scholarly journals An Improved Segmentation Method for Automatic Mapping of Cone Karst from Remote Sensing Data Based on DeepLab V3+ Model

2021 ◽  
Vol 13 (3) ◽  
pp. 441
Author(s):  
Han Fu ◽  
Bihong Fu ◽  
Pilong Shi
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Guizhou Province ◽  
Training Dataset ◽  
Optical Remote Sensing ◽  
Remote Sensing Images ◽  
Karst Landscape ◽  
Heritage Site ◽  
Training Samples ◽  
Input Module

The South China Karst, a United Nations Educational, Scientific and Cultural Organization (UNESCO) natural heritage site, is one of the world’s most spectacular examples of humid tropical to subtropical karst landscapes. The Libo cone karst in the southern Guizhou Province is considered as the world reference site for these types of karst, forming a distinctive and beautiful landscape. Geomorphic information and spatial distribution of cone karst is essential for conservation and management for Libo heritage site. In this study, a deep learning (DL) method based on DeepLab V3+ network was proposed to document the cone karst landscape in Libo by multi-source data, including optical remote sensing images and digital elevation model (DEM) data. The training samples were generated by using Landsat remote sensing images and their combination with satellite derived DEM data. Each group of training dataset contains 898 samples. The input module of DeepLab V3+ network was improved to accept four-channel input data, i.e., combination of Landsat RGB images and DEM data. Our results suggest that the mean intersection over union (MIoU) using the four-channel data as training samples by a new DL-based pixel-level image segmentation approach is the highest, which can reach 95.5%. The proposed method can accomplish automatic extraction of cone karst landscape by self-learning of deep neural network, and therefore it can also provide a powerful and automatic tool for documenting other type of geological landscapes worldwide.

scholarly journals Crop Classification Method Based on Optimal Feature Selection and Hybrid CNN-RF Networks for Multi-Temporal Remote Sensing Imagery

2020 ◽  
Vol 12 (19) ◽  
pp. 3119
Author(s):  
Shuting Yang ◽  
Lingjia Gu ◽  
Xiaofeng Li ◽  
Tao Jiang ◽  
Ruizhi Ren
Keyword(s):  
Remote Sensing ◽  
Feature Selection ◽  
Random Forest ◽  
Remote Sensing Data ◽  
Optical Remote Sensing ◽  
Remote Sensing Images ◽  
Multi Temporal ◽  
Optimal Feature Selection ◽  
Crop Classification ◽  
Optimal Feature

Although efforts and progress have been made in crop classification using optical remote sensing images, it is still necessary to make full use of the high spatial, temporal, and spectral resolutions of remote sensing images. However, with the increasing volume of remote sensing data, a key emerging issue in the field of crop classification is how to find useful information from massive data to balance classification accuracy and processing time. To address this challenge, we developed a novel crop classification method, combining optimal feature selection (OFSM) with hybrid convolutional neural network-random forest (CNN-RF) networks for multi-temporal optical remote sensing images. This research used 234 features including spectral, segmentation, color, and texture features from three scenes of Sentinel-2 images to identify crop types in the Jilin province of northeast China. To effectively extract the effective features of remote sensing data with lower time requirements, the use of OFSM was proposed with the results compared with two traditional feature selection methods (TFSM): random forest feature importance selection (RF-FI) and random forest recursive feature elimination (RF-RFE). Although the time required for OFSM was 26.05 s, which was between RF-FI with 1.97 s and RF-RFE with 132.54 s, OFSM outperformed RF-FI and RF-RFE in terms of the overall accuracy (OA) of crop classification by 4% and 0.3%, respectively. On the basis of obtaining effective feature information, to further improve the accuracy of crop classification we designed two hybrid CNN-RF networks to leverage the advantages of one-dimensional convolution (Conv1D) and Visual Geometry Group (VGG) with random forest (RF), respectively. Based on the selected optimal features using OFSM, four networks were tested for comparison: Conv1D-RF, VGG-RF, Conv1D, and VGG. Conv1D-RF achieved the highest OA at 94.27% as compared with VGG-RF (93.23%), Conv1D (92.59%), and VGG (91.89%), indicating that the Conv1D-RF method with optimal feature input provides an effective and efficient method of time series representation for multi-temporal crop-type classification.

scholarly journals Region search based on hybrid convolutional neural network in optical remote sensing images

2019 ◽  
Vol 15 (5) ◽  
pp. 155014771985203 ◽  
Author(s):  
Shoulin Yin ◽  
Ye Zhang ◽  
Shahid Karim
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Convolutional Neural Network ◽  
Remote Sensing Data ◽  
Search Method ◽  
Optical Remote Sensing ◽  
Remote Sensing Images ◽  
Candidate Regions ◽  
Region Search ◽  
Fast Region

Currently, big data is a new and hot issue. Particularly, the rapid growth of the Internet of Things causes a sharp growth of data. Enormous amounts of networking sensors are continuously collecting and transmitting data to be stored and processed in the cloud, including remote sensing data, environmental data, and geographical data. And region is regarded as the very important object in remote sensing data, which is mainly researched in this article. Region search is a crucial task in remote sensing process, especially for military area and civilian fields. It is difficult to fast search region accurately and achieve generalizability of the regions’ features due to the complex background information, as well as the smaller size. Especially, when processing region search in large-scale remote sensing image, detailed information as the feature can be extracted in inner region. To overcome the above difficulty region search task, we propose an accurate and fast region search in optical remote sensing images under cloud computing environment, which is based on hybrid convolutional neural network. The proposed region search method partitioned into four processes. First, fully convolutional network is adopted to produce all the candidate regions that contain the possible object regions. This process avoids exhaustive search for input images. Then, the features of all candidate regions are extracted by a fast region-based convolutional neural network structure. Third, we design a new difficult sample mining method for the training process. At the end, in order to improve the region search precision, we use an iterative bounding box regression algorithm to normalize the detected bounding boxes, in which the regions contain candidate objects. The proposed algorithm is evaluated on optical remote sensing images acquired from Google Earth. Finally, we conduct the experiments, and the obtained results show that the proposed region search method constantly achieves better results regardless of the type of images tested. Compared with traditional region search methods, such as region-based convolutional neural network and newest feature extraction frameworks, our proposed methods show better robustness with complex context semantic information and backgrounds.

Band Selection for Forest Stock Volume Estimation in Southern China

2012 ◽  
Vol 500 ◽  
pp. 616-622
Author(s):  
Chen Xi Song ◽  
Zhong Sheng Xia ◽  
Yun Shao ◽  
Feng Li Zhang ◽  
Kun Li ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Southern China ◽  
Remote Sensing Data ◽  
Volume Estimation ◽  
Guizhou Province ◽  
Optical Data ◽  
Optical Remote Sensing ◽  
Optimal Ratio ◽  
Stock Volume ◽  
The Impact

When forest stock volume is quantitative estimated using SPOT-5, QuickBird and ALOS optical data with linear regression model, the optimal ratio of remote sensing band is chosen from the above three types of optical remote sensing data respectively, which is a significant part. In this study, the experiments are taken in Zhazuo Forest of Xiuwen County of Guizhou Province. Comprehensive utilization of the three optical data, the selected ratio of band is confirmed according with characteristics of the forest region. Optimization of the ratio of band remote sensing method used is the criteria of mean residual sum of square called RMSq. In this paper the multicollinearity which commonly exsits between ratio of the original band is analyzed and studied to get rid of its unfavorable influence in this paper. By means of the criteria of mean residual sum of square, the ratio of remote sensing band which determines the impact of forest stock volume estimation is confirmed finally. Conclusions are as follows: Compared with the selected band, multiple-correlation has been greatly reduced. The optimal ratio of remote sensing band such as SP4, SP2-3/2+3, SP 1-4/1+4, SP1*3/2 has an important role on the interpretation of forest stock volume estimation.

scholarly journals Rapid Evaluation and Validation Method of Above Ground Forest Biomass Estimation Using Optical Remote Sensing in Tundi Reserved Forest Area, India

2021 ◽  
Vol 10 (1) ◽  
pp. 29
Author(s):  
Praveen Kumar ◽  
Akhouri P. Krishna ◽  
Thorkild M. Rasmussen ◽  
Mahendra K. Pal
Keyword(s):  
Remote Sensing ◽  
Vegetation Cover ◽  
Remote Sensing Data ◽  
Test Site ◽  
Forest Area ◽  
Relational Model ◽  
Biomass Estimation ◽  
Optical Remote Sensing ◽  
Ground Sample ◽  
Sensing Data

Optical remote sensing data are freely available on a global scale. However, the satellite image processing and analysis for quick, accurate, and precise forest above ground biomass (AGB) evaluation are still challenging and difficult. This paper is aimed to develop a novel method for precise, accurate, and quick evaluation of the forest AGB from optical remote sensing data. Typically, the ground forest AGB was calculated using an empirical model from ground data for biophysical parameters such as tree density, height, and diameter at breast height (DBH) collected from the field at different elevation strata. The ground fraction of vegetation cover (FVC) in each ground sample location was calculated. Then, the fraction of vegetation cover (FVC) from optical remote sensing imagery was calculated. In the first stage of method implementation, the relation model between the ground FVC and ground forest AGB was developed. In the second stage, the relational model was established between image FVC and ground FVC. Finally, both models were fused to derive the relational model between image FVC and forest AGB. The validation of the developed method was demonstrated utilizing Sentinel-2 imagery as test data and the Tundi reserved forest area located in the Dhanbad district of Jharkhand state in eastern India was used as the test site. The result from the developed model was ground validated and also compared with the result from a previously developed crown projected area (CPA)-based forest AGB estimation approach. The results from the developed approach demonstrated superior capabilities in precision compared to the CPA-based method. The average forest AGB estimation of the test site obtained by this approach revealed 463 tons per hectare, which matches the previous estimate from this test site.

scholarly journals An Efficient Decision Support System for Flood Inundation Management Using Intermittent Remote-Sensing Data

2021 ◽  
Vol 13 (14) ◽  
pp. 2818
Author(s):  
Hai Sun ◽  
Xiaoyi Dai ◽  
Wenchi Shou ◽  
Jun Wang ◽  
Xuejing Ruan
Keyword(s):  
Remote Sensing ◽  
Decision Support ◽  
Decision Support System ◽  
Support System ◽  
Water Body ◽  
Remote Sensing Data ◽  
Flood Inundation ◽  
Remote Sensing Images ◽  
Sensing Data ◽  
Tracking Model

Timely acquisition of spatial flood distribution is an essential basis for flood-disaster monitoring and management. Remote-sensing data have been widely used in water-body surveys. However, due to the cloudy weather and complex geomorphic environment, the inability to receive remote-sensing images throughout the day has resulted in some data being missing and unable to provide dynamic and continuous flood inundation process data. To fully and effectively use remote-sensing data, we developed a new decision support system for integrated flood inundation management based on limited and intermittent remote-sensing data. Firstly, we established a new multi-scale water-extraction convolutional neural network named DEU-Net to extract water from remote-sensing images automatically. A specific datasets training method was created for typical region types to separate the water body from the confusing surface features more accurately. Secondly, we built a waterfront contour active tracking model to implicitly describe the flood movement interface. In this way, the flooding process was converted into the numerical solution of the partial differential equation of the boundary function. Space upwind difference format and the time Euler difference format were used to perform the numerical solution. Finally, we established seven indicators that considered regional characteristics and flood-inundation attributes to evaluate flood-disaster losses. The cloud model using the entropy weight method was introduced to account for uncertainties in various parameters. In the end, a decision support system realizing the flood losses risk visualization was developed by using the ArcGIS application programming interface (API). To verify the effectiveness of the model constructed in this paper, we conducted numerical experiments on the model's performance through comparative experiments based on a laboratory scale and actual scale, respectively. The results were as follows: (1) The DEU-Net method had a better capability to accurately extract various water bodies, such as urban water bodies, open-air ponds, plateau lakes etc., than the other comparison methods. (2) The simulation results of the active tracking model had good temporal and spatial consistency with the image extraction results and actual statistical data compared with the synthetic observation data. (3) The application results showed that the system has high computational efficiency and noticeable visualization effects. The research results may provide a scientific basis for the emergency-response decision-making of flood disasters, especially in data-sparse regions.

scholarly journals Some Peculiarities of Arable Soil Organic Matter Detection Using Optical Remote Sensing Data

2021 ◽  
Vol 13 (12) ◽  
pp. 2313
Author(s):  
Elena Prudnikova ◽  
Igor Savin
Keyword(s):  
Remote Sensing ◽  
Organic Matter ◽  
Soil Organic Matter ◽  
Spectral Reflectance ◽  
Remote Sensing Data ◽  
Soil Surface ◽  
Optical Remote Sensing ◽  
Test Field ◽  
Sensing Data ◽  
Sentinel 2

Optical remote sensing only provides information about the very thin surface layer of soil. Rainfall splash alters soil surface properties and its spectral reflectance. We analyzed the impact of rainfall on the success of soil organic matter (SOM) content (% by mass) detection and mapping based on optical remote sensing data. The subject of the study was the arable soils of a test field located in the Tula region (Russia), their spectral reflectance, and Sentinel-2 data. Our research demonstrated that rainfall negatively affects the accuracy of SOM predictions based on Sentinel-2 data. Depending on the average precipitation per day, the R2cv of models varied from 0.67 to 0.72, RMSEcv from 0.64 to 1.1% and RPIQ from 1.4 to 2.3. The incorporation of information on the soil surface state in the model resulted in an increase in accuracy of SOM content detection based on Sentinel-2 data: the R2cv of the models increased up to 0.78 to 0.84, the RMSEcv decreased to 0.61 to 0.71%, and the RPIQ increased to 2.1 to 2.4. Further studies are necessary to identify how the SOM content and composition of the soil surface change under the influence of rainfall for other soils, and to determine the relationships between rainfall-induced SOM changes and soil surface spectral reflectance.

Sign in / Sign up

Export Citation Format

Share Document