectively utilize the historical optical remote sensing images before the disaster and the real-time optical remote sensing during the disaster. The image is applied to detect the flooded and non-flooded roads in the disaster-stricken area, and a comparative experiment is carried out on the self-built dataset. Results: The experimental results show that the precison and recall rate are 0.838 1 and 0.666 8 on pre-disaster road, 0.796 6 and 0.607 4 on post-disaster road, 0.780 0 and 0.661 4 on affected road respectively. Conclusions: The proposed method has achieved the goal of automatically identifying the flooded roads in the flood-stricken area. The ability of detecting flooded roads and non-flooded roads can provide strong support for flood disaster rescue and reduce losses of life and property caused by flood disasters. [ABSTRACT FROM AUTHOR]

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objectives: It is difficult for the traditional traffic information acquisition method to obtain the real-time dynamic traffic flow information of large scope and full coverage. With urbanization, the increasing number of supertall buildings makes the city skyline a favorable platform for earth observation. This paper studies the urban remote sensing video production and traffic information extraction method using the urban skyline as the observation platform. Methods: First, the earth observation data shooting is carried out in the super-tall buildings. Then, the original oblique observation data is corrected by orthography, which is further fused with the satellite image to generate a large range of remote sensing video data of the city. Finally, we train a deep learning model and use it for vehicle classification and identification. The number and density of vehicles in the area are calculated based on the identification results. Results: This paper carries out data collection and processing analysis on the sightseeing floor of Ping, an Building in Shenzhen. Results show that the proposed method can produce low-cost, long-time, large-scale and high-quality urban remote sensing video. The vehicle detection based on the remote sensing video have high accuracy. Conclusions: The proposed framework can be used to effectively monitor the regional traffic flow and sever for the smart city management. Furthermore, based on its capability of long-time, high-resolution, full-coverage and real-time remote sensing, this method can also be applied to many other urban management fields, such as urban disaster emergency response, crowd monitoring, and construction site monitoring. [ABSTRACT FROM AUTHOR]

Objectives: Recognition of building group patterns is an important part of the building generalization. Efficient methods for the recognition of building group patterns can effectively improve the quality of automated map generalization. Traditional recognition methods mainly include geometric methods and traditional machine learning methods, which are limited by the complex rule definitions and huge feature engineering. The graph convolution neural network (GCN) can overcome the limitations of traditional methods to some extent and has been successfully applied to the pattern analysis of buildings. However, there are few methods to recognize multiple building group patterns using GCN, and the existing GCN methods are almost based on spectral graph convolution, which do not consider local spatial information fully. Methods: As the spatial GCN is more efficient than the spectral GCN, this paper introduces a spatial GCN method DGCNN to recognize three building group patterns, including linear pattern, grid pattern and irregular pattern. The first step is to cluster the buildings into different groups, then some indices are selected to construct the feature vector of each group according to the Gestalt principles. Second, Delaunay triangulation (DT) and minimum spanning tree (MST) are chosen to construct graph structures of building groups. Finally, graph structures are used as input for the DGCNN model, and building group patterns are obtained after training. Results: The experiment selects the urban areas in Shanghai and we compare the accuracies with traditional spectral GCN method. The results show that the accuracy for the DGCNN model in the train set can reach 97.06%, and 95% for the test set. And the accuracies for the spectral GCN model in the train set is 90.90%, and 86.05% in the test set. Conclusions: The proposed method overcomes the limitations of spectral GCN, and it does not need graph Fourier transform. It can improve the recognition accuracy significantly and faces less difficulty in explaining the process of feature extraction. Hence it is an effective method for the recognition of building group patterns. [ABSTRACT FROM AUTHOR]

Objective: Deep convolutional neural network (DCNN) is widely used in automatic road extraction from high-resolution remote sensing images (HRSIs). However, the existing methods make it difficult to model the context relationship of pixels in the predicted results. To solve this problem, some studies have used fully connected conditional random field (FullCRF) to perform secondary optimization of semantic segmentation results combined with context information, but the discontinuity problem of road structure cannot be effectively improved. Methods: In order to improve the integrity of road structure, this paper proposes a short range conditional random filed (SRCRF) model combined with DCNN. SRCRF mainly includes a unary potential function based on road pre-segmentation, a binary potential function based on spectral spatial features, and a K-neighborhood mean field inference algorithm. First, the prior knowledge of road pre-segmentation results is obtained by using the powerful feature extraction capability of DCNN as the unary potential function of SRCRF. Then, the dependence of the binary potential function defined by the linear combination of Gaussian kernel functions on the surrounding nodes is modeled. The binary potential function enables the classification results to have local consistency,that is, adjacent pixels with similar spectral features have the same label. Finally, the K-neighborhood mean field inference algorithm based on the mean-field approximation inference algorithm optimizes the inference range to make full use of the spatial context information and spectral feature context information of the road, and then calculates the optimal label corresponding to each pixel based on the space and spectral feature to optimize the road accurately. The convolution method is adopted to control the inference range of SRCRF within the radius of K in order to improve the proportion of feature vectors. Results: The experimental results show that SRCRF not only alleviates the transition smoothness of FullCRF, but also alleviates the structural discontinuity and incompleteness in the road acquisition results of HRSIs. In Zimbawe-Roads dataset and Cheng-Roads dataset, F1-scores of SRCRF are increased by about 4.01% and 3.73% respectively compared with DCNN, and about 3.25% and 2.28% respectively compared with FullCRF. Conclusions: The proposed SRCRF combines the advantages of DCNN, optimizes the fully connected structure of traditional conditional random fields into the K-neighborhood structure, reduces the inference scope, and improves the proportion of feature vectors. Compared with FullCRF, SRCRF can make better use of image color features and spatial features to accurately optimize the road extraction results of deep learning output. The performance of SRCRF is improved compared with DCNN and FullCRF, and the time is shortened by one order of magnitude compared with FullCRF. In the future, we will further investigate the potential for learning Gaussian features and investigate more complex architecture of conditional random field to better capture global context information. Additionally, we are particularly interested in exploring the application potential of SRCRF in other fields, such as building extraction, vehicle extraction, lake extraction, etc. [ABSTRACT FROM AUTHOR]

Objectives: Incremental structure from motion（SfM） has become the widely used workflow for aerial triangulation（AT） of unmanned aerial vehicle （UAV） images. Recently, extensive research has been conducted to improve the efficiency, precision and scalability of SfM-based AT for UAV images. Meanwhile, deep learning-based methods have also been exploited for the geometry processing in the fields of photogrammetry and computer vision, which have been verified with large potential in the AT of UAV images. This paper aims to give a review of recent work in the SfM-based AT for UAV images. Methods:Firstly, the workflow of SfM-based AT is briefly presented in terms of feature matching and geometry solving,in which the former aims to obtain enough and accurate correspondences, and the latter attempts to solve unknown parameters. Secondly, literature review is given for feature matching and geometry solving. For feature matching, classical hand-crafted and recent learning-based methods are presented from the aspects of feature extraction, feature matching and outlier removal. For geometry solving, the principle of SfM-based AT is firstly given with some well-known and widely-used open-source SfM software. Efficiency improvement and large-scale processing are then summarized, which focus on improving the capability of SfM to process large-scale UAV images. Finally, further search is concluded from four aspects, including the change of data acquisition modes, the scalability for large-scale scenes, the development of communication and hardware, and the fusion of deep learning-based methods. Results: The review demonstrates that the existing research promotes the development of SfM-based AT towards the direction of high efficiency, high precision and high robustness, and also promotes the development of both commercial and open-source software packages. Conclusions: Considering the characteristics of UAV images, the efficiency, precision and robustness of SfMbased AT and its application need further improvement and exploitation. This paper could give an extensive conclusion and be a useful reference to the related researchers [ABSTRACT FROM AUTHOR]

Objectives: Forest canopy density is an important factor in forest resource surveys. It plays an important role in forest quality evaluation and forest resource management. In recent years, artificial intelligence technology and remote sensing technology have developed rapidly and they have been successfully applied to forestry remote sensing quantitative estimation. It is significant to study how to use deep learning methods to effectively integrate the remote sensing data with different spatial coverage capabilities in regional forest canopy closure estimation. Methods: This paper proposes a deep learning model (UnetR) which aims to estimate forest canopy closure based on deep learning model with the high-density light detection and ranging and high spatial resolution satellite imagery. We optimized the loss function of Unet for image classification, and added a batch normalization layer after the convolution layer, the model had the ability to quantitatively estimate continuous variables. Results : The comparative evaluation results with fully convolutional networks, random forest and support vector regression models show that the root mean square error of the UnetR model was lower, the estimation accuracy was higher determination coefficient is 0.777, root mean square error is 0.137, estimation accuracy is 75.60%. Conclusions: This paper provided a low labor cost and high degree of automation estimation model for remote sensing monitoring of regional forest canopy closure. [ABSTRACT FROM AUTHOR]

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objectives: Mars is the main target object for deep space exploration. Mars rovers, or roving probes, are important tools for surface exploration and scientific research on Mars. For the growing amount of remote sensing data collected by Mars rovers, there is an urgent need for a method that can intelligently detect novel targets of scientific value from the massive amount of images, reduce the time cost of detection planning, and provide information for subsequent scientific analysis. The traditional novel detection methods mostly include distance-based metrics and image-based reconstruction methods, distance-based metrics calculate novel scores pixel by pixel without considering spatial contextual information, and image-based re‐ construction methods focus on reconstruction of typical landscape backgrounds, and novelty is manifested by image reconstruction errors, which is not effective in extracting small novel targets such as boreholes and dust removal points. Methods: To address the above problems of traditional novel detection methods in Mars rover novel target detection, this paper proposes an improved Mars rover multispectral image depth novel target detection method, uses full convolutional self-coding neural network to extract deep features for typical landscape reconstruction, and joints Mahalanobis distance for novel target and typical landscape background separation, fully exploits the spatial and spectral dimensional features to improve the accuracy of Mars rover novel target detection results. Results: The experiments use the multispectral image dataset of Curiosity rover released by NASA ( National Aeronautics and Space Administration ), and the proposed convolution auto-encoder combined Mahalanobis distance method(CAE-M) is compared with Reed-Xiaoli detector, principal component analysis, convolution auto-encoder convolution, and generative adversarial networks on the surface of Gale crater. The results show that CAE-M outperforms previous detection methods in terms of detection accuracy and visual interpretation, and has a balanced and stable performance in different classes of novel target detection. Conclusion: The proposed CAE-M method comprehensively utilizes spatial and spectral information of multispectral images, which can help Mars rover exploration missions to quickly and intelligently screen and sort novel data with scientific value in massive data, save the time and cost of route planning, improve scientific returns. [ABSTRACT FROM AUTHOR]

Urban waterlogging is a typical kind of urban natural disasters, which affecting the quality of residents? life. This paper takes a series of waterlogging points produced by urban rainstorm as the research objects, comprehensively considering the influence of urban waterlogging on the work and life of residents, and screens out 21 kinds of data related to the influence degree. At the same time, based on the principle of deep learning, we construct a stacked autoencoder neural network model. With the influence degree labels of urban waterlogging points obtained by analytic hierarchy process method, the relationship between the 21 types of data and the influence degree of waterlogging points is analyzed, which will be applied to the quantitative analysis of the influence of urban waterlogging points. The experimental results show that the proposed model in this paper can describe the relationship between the spatial data and the influence degree accurately. In addition, this model can effectively predict the influence degree of potential waterlogging points, which is not only beneficial to the formulation of the urban waterlogging prevention scheme, but also provides a reference for the design of urban drainage pipe network. [ABSTRACT FROM AUTHOR]

In recent years, the rapid development of the earth observation capability and the intelligent computing technology has provided opportunities for the advancement and even revolution of remote sensing information technology. Remote sensing data processing technology has experienced the Digi-tal Signal Processing Era from 60s to 80s of last century, which utilizes the Statistical Model as the core, and the Quantitative Remote Sensing Era from 90s marked by the Physical Model. Recently, it is developing towards Remotely Sensed Big Data Era which relies on Data Model by data-driven intelligent analysis. This paper summarizes the history of remote sensing information technology and presents the concept of remotely sensed big data and the characteristics of intelligent information extraction era. Firstly, from the view of remotely sensed big data, this paper discusses the construction of object-based remote sensing knowledge dataset and analyzes the data-driven intelligent information extraction strategy combined the knowledge of remote sensing and deep learning algorithm. Then the current status and development of intelligent algorithms represented by deep learning are introduced by typical applications on object detection, fine classification and parameter inversion based on remote sensing data. Consequently, the application potential of deep learning on intelligent information extraction in Remotely Sensed Big Data Era is discussed. [ABSTRACT FROM AUTHOR]

Objectives: Manual seismic phase picking and earthquake catalog building become challenging because the number of seismic stations increases. With the rapid development of artificial intelligence, several deep learning models are developed for seismic phase picking, but their performance and applicability remain ambiguous. Methods: Phase-Net and EqT can extract relevant features at different levels from raw seismic waveforms and map them into probabilistic sequences. In this paper, the performance of these two widely-used deep learning models for earthquake detection and phase picking is investigated with the 2019 Ridgecrest earthquake (California, USA) sequence and the 2019 Weiyuan Ms 5.4 earthquake (Sichuan, China) sequence. Besides, the completeness and accuracy of the constructed earthquake catalogs are analyzed and evaluated by cross-validation. Results: The results show that the two models, though trained with datasets from different regions, perform well in cross-region applications and are comparable to manual analysis. EqT1 provides high detection precision with few false alarms, even under a low threshold. But EqT1 has a limited recall rate, implying that fewer earthquakes are detected compared with Phase-Net. The picking performance of Phase-Net is sensitive to the employed threshold. With the low and moderate thresholds, Phase-Net can detect more earthquakes than EqT1 and manual catalog, while registering a relatively low detection precision. With the high threshold, the precision of Phase-Net is comparable to that of EqT1. EqT2 is not recommended due to its inferior performance over EqT1 and Phase-Net. Conclusions: EqT1 provides a higher precision when being employed for seismic phase picking, leading to earthquake catalogs with better accuracy. Phase-Net has a higher recall rate and generates more complete catalogs. Both models can facilitate automatic and rapid construction of earthquake catalogs. [ABSTRACT FROM AUTHOR]

Objectives: CAE (convolutional autoencoder) combines the autoencoder neural network structure and the convolutional network structure. This paper processes the gravity data based on the deep learning, and reconstructs the gravity contour image from the noisy gravity data with the CAE. The autoencoder structure contains the equal dimensional input and output data, which goes for the gravity data processing. The convolutional network structure is widely used in image recognition recent years, which can learn and recognize the specific objects in an image. Methods: To create the training set, we generate 1000 hexahedrons with the random triaxial length parameters and the random density to simulate the natural gravity source bodies. The 2D gravity data set for these bodies is fast computed with the gravity forward formula and the noisy gravity data set is generated by adding Gaussian noise to the computed data. Meanwhile the accuracy of the length parameters and density is limited in order to improve the representativeness of the training data set. Hence the 2D gravity data and the noisy data will be output and input data of the CAE. We design 5 layers CAE. The input and output layers both are 26×26. 32 and 64 feature maps are generated with 3×3 convolution kernels in the inner layers. The training is executed using RMSProp(root mean square propagation) optimizer. Results: To test the generalization of the trained CAE, the testing set with 500 samples is generated in the same way with the training set. The relative error histogram on the testing set shows that the reconstructing error is less than 5% and most of the error is around 0. To test the recognition of the gravity features in the 2D gravity, we test the CAE with simulated gravity data which contain 2 and more gravity anomalies. The results show that the CAE can recognize all gravity anomalies in an noisy gravity image and reconstruct them and the output image shows fairly fine reconstruction from the gravity with 10% noise. The measured gravity data of Kauring testing ground are used to test the generalization performance of the CAE. The reconstructed image is compared with the traditional FFT(fast Fourier transform) filtering and db wavelet filtering results. To increase the reconstruction difficulty, the Kauring data is added with 10% Gaussian noise. The results show that the trained CAE performs significantly less error than the FFT filter and the wavelet filter. Conclusions: In terms of reconstructing performance, the CAE can avoid over processing that may eliminate the real gravity anomaly, which is often seen in filtering especially for FFT filtering. The CAE reconstructs all of the 3 gravity anomalies of Kauring while the FFT filtering reconstructs 2. And the over-smoothing artifact is less than filtering methods. The CAE can process 2D gravity data and show lower error and generate less artifacts than filtering methods in our tests with testing set, simulated gravity data and measuring data. Beyond that, this article reveals that the deep learning can learn gravity image. With the convolution structure in a neural network, the network can learn single gravity anomaly samples and extensively recognize all gravity anomalies in a gravity image, which signifies that the gravity can integrate with the artificial intelligence technology. [ABSTRACT FROM AUTHOR]

Objectives: Road information extraction based on vehicle trajectory data is one of the hotspots and difficulties in the field of geographic information data acquisition. Traditional methods are faced with the problems of high accuracy of trajectory data source, complex road extraction algorithm model, and poor adaptability of different road extraction model parameters. In order to solve the above problems, a trajectoryroad conversion model based on conditional generative adversarial nets is proposed, and we called it trajectory‐ to‐road translation with conditional generative adversarial nets( TR‐CGAN).Methods: Firstly, the trajectory data and the corresponding road data are raster processed in the sample area to construct the trajectory‐ road sample image pairs, then the parameters of TR‐CGAN are learned based on the sample data as the prior knowledge. Through the continuous iteration of the one player game, the optimal generation result is gradually approached. Before that, according to the characteristics of vehicle trajectory data, this paper uses the control variable method and enumeration method to analyze the parameters of U ‐Net generator depth, discriminator receptive field size and objective function in the conversion model, so as to obtain the optimal structure of TR‐CGAN.Results: Using the taxi track data in the third ring road of Zhengzhou city, the experiment results show that this proposed method can find new roads more effectively. At the same time, the trained TR‐CGAN is compared with the raster road extraction method, and it is found that our method has stronger adaptability of trajectory data in both the sparse and dense areas of the trajectory, and the accuracy of generated road is higher.Conclusions: Our proposed method can realize road extraction based on trajectory data, and has better data adaptability and accuracy. In the further research, we can increase the type of sample data, so that the road extraction model can learn to generate more road types, such as ring road types. The model can be further optimized to extract two lane roads or even lane roads. [ABSTRACT FROM AUTHOR]

3D reconstruction technology is widely used in digital elevation model production, robot naviga‐ tion, augmented reality and autonomous driving, etc. Disparity map is an important expression of 3D recon‐ struction, and stereo matching is the most widely used technology to obtain a disparity map. In recent years, with the development of hardware, data sets, and algorithms, stereo matching methods based on deep learning have received extensive attention and achieved great success. However, these works are mainly validated in close ‐ range images, and the evaluation on remote sensing aerial images is scarce. This paper reviews deep learning methods for stereo matching, and selects five representative models, such as GC‐Net (geometry and context network), PSM‐Net (pyramid stereo matching network), GWC‐Net (group‐ wise correlation stereo network), GA ‐Net (guided aggregation network), HSM ‐Net (hierarchical deep ste‐ reo matching network), and applies them to a set of open source street ‐ scene datasets (KITTI2015) and two sets of aerial remote sensing image datasets (München, WHU). The various networks are analyzed, and the performance of deep learning stereo matching methods is discussed and compared to traditional methods. The experimental results reveals that most of the deep learning methods exceed the classic semi‐ global matching and had a powerful generalization ability on cross‐dataset transfer. [ABSTRACT FROM AUTHOR]

Objective: The building collapse is the main cause of casualties and economic losses in all kinds of disasters. Accurate assessment of the collapse of buildings is an important basis for disaster rescue and government decision-making, and plays an important role in the proper placement of the victims, the protection of the lives and property of the victims. Therefore, the rapid assessment of building collapse after disaster is a research hotspot in the field of remote sensing and civil engineering. The main Objective: of this study was to apply the deep learning technology to automatically identify and assess building collapse and structural damage with on-site images. Methods: The building collapse assessment method used in this paper is ResNet (residual network). A ResNet-50 architecture was implemented in TensorFlow, which consists of 5 stages each with a convolution and identity block, 3 convolution layers in each convolution block and 3 convolution layers in each identity block. According to the building damage assessment standard developed by the China Earthquake Administration, the evaluation output of this model is adjusted to three types: Completely collapsed, semi-collapsed, and non-collapse. In the data augmentation process, geometry transformation and blur processing were used to simulate different shooting environments, to reduce the overfitting of the classifier model by enhancing the training image. Through data expansion, the number of training data has been increased by at least 10 times on the basis of PEER Hub ImageNet Challenge open dataset. In the process of transfer learning, the gradient descent algorithm was used to adjust and optimize the parameters of the neural network. The Results: of this method were evaluated by using accuracy and Kappa coefficient. Results: Finally, in the building collapse assessment experiment, the classification accuracy of the assessment model reached 77.23% and the Kappa coefficient was 0.65; in the structural damage assessment experiment, the classification accuracy of the assessment model reached 77% and the Kappa coefficient was 0.693.The proposed collapse classification successfully attains a relatively high rate for true-positives. Overall, this method performed well. This method shows great promise in supporting on-site decision-making for the rapid accurate assessment of building collapse after disaster. Conclusions: A novel automatic classification method for post-disaster building collapse evaluation is proposed,which meets the building damage evaluation standard. The method is demonstrated on a specific example classification focused on collapse classification and structural damage type identification.The experiment Results: show great promise in the rapid accurate assessment of building collapse after disaster. In the future we plan to improve the model to enhance the ability to extract subtle features in the image. [ABSTRACT FROM AUTHOR]

Impervious rate is an important indicator to evaluate the urban ecological environment. Currently, there is only 1 km and 30 m resolution of impervious surface thematic information in the global scope, which cannot meet the needs of urban scale hydrological modeling, sponge city planning and construction. In this paper, an impervious surface extraction model incorporated spectral and texture information is proposed, and a new method based on deep learning is implemented to estimate imper-vious surface information. In addition the software for extracting and monitoring of impervious surface is also developed. Based on multi-source high spatial resolution imagery, impervious surface map with 2 m spatial resolution in mainland China including 31 provinces (municipalities, autonomous regions) is accomplished, just supports the high resolution data to research and monitor sponge and ecological cities. [ABSTRACT FROM AUTHOR]

Human action recognition plays an important role in the field such as video supervision and medical diagnosis. Current methods are based on the expansion from two-dimension artificial design features to three-dimensions, ones or extracting spatio-temporal features via trajectories. Based on deep learning methods, this paper proposes a multilayer neural network in three-dimensional space, learning rich spatio-temporal features from large amount of videos. First, we use independent subspace analysis to build a two layer stacked convolutional neural network, obtaining weights from training database. Spatio-temporal features are then quantized into visual words with K-means clustering. Non-linear support vector machine(SVM) were used to classify frequency histograms of visual words into different action groups. We apply our algorithm to Hollywood2 database, extracting spatio-temporal features from 12 human action groups. Result shows that the feature weights trained by ISA network are similar with those by Gabor filter, which have obvious selectivity of frequency and direction, robustness to phase variation, conforming to the human visual system. [ABSTRACT FROM AUTHOR]