Search

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]

Objectives: The scale of buildings and their distribution is key indicators to measure the economic and social development of a region. Therefore, it is significant to study the extraction of buildings based on remote sensing images. Existing neural network methods still have shortcomings in the completeness of building extraction and the accuracy of building edges. To solve the above problems, this paper proposes a multi-level feature fusion network (MFFNet) based on high-resolution images. Methods: Firstly, we use edge detection operators to improve the ability of the network to recognize the boundaries of buildings. Secondly, we use a multi-path convolution fusion module to extract building features from multiple dimensions, and introduce a large receptive field convolution module to break through feature extraction. The process is limited by the size of the receptive field. After fusing the extracted features, the convolutional attention module is used to compress them, and the global features are further mined by pyramid pooling, so as to achieve high-precision extraction of buildings. Results: The current mainstream UNet, pyramid scene parsing network (PSPNet),multi attending path neural network (MAPNet) and multiscale-feature fusion deep neural networks with dilated convolution (MDNNet) are used as the comparison methods, and we use Wuhan University Aerial Image Dataset, Satellite Dataset II (East Asia) and Inria Aerial Image Dataset as experimental data for testing. Compared with the other four methods, MFFNet improves intersection over union, precision, recall, F1-score and mean average precision by 1.53%, 2.65%, 2.41%, 3.32% and 1.19% on average, achieves a better effect. Conclusions: MFFNet not only accurately captures the detail features of buildings, but also strengthens the extraction and utilization of global features. It has better ex‐ traction effect on large buildings and buildings in complex environment. [ABSTRACT FROM AUTHOR]

At present, pattern recognition technology has been widely used in the fields of objects, faces, fingerprints, military target recognition, etc. However， pattern recognition method still has obvious short⁃ comings when applied to the above fields. It is currently restricted to the use of image information for identi⁃ fication. When the image features of the research object are highly similar, the accuracy of pattern recogni⁃ tion is low and cannot meet the actual application requirements. For example, in the case of mixed true and false targets, it is difficult to obtain satisfactory recognition results using only image information. Aiming at the above problems, a pattern recognition method integrating image information and spectral information is proposed in this paper. Firstly, the image recognition model based on the convolutional neural network model is built to identify object categories based on the semantic features of objects and obtain preliminary recognition results. Then, on the basis of the preliminary recognition results, the measured spectral data of the object (spectrum range 400-1 000 nm, spectral resolution 2 nm) is used to perform true and fake identifi⁃ cation of the object based on the back propagation (BP) neural network model. The principle of true and false recognition is that the true and false targets are different in material, causing significant difference in their hyperspectral information. Finally, recognition results are obtained. In order to verify the accuracy of the proposed method, true and fake apples and grapes are used as experimental subjects and the result is that: The recognition accuracy obtained by using only image information is 38.50%, and the recognition accuracy obtained by using only spectral information is 63.00%, however, the recognition accuracy obtained by the method proposed in this paper is 95.00%. Compared with the existing pattern recognition method without spectral information participation, the pattern recognition method using image information and spectral information proposed in this paper improves the pattern recognition accuracy under the mixed condi⁃ tion of true and false targets, and can be widely applied to object recognition, face recognition, fingerprint recognition, military target recognition and other fields. [ABSTRACT FROM AUTHOR]

In this paper, a method is proposed to locate the insulator automatically in aerial image based on binarized normed gradients (BING) and convolutional neural networks (CNNs). Firstly, we extract insulator candidate windows with BING algorithm. Secondly, we identify the windows containing insulator with convolution neural networks. Finally, the weighted iteration of the window set with high overlap is used to acquire the final insulator positioning results. The method proposed in this paper is validated with the transmission line aerial images obtained by the actual inspection of the large-scale unmanned helicopter of Guangdong Grid Co. Experiment shows that the recall of insulators with complex background is 90. 5% and the positioning accuracy is 92%, which means the proposed method can effectively locate the insulators in aerial image with complex background, the method also has strong versatility, and can he adapted to the visible light image of different background. [ABSTRACT FROM AUTHOR]

A method of detecting outlier of multibeam sounding with back propagation (BP) neural network is proposed in this paper for the complexity of bathymetric data of a ping. This paper constructs a training and learning algorithm for complex curve of multibeam single ping data for curve fitting based on the mapping function from input to output of BP neural network. Then it inspects the results from the previous steps lengthways by the correlation analysis of data of adjacent pings, and a vertical check to locate and remore outlier is also proposed. The experiment is conducted using the real bathymetric data, where there is a shipwreck in the middle. And also the result is compared with the combined uncertainty and bathymetry estimator (CUBE) algorithm, which is a popular method in detecting outlier of multibeam sounding at present. The experiment proves that the method proposed in this paper can detect the outlier more effectively. [ABSTRACT FROM AUTHOR]

Performance of artificial neural network modeling and Kriging interpolation in PM2.5 concentration estimation varies with sample sizes and predictor variables change. This paper analyzes the performance of ordinary Kriging (OK), radical basis function (RBF) networks based on geographic coordinates, CoKriging and RBF with the key factor(s) (CK and CoRBF) selected by correlation analysis and RBF network, using different training sets with various sizes. The spatial distribution of PM2.5 concentration is then estimated by the best performed method. Results show that RBF, CoRBF, OK, and CK can all be used to estimate PM2.5 concentration efficiently, and their accuracies improved unstably as the number of training sites increase. CoRBF with the key factor of population illustrates the largest variation of PM2.5 concentration, while CK has the highest coefficient of determination (R² ) and index of agreement (IOA) and the lowest mean square error (MSE), mean absolute error (MAE), and relative error (RE). Correspondingly, the spatial pattern of CK estimated PM2.5 concentration is smoother than CoRBF estimated PM2.5 concentration, while they both are very similar to site measurements and reveal detailed information. [ABSTRACT FROM AUTHOR]

Maps play an important role in people's production and life. There is a lot of information in anno⁃ tations. Identifying map name annotation categories is of great significance for computer reading maps and further drawing maps in the future. Recently, popular deep learning technologies, especially convolutional neural networks, have a good effect on solving image classification problems. Training sets are used to train deep neural networks, and deep neural networks can extract the features of the data set pictures themselves and continue to adjust model parameters until the training is completed. This paper uses Google's open source framework TensorFlow as the experimental deep learning platform to conduct intelligent classifica⁃ tion research on multiple annotation datasets of multiple Atlases. Manually obtain annotation images from the Atlas as sample datasets to construct a convolutional neural network model and try to use two methods of mixed training and separate training to train the models. Experiments show that the model obtained by the mixed training method performs better. [ABSTRACT FROM AUTHOR]

Soil moisture has great significance in the researches of hydrology, meteorology and agriculture yield estimation. The quad-polarimetric SAR images can provide a lot of polarimetric features, the significance of the features in surface parameter retrieval have attracted attentions in previous researches with no final conclusions because of the complexity of terrain scattering. In this paper, random forest regression (RFR) is used for both soil moisture retrieval and the importance evaluation of polarimetric features of Radarsat-2 images in winter wheat fields. According to the score of importance, feature selection and combination are done for modelling. We evaluate the retrieval accuracy of models with different feature combinations. The results show that models of important features selected by RFR have RMSE(root mean square error) less than 6% which are better results compared to traditional models; when compared with support vector regression and artifical neural networks, the RFR also shows best retrieval accuracies, which proves that RFR is suitable for soil moisture retrieval and feature selection. The high retrieval accuracies of LBC-CPD(linear backscatter coefficients-Cloude-Pottier decomposition) and LBC-CPR(linear backscatter coefficients-circular polarimetric ratio) indicates these features can improve the retrieval accuracy of soil moisture. [ABSTRACT FROM AUTHOR]