Sensors

Research

Jump to: Other

19 pages, 6887 KiB

Open AccessArticle

Amalgamation of Geometry Structure, Meteorological and Thermophysical Parameters for Intelligent Prediction of Temperature Fields in 3D Scenes

by Yuan Cao, Ligang Li, Wei Ni, Bo Liu, Wenbo Zhou and Qi Xiao

Sensors 2022, 22(6), 2386; https://doi.org/10.3390/s22062386 - 20 Mar 2022

Cited by 1 | Viewed by 2023

Abstract

Temperature field calculation is an important step in infrared image simulation. However, the existing solutions, such as heat conduction modelling and pre-generated lookup tables based on temperature calculation tools, are difficult to meet the requirements of high-performance simulation of infrared images based on [...] Read more.

Temperature field calculation is an important step in infrared image simulation. However, the existing solutions, such as heat conduction modelling and pre-generated lookup tables based on temperature calculation tools, are difficult to meet the requirements of high-performance simulation of infrared images based on three-dimensional scenes under multi-environmental conditions in terms of accuracy, timeliness, and flexibility. In recent years, machine learning-based temperature field prediction methods have been proposed, but these methods only consider the influence of meteorological parameters on the temperature value, while not considering the geometric structure and the thermophysical parameters of the object, which results in the low accuracy. In this paper, a multivariate temperature field prediction network based on heterogeneous data (MTPHNet) is proposed. The network fuses geometry structure, meteorological, and thermophysical parameters to predict temperature. First, a Point Cloud Feature Extraction Module and Environmental Data Mapping Module are used to extract geometric information, thermophysical, and meteorological features. The extracted features are fused by the Data Fusion Module for temperature field prediction. Experiment results show that MTPHNet significantly improves the prediction accuracy of the temperature field. Compared with the v-Support Vector Regression and the combined back-propagation neural network, the mean absolute error and root mean square error of MTPHNet are reduced by at least 23.4% and 27.7%, respectively, while the R-square is increased by at least 5.85%. MTPHNet also achieves good results in multi-target and complex target temperature field prediction tasks. These results validate the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

18 pages, 2070 KiB

Open AccessArticle

Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation

by Rafik Ghali, Moulay A. Akhloufi and Wided Souidene Mseddi

Sensors 2022, 22(5), 1977; https://doi.org/10.3390/s22051977 - 3 Mar 2022

Cited by 89 | Viewed by 7960

Abstract

Wildfires are a worldwide natural disaster causing important economic damages and loss of lives. Experts predict that wildfires will increase in the coming years mainly due to climate change. Early detection and prediction of fire spread can help reduce affected areas and improve [...] Read more.

Wildfires are a worldwide natural disaster causing important economic damages and loss of lives. Experts predict that wildfires will increase in the coming years mainly due to climate change. Early detection and prediction of fire spread can help reduce affected areas and improve firefighting. Numerous systems were developed to detect fire. Recently, Unmanned Aerial Vehicles were employed to tackle this problem due to their high flexibility, their low-cost, and their ability to cover wide areas during the day or night. However, they are still limited by challenging problems such as small fire size, background complexity, and image degradation. To deal with the aforementioned limitations, we adapted and optimized Deep Learning methods to detect wildfire at an early stage. A novel deep ensemble learning method, which combines EfficientNet-B5 and DenseNet-201 models, is proposed to identify and classify wildfire using aerial images. In addition, two vision transformers (TransUNet and TransFire) and a deep convolutional model (EfficientSeg) were employed to segment wildfire regions and determine the precise fire regions. The obtained results are promising and show the efficiency of using Deep Learning and vision transformers for wildfire classification and segmentation. The proposed model for wildfire classification obtained an accuracy of 85.12% and outperformed many state-of-the-art works. It proved its ability in classifying wildfire even small fire areas. The best semantic segmentation models achieved an F1-score of 99.9% for TransUNet architecture and 99.82% for TransFire architecture superior to recent published models. More specifically, we demonstrated the ability of these models to extract the finer details of wildfire using aerial images. They can further overcome current model limitations, such as background complexity and small wildfire areas. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

19 pages, 5824 KiB

Open AccessArticle

Transmission Line Vibration Damper Detection Using Deep Neural Networks Based on UAV Remote Sensing Image

by Wenxiang Chen, Yingna Li and Zhengang Zhao

Sensors 2022, 22(5), 1892; https://doi.org/10.3390/s22051892 - 28 Feb 2022

Cited by 8 | Viewed by 7039

Abstract

Vibration dampers can greatly eliminate the galloping phenomenon of overhead transmission wires caused by wind. The detection of vibration dampers based on visual technology is an important issue. The current vibration damper detection work is mainly carried out manually. In view of the [...] Read more.

Vibration dampers can greatly eliminate the galloping phenomenon of overhead transmission wires caused by wind. The detection of vibration dampers based on visual technology is an important issue. The current vibration damper detection work is mainly carried out manually. In view of the above situation, this article proposes a vibration damper detection model named DamperYOLO based on the one-stage framework in object detection. DamperYOLO first uses a Canny operator to smooth the overexposed points of the input image and extract edge features, then selectees ResNet101 as the backbone of the framework to improve the detection speed, and finally injects edge features into backbone through an attention mechanism. At the same time, an FPN-based feature fusion network is used to provide feature maps of multiple resolutions. In addition, we built a vibration damper detection dataset named DamperDetSet based on UAV cruise images. Multiple sets of experiments on self-built DamperDetSet dataset prove that our model reaches state-of-the-art level in terms of accuracy and test speed and meets the standard of real-time output of high-accuracy test results. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

25 pages, 10450 KiB

Open AccessArticle

MAFF-Net: Multi-Attention Guided Feature Fusion Network for Change Detection in Remote Sensing Images

by Jinming Ma, Gang Shi, Yanxiang Li and Ziyu Zhao

Sensors 2022, 22(3), 888; https://doi.org/10.3390/s22030888 - 24 Jan 2022

Cited by 14 | Viewed by 3645

Abstract

One of the most important tasks in remote sensing image analysis is remote sensing image Change Detection (CD), and CD is the key to helping people obtain more accurate information about changes on the Earth’s surface. A Multi-Attention Guided Feature Fusion Network (MAFF-Net) [...] Read more.

One of the most important tasks in remote sensing image analysis is remote sensing image Change Detection (CD), and CD is the key to helping people obtain more accurate information about changes on the Earth’s surface. A Multi-Attention Guided Feature Fusion Network (MAFF-Net) for CD tasks has been designed. The network enhances feature extraction and feature fusion by building different blocks. First, a Feature Enhancement Module (FEM) is proposed. The FEM introduces Coordinate Attention (CA). The CA block embeds the position information into the channel attention to obtain the accurate position information and channel relationships of the remote sensing images. An updated feature map is obtained by using an element-wise summation of the input of the FEM and the output of the CA. The FEM enhances the feature representation in the network. Then, an attention-based Feature Fusion Module (FFM) is designed. It changes the previous idea of layer-by-layer fusion and chooses cross-layer aggregation. The FFM is to compensate for some semantic information missing as the number of layers increases. FFM plays an important role in the communication of feature maps at different scales. To further refine the feature representation, a Refinement Residual Block (RRB) is proposed. The RRB changes the number of channels of the aggregated features and uses convolutional blocks to further refine the feature representation. Compared with all compared methods, MAFF-Net improves the F1-Score scores by 4.9%, 3.2%, and 1.7% on three publicly available benchmark datasets, the CDD, LEVIR-CD, and WHU-CD datasets, respectively. The experimental results show that MAFF-Net achieves state-of-the-art (SOTA) CD performance on these three challenging datasets. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

19 pages, 5219 KiB

Open AccessArticle

Radar Signal Modulation Recognition Based on Sep-ResNet

by Yongjiang Mao, Wenjuan Ren and Zhanpeng Yang

Sensors 2021, 21(22), 7474; https://doi.org/10.3390/s21227474 - 10 Nov 2021

Cited by 4 | Viewed by 2719

Abstract

With the development of signal processing technology and the use of new radar systems, signal aliasing and electronic interference have occurred in space. The electromagnetic signals have become extremely complicated in their current applications in space, causing difficult problems in terms of accurately [...] Read more.

With the development of signal processing technology and the use of new radar systems, signal aliasing and electronic interference have occurred in space. The electromagnetic signals have become extremely complicated in their current applications in space, causing difficult problems in terms of accurately identifying radar-modulated signals in low signal-to-noise ratio (SNR) environments. To address this problem, in this paper, we propose an intelligent recognition method that combines time–frequency (T–F) analysis and a deep neural network to identify radar modulation signals. The T–F analysis of the complex Morlet wavelet transform (CMWT) method is used to extract the characteristics of signals and obtain the T–F images. Adaptive filtering and morphological processing are used in T–F image enhancement to reduce the interference of noise on signal characteristics. A deep neural network with the channel-separable ResNet (Sep-ResNet) is used to classify enhanced T–F images. The proposed method completes high-accuracy intelligent recognition of radar-modulated signals in a low-SNR environment. When the SNR is −10 dB, the probability of successful recognition (PSR) is 93.44%. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

32 pages, 33785 KiB

Open AccessArticle

The Effect of Synergistic Approaches of Features and Ensemble Learning Algorithms on Aboveground Biomass Estimation of Natural Secondary Forests Based on ALS and Landsat 8

by Chunyu Du, Wenyi Fan, Ye Ma, Hung-Il Jin and Zhen Zhen

Sensors 2021, 21(17), 5974; https://doi.org/10.3390/s21175974 - 6 Sep 2021

Cited by 22 | Viewed by 3263

Abstract

Although the combination of Airborne Laser Scanning (ALS) data and optical imagery and machine learning algorithms were proved to improve the estimation of aboveground biomass (AGB), the synergistic approaches of different data and ensemble learning algorithms have not been fully investigated, especially for [...] Read more.

Although the combination of Airborne Laser Scanning (ALS) data and optical imagery and machine learning algorithms were proved to improve the estimation of aboveground biomass (AGB), the synergistic approaches of different data and ensemble learning algorithms have not been fully investigated, especially for natural secondary forests (NSFs) with complex structures. This study aimed to explore the effects of the two factors on AGB estimation of NSFs based on ALS data and Landsat 8 imagery. The synergistic method of extracting novel features (i.e., COLI1 and COLI2) using optimal Landsat 8 features and the best-performing ALS feature (i.e., elevation mean) yielded higher accuracy of AGB estimation than either optical-only or ALS-only features. However, both of them failed to improve the accuracy compared to the simple combination of the untransformed features that generated them. The convolutional neural networks (CNN) model was much superior to other classic machine learning algorithms no matter of features. The stacked generalization (SG) algorithms, a kind of ensemble learning algorithms, greatly improved the accuracies compared to the corresponding base model, and the SG with the CNN meta-model performed best. This study provides technical support for a wall-to-wall AGB mapping of NSFs of northeastern China using efficient features and algorithms. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

19 pages, 10806 KiB

Open AccessArticle

Modular Neural Networks with Fully Convolutional Networks for Typhoon-Induced Short-Term Rainfall Predictions

by Chih-Chiang Wei and Tzu-Heng Huang

Sensors 2021, 21(12), 4200; https://doi.org/10.3390/s21124200 - 18 Jun 2021

Cited by 9 | Viewed by 2690

Abstract

Taiwan is located at the edge of the northwestern Pacific Ocean and within a typhoon zone. After typhoons are generated, strong winds and heavy rains come to Taiwan and cause major natural disasters. This study employed fully convolutional networks (FCNs) to establish a [...] Read more.

Taiwan is located at the edge of the northwestern Pacific Ocean and within a typhoon zone. After typhoons are generated, strong winds and heavy rains come to Taiwan and cause major natural disasters. This study employed fully convolutional networks (FCNs) to establish a forecast model for predicting the hourly rainfall data during the arrival of a typhoon. An FCN is an advanced technology that can be used to perform the deep learning of image recognition through semantic segmentation. FCNs deepen the neural net layers and perform upsampling on the feature map of the final convolution layer. This process enables FCN models to restore the size of the output results to that of the raw input image. In this manner, the classification of each raw pixel becomes feasible. The study data were radar echo images and ground station rainfall information for typhoon periods during 2013–2019 in southern Taiwan. Two model cases were designed. The ground rainfall image-based FCN (GRI_FCN) involved the use of the ground rain images to directly forecast the ground rainfall. The GRI combined with rain retrieval image-based modular convolutional neural network (GRI-RRI_MCNN) involved the use of radar echo images to determine the ground rainfall before the prediction of future ground rainfall. Moreover, the RMMLP, a conventional multilayer perceptron neural network, was used to a benchmark model. Forecast horizons varying from 1 to 6 h were evaluated. The results revealed that the GRI-RRI_MCNN model enabled a complete understanding of the future rainfall variation in southern Taiwan during typhoons and effectively improved the accuracy of rainfall forecasting during typhoons. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

17 pages, 13640 KiB

Open AccessArticle

Off-Grid DOA Estimation Based on Circularly Fully Convolutional Networks (CFCN) Using Space-Frequency Pseudo-Spectrum

by Wenqiong Zhang, Yiwei Huang, Jianfei Tong, Ming Bao and Xiaodong Li

Sensors 2021, 21(8), 2767; https://doi.org/10.3390/s21082767 - 14 Apr 2021

Cited by 5 | Viewed by 2252

Abstract

Low-frequency multi-source direction-of-arrival (DOA) estimation has been challenging for micro-aperture arrays. Deep learning (DL)-based models have been introduced to this problem. Generally, existing DL-based methods formulate DOA estimation as a multi-label multi-classification problem. However, the accuracy of these methods is limited by the [...] Read more.

Low-frequency multi-source direction-of-arrival (DOA) estimation has been challenging for micro-aperture arrays. Deep learning (DL)-based models have been introduced to this problem. Generally, existing DL-based methods formulate DOA estimation as a multi-label multi-classification problem. However, the accuracy of these methods is limited by the number of grids, and the performance is overly dependent on the training data set. In this paper, we propose an off-grid DL-based DOA estimation. The backbone is based on circularly fully convolutional networks (CFCN), trained by the data set labeled by space-frequency pseudo-spectra, and provides on-grid DOA proposals. Then, the regressor is developed to estimate the precise DOAs according to corresponding proposals and features. In this framework, spatial phase features are extracted by the circular convolution calculation. The improvement in spatial resolution is converted to increasing the dimensionality of features by rotating convolutional networks. This model ensures that the DOA estimations at different sub-bands have the same interpretation ability and effectively reduce network model parameters. The simulation and semi-anechoic chamber experiment results show that CFCN-based DOA is superior to existing methods in terms of generalization ability, resolution, and accuracy. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

17 pages, 2595 KiB

Open AccessEditor’s ChoiceArticle

Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors

by Emilio Guirado, Javier Blanco-Sacristán, Emilio Rodríguez-Caballero, Siham Tabik, Domingo Alcaraz-Segura, Jaime Martínez-Valderrama and Javier Cabello

Sensors 2021, 21(1), 320; https://doi.org/10.3390/s21010320 - 5 Jan 2021

Cited by 37 | Viewed by 8437

Abstract

Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. [...] Read more.

Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. For this reason, improving segmentation methods and understanding the effect of spatial resolution on segmentation results is key to improve dryland vegetation monitoring. We explored and analyzed the accuracy of Object-Based Image Analysis (OBIA) and Mask Region-based Convolutional Neural Networks (Mask R-CNN) and the fusion of both methods in the segmentation of scattered vegetation in a dryland ecosystem. As a case study, we mapped Ziziphus lotus, the dominant shrub of a habitat of conservation priority in one of the driest areas of Europe. Our results show for the first time that the fusion of the results from OBIA and Mask R-CNN increases the accuracy of the segmentation of scattered shrubs up to 25% compared to both methods separately. Hence, by fusing OBIA and Mask R-CNNs on very high-resolution images, the improved segmentation accuracy of vegetation mapping would lead to more precise and sensitive monitoring of changes in biodiversity and ecosystem services in drylands. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

21 pages, 7213 KiB

Open AccessArticle

Flash-Flood Potential Mapping Using Deep Learning, Alternating Decision Trees and Data Provided by Remote Sensing Sensors

by Romulus Costache, Alireza Arabameri, Thomas Blaschke, Quoc Bao Pham, Binh Thai Pham, Manish Pandey, Aman Arora, Nguyen Thi Thuy Linh and Iulia Costache

Sensors 2021, 21(1), 280; https://doi.org/10.3390/s21010280 - 4 Jan 2021

Cited by 56 | Viewed by 5033

Abstract

There is an evident increase in the importance that remote sensing sensors play in the monitoring and evaluation of natural hazards susceptibility and risk. The present study aims to assess the flash-flood potential values, in a small catchment from Romania, using information provided [...] Read more.

There is an evident increase in the importance that remote sensing sensors play in the monitoring and evaluation of natural hazards susceptibility and risk. The present study aims to assess the flash-flood potential values, in a small catchment from Romania, using information provided remote sensing sensors and Geographic Informational Systems (GIS) databases which were involved as input data into a number of four ensemble models. In a first phase, with the help of high-resolution satellite images from the Google Earth application, 481 points affected by torrential processes were acquired, another 481 points being randomly positioned in areas without torrential processes. Seventy percent of the dataset was kept as training data, while the other 30% was assigned to validating sample. Further, in order to train the machine learning models, information regarding the 10 flash-flood predictors was extracted in the training sample locations. Finally, the following four ensembles were used to calculate the Flash-Flood Potential Index across the Bâsca Chiojdului river basin: Deep Learning Neural Network–Frequency Ratio (DLNN-FR), Deep Learning Neural Network–Weights of Evidence (DLNN-WOE), Alternating Decision Trees–Frequency Ratio (ADT-FR) and Alternating Decision Trees–Weights of Evidence (ADT-WOE). The model’s performances were assessed using several statistical metrics. Thus, in terms of Sensitivity, the highest value of 0.985 was achieved by the DLNN-FR model, meanwhile the lowest one (0.866) was assigned to ADT-FR ensemble. Moreover, the specificity analysis shows that the highest value (0.991) was attributed to DLNN-WOE algorithm, while the lowest value (0.892) was achieved by ADT-FR. During the training procedure, the models achieved overall accuracies between 0.878 (ADT-FR) and 0.985 (DLNN-WOE). K-index shows again that the most performant model was DLNN-WOE (0.97). The Flash-Flood Potential Index (FFPI) values revealed that the surfaces with high and very high flash-flood susceptibility cover between 46.57% (DLNN-FR) and 59.38% (ADT-FR) of the study zone. The use of the Receiver Operating Characteristic (ROC) curve for results validation highlights the fact that FFPI_DLNN-WOE is characterized by the most precise results with an Area Under Curve of 0.96. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

16 pages, 7985 KiB

Open AccessArticle

Mapping and Discriminating Rural Settlements Using Gaofen-2 Images and a Fully Convolutional Network

by Ziran Ye, Bo Si, Yue Lin, Qiming Zheng, Ran Zhou, Lu Huang and Ke Wang

Sensors 2020, 20(21), 6062; https://doi.org/10.3390/s20216062 - 25 Oct 2020

Cited by 8 | Viewed by 3015

Abstract

New ongoing rural construction has resulted in an extensive mixture of new settlements with old ones in the rural areas of China. Understanding the spatial characteristic of these rural settlements is of crucial importance as it provides essential information for land management and [...] Read more.

New ongoing rural construction has resulted in an extensive mixture of new settlements with old ones in the rural areas of China. Understanding the spatial characteristic of these rural settlements is of crucial importance as it provides essential information for land management and decision-making. Despite a great advance in High Spatial Resolution (HSR) satellite images and deep learning techniques, it remains a challenging task for mapping rural settlements accurately because of their irregular morphology and distribution pattern. In this study, we proposed a novel framework to map rural settlements by leveraging the merits of Gaofen-2 HSR images and representation learning of deep learning. We combined a dilated residual convolutional network (Dilated-ResNet) and a multi-scale context subnetwork into an end-to-end architecture in order to learn high resolution feature representations from HSR images and to aggregate and refine the multi-scale features extracted by the aforementioned network. Our experiment in Tongxiang city showed that the proposed framework effectively mapped and discriminated rural settlements with an overall accuracy of 98% and Kappa coefficient of 85%, achieving comparable and improved performance compared to other existing methods. Our results bring tangible benefits to support other convolutional neural network (CNN)-based methods in accurate and timely rural settlement mapping, particularly when up-to-date ground truth is absent. The proposed method does not only offer an effective way to extract rural settlement from HSR images but open a new opportunity to obtain spatial-explicit understanding of rural settlements. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

27 pages, 22103 KiB

Open AccessArticle

Novel Ensemble Approach of Deep Learning Neural Network (DLNN) Model and Particle Swarm Optimization (PSO) Algorithm for Prediction of Gully Erosion Susceptibility

by Shahab S. Band, Saeid Janizadeh, Subodh Chandra Pal, Asish Saha, Rabin Chakrabortty, Manouchehr Shokri and Amirhosein Mosavi

Sensors 2020, 20(19), 5609; https://doi.org/10.3390/s20195609 - 30 Sep 2020

Cited by 123 | Viewed by 6353

Abstract

This study aims to evaluate a new approach in modeling gully erosion susceptibility (GES) based on a deep learning neural network (DLNN) model and an ensemble particle swarm optimization (PSO) algorithm with DLNN (PSO-DLNN), comparing these approaches with common artificial neural network (ANN) [...] Read more.

This study aims to evaluate a new approach in modeling gully erosion susceptibility (GES) based on a deep learning neural network (DLNN) model and an ensemble particle swarm optimization (PSO) algorithm with DLNN (PSO-DLNN), comparing these approaches with common artificial neural network (ANN) and support vector machine (SVM) models in Shirahan watershed, Iran. For this purpose, 13 independent variables affecting GES in the study area, namely, altitude, slope, aspect, plan curvature, profile curvature, drainage density, distance from a river, land use, soil, lithology, rainfall, stream power index (SPI), and topographic wetness index (TWI), were prepared. A total of 132 gully erosion locations were identified during field visits. To implement the proposed model, the dataset was divided into the two categories of training (70%) and testing (30%). The results indicate that the area under the curve (AUC) value from receiver operating characteristic (ROC) considering the testing datasets of PSO-DLNN is 0.89, which indicates superb accuracy. The rest of the models are associated with optimal accuracy and have similar results to the PSO-DLNN model; the AUC values from ROC of DLNN, SVM, and ANN for the testing datasets are 0.87, 0.85, and 0.84, respectively. The efficiency of the proposed model in terms of prediction of GES was increased. Therefore, it can be concluded that the DLNN model and its ensemble with the PSO algorithm can be used as a novel and practical method to predict gully erosion susceptibility, which can help planners and managers to manage and reduce the risk of this phenomenon. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

20 pages, 5516 KiB

Open AccessArticle

Automatic Changes Detection between Outdated Building Maps and New VHR Images Based on Pre-Trained Fully Convolutional Feature Maps

by Yunsheng Zhang, Yaochen Zhu, Haifeng Li, Siyang Chen, Jian Peng and Ling Zhao

Sensors 2020, 20(19), 5538; https://doi.org/10.3390/s20195538 - 27 Sep 2020

Cited by 1 | Viewed by 2351

Abstract

Detecting changes between the existing building basemaps and newly acquired high spatial resolution remotely sensed (HRS) images is a time-consuming task. This is mainly because of the data labeling and poor performance of hand-crafted features. In this paper, for efficient feature extraction, we [...] Read more.

Detecting changes between the existing building basemaps and newly acquired high spatial resolution remotely sensed (HRS) images is a time-consuming task. This is mainly because of the data labeling and poor performance of hand-crafted features. In this paper, for efficient feature extraction, we propose a fully convolutional feature extractor that is reconstructed from the deep convolutional neural network (DCNN) and pre-trained on the Pascal VOC dataset. Our proposed method extract pixel-wise features, and choose salient features based on a random forest (RF) algorithm using the existing basemaps. A data cleaning method through cross-validation and label-uncertainty estimation is also proposed to select potential correct labels and use them for training an RF classifier to extract the building from new HRS images. The pixel-wise initial classification results are refined based on a superpixel-based graph cuts algorithm and compared to the existing building basemaps to obtain the change map. Experiments with two simulated and three real datasets confirm the effectiveness of our proposed method and indicate high accuracy and low false alarm rate. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

18 pages, 1280 KiB

Open AccessArticle

Crop Disease Classification on Inadequate Low-Resolution Target Images

by Juan Wen, Yangjing Shi, Xiaoshi Zhou and Yiming Xue

Sensors 2020, 20(16), 4601; https://doi.org/10.3390/s20164601 - 16 Aug 2020

Cited by 24 | Viewed by 3701

Abstract

Currently, various agricultural image classification tasks are carried out on high-resolution images. However, in some cases, we cannot get enough high-resolution images for classification, which significantly affects classification performance. In this paper, we design a crop disease classification network based on Enhanced Super-Resolution [...] Read more.

Currently, various agricultural image classification tasks are carried out on high-resolution images. However, in some cases, we cannot get enough high-resolution images for classification, which significantly affects classification performance. In this paper, we design a crop disease classification network based on Enhanced Super-Resolution Generative adversarial networks (ESRGAN) when only an insufficient number of low-resolution target images are available. First, ESRGAN is used to recover super-resolution crop images from low-resolution images. Transfer learning is applied in model training to compensate for the lack of training samples. Then, we test the performance of the generated super-resolution images in crop disease classification task. Extensive experiments show that using the fine-tuned ESRGAN model can recover realistic crop information and improve the accuracy of crop disease classification, compared with the other four image super-resolution methods. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

23 pages, 5970 KiB

Open AccessArticle

High-Resolution U-Net: Preserving Image Details for Cultivated Land Extraction

by Wenna Xu, Xinping Deng, Shanxin Guo, Jinsong Chen, Luyi Sun, Xiaorou Zheng, Yingfei Xiong, Yuan Shen and Xiaoqin Wang

Sensors 2020, 20(15), 4064; https://doi.org/10.3390/s20154064 - 22 Jul 2020

Cited by 21 | Viewed by 3303

Abstract

Accurate and efficient extraction of cultivated land data is of great significance for agricultural resource monitoring and national food security. Deep-learning-based classification of remote-sensing images overcomes the two difficulties of traditional learning methods (e.g., support vector machine (SVM), K-nearest neighbors (KNN), and random [...] Read more.

Accurate and efficient extraction of cultivated land data is of great significance for agricultural resource monitoring and national food security. Deep-learning-based classification of remote-sensing images overcomes the two difficulties of traditional learning methods (e.g., support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF)) when extracting the cultivated land: (1) the limited performance when extracting the same land-cover type with the high intra-class spectral variation, such as cultivated land with both vegetation and non-vegetation cover, and (2) the limited generalization ability for handling a large dataset to apply the model to different locations. However, the “pooling” process in most deep convolutional networks, which attempts to enlarge the sensing field of the kernel by involving the upscale process, leads to significant detail loss in the output, including the edges, gradients, and image texture details. To solve this problem, in this study we proposed a new end-to-end extraction algorithm, a high-resolution U-Net (HRU-Net), to preserve the image details by improving the skip connection structure and the loss function of the original U-Net. The proposed HRU-Net was tested in Xinjiang Province, China to extract the cultivated land from Landsat Thematic Mapper (TM) images. The result showed that the HRU-Net achieved better performance (Acc: 92.81%; kappa: 0.81; F1-score: 0.90) than the U-Net++ (Acc: 91.74%; kappa: 0.79; F1-score: 0.89), the original U-Net (Acc: 89.83%; kappa: 0.74; F1-score: 0.86), and the Random Forest model (Acc: 76.13%; kappa: 0.48; F1-score: 0.69). The robustness of the proposed model for the intra-class spectral variation and the accuracy of the edge details were also compared, and this showed that the HRU-Net obtained more accurate edge details and had less influence from the intra-class spectral variation. The model proposed in this study can be further applied to other land cover types that have more spectral diversity and require more details of extraction. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

Other

Jump to: Research

12 pages, 12182 KiB

Open AccessLetter

Chimney Detection Based on Faster R-CNN and Spatial Analysis Methods in High Resolution Remote Sensing Images

by Chunming Han, Guangfu Li, Yixing Ding, Fuli Yan and Linyan Bai

Sensors 2020, 20(16), 4353; https://doi.org/10.3390/s20164353 - 5 Aug 2020

Cited by 12 | Viewed by 3350

Abstract

Spatially location and working status of pollution sources are very important pieces of information for environment protection. Waste gas produced by fossil fuel consumption in the industry is mainly discharged to the atmosphere through a chimney. Therefore, detecting the distribution of chimneys and [...] Read more.

Spatially location and working status of pollution sources are very important pieces of information for environment protection. Waste gas produced by fossil fuel consumption in the industry is mainly discharged to the atmosphere through a chimney. Therefore, detecting the distribution of chimneys and their working status is of great significance to urban environment monitoring and environmental governance. In this paper, we use an open access dataset BUAA-FFPP60 and the faster regions with convolutional neural network (Faster R-CNN) algorithm to train the preliminarily detection model. Then, the trained model is used to detect the chimneys in three high-resolution remote sensing images of Google Maps, which is located in Tangshan city. The results show that a large number of false positive targets are detected. For working chimney detection, the recall rate is 77.27%, but the precision is only 40.47%. Therefore, two spatial analysis methods, the digital terrain model (DTM) filtering, and main direction test are introduced to remove the false chimneys. The DTM is generated by ZiYuan-3 satellite images and then registered to the high-resolution image. We set an elevation threshold to filter the false positive targets. After DTM filtering, we use principle component analysis (PCA) to calculate the main direction of each target image slice, and then use the main direction to remove false positive targets further. The results show that by using the combination of DTM filtering and main direction test, more than 95% false chimneys can be removed and, therefore, the detection precision is significantly increased. Full article

(This article belongs to the Special Issue Deep Learning Methods for Remote Sensing)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Deep Learning Methods for Remote Sensing

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (16 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI