scholarly journals High-Resolution Remote-Sensing Image-Change Detection Based on Morphological Attribute Profiles and Decision Fusion

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-17
Author(s):  
Chao Wang ◽  
Hui Liu ◽  
Yi Shen ◽  
Kaiguang Zhao ◽  
Hongyan Xing ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Change Detection ◽  
Land Surface ◽  
Spatial Information ◽  
Decision Fusion ◽  
Information Modeling ◽  
Observation Data ◽  
Scale Parameters ◽  
Morphological Attribute

Change detection (CD) is essential for accurate understanding of land surface changes with multitemporal Earth observation data. Due to the great advantages in spatial information modeling, Morphological Attribute Profiles (MAPs) are becoming increasingly popular for improving the recognition ability in CD applications. However, most of the MAPs-based CD methods are implemented by setting the scale parameters of Attribute Profiles (APs) manually and ignoring the uncertainty of change information from different sources. To address these issues, a novel method for CD in high-resolution remote sensing (HRRS) images based on morphological attribute profiles and decision fusion is proposed in this study. By establishing the objective function based on the minimum of average interscale correlation, a morphological attribute profile with adaptive scale parameters (ASP-MAPs) is presented to exploit the spatial structure information. On this basis, a multifeature decision fusion framework based on the Dempster–Shafer (D-S) theory is constructed for obtaining the CD map. Experiments of multitemporal HRRS images from different sensors have shown that the proposed method outperforms the other advanced comparison CD methods, and the overall accuracy (OA) can reach more than 83.9%.

scholarly journals End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++

2019 ◽  
Vol 11 (11) ◽  
pp. 1382 ◽  
Author(s):  
Daifeng Peng ◽  
Yongjun Zhang ◽  
Haiyan Guan
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Change Detection ◽  
Land Surface ◽  
Satellite Image ◽  
Feature Representation ◽  
Observation Data ◽  
Feature Maps ◽  
High Resolution Satellite Images ◽  
End To End

Change detection (CD) is essential to the accurate understanding of land surface changes using available Earth observation data. Due to the great advantages in deep feature representation and nonlinear problem modeling, deep learning is becoming increasingly popular to solve CD tasks in remote-sensing community. However, most existing deep learning-based CD methods are implemented by either generating difference images using deep features or learning change relations between pixel patches, which leads to error accumulation problems since many intermediate processing steps are needed to obtain final change maps. To address the above-mentioned issues, a novel end-to-end CD method is proposed based on an effective encoder-decoder architecture for semantic segmentation named UNet++, where change maps could be learned from scratch using available annotated datasets. Firstly, co-registered image pairs are concatenated as an input for the improved UNet++ network, where both global and fine-grained information can be utilized to generate feature maps with high spatial accuracy. Then, the fusion strategy of multiple side outputs is adopted to combine change maps from different semantic levels, thereby generating a final change map with high accuracy. The effectiveness and reliability of our proposed CD method are verified on very-high-resolution (VHR) satellite image datasets. Extensive experimental results have shown that our proposed approach outperforms the other state-of-the-art CD methods.

scholarly journals Automatic Building Detection from High-Resolution Remote Sensing Images Based on Joint Optimization and Decision Fusion of Morphological Attribute Profiles

2021 ◽  
Vol 13 (3) ◽  
pp. 357 ◽  
Author(s):  
Chao Wang ◽  
Yan Zhang ◽  
Xiaohui Chen ◽  
Hao Jiang ◽  
Mithun Mukherjee ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Decision Fusion ◽  
Joint Optimization ◽  
Selection Strategy ◽  
Building Detection ◽  
Adaptive Selection ◽  
Processing Step ◽  
Morphological Attribute ◽  
Selection Of

High-resolution remote sensing (HRRS) images, when used for building detection, play a key role in urban planning and other fields. Compared with the deep learning methods, the method based on morphological attribute profiles (MAPs) exhibits good performance in the absence of massive annotated samples. MAPs have been proven to have a strong ability for extracting detailed characterizations of buildings with multiple attributes and scales. So far, a great deal of attention has been paid to this application. Nevertheless, the constraints of rational selection of attribute scales and evidence conflicts between attributes should be overcome, so as to establish reliable unsupervised detection models. To this end, this research proposes a joint optimization and fusion building detection method for MAPs. In the pre-processing step, the set of candidate building objects are extracted by image segmentation and a set of discriminant rules. Second, the differential profiles of MAPs are screened by using a genetic algorithm and a cross-probability adaptive selection strategy is proposed; on this basis, an unsupervised decision fusion framework is established by constructing a novel statistics-space building index (SSBI). Finally, the automated detection of buildings is realized. We show that the proposed method is significantly better than the state-of-the-art methods on HRRS images with different groups of different regions and different sensors, and overall accuracy (OA) of our proposed method is more than 91.9%.

scholarly journals Adaptive Feature Weighted Fusion Nested U-Net with Discrete Wavelet Transform for Change Detection of High-Resolution Remote Sensing Images

2021 ◽  
Vol 13 (24) ◽  
pp. 4971
Author(s):  
Congcong Wang ◽  
Wenbin Sun ◽  
Deqin Fan ◽  
Xiaoding Liu ◽  
Zhi Zhang
Keyword(s):  
Remote Sensing ◽  
Wavelet Transform ◽  
High Resolution ◽  
Change Detection ◽  
Discrete Wavelet Transform ◽  
Spatial Information ◽  
Discrete Wavelet ◽  
Remote Sensing Images ◽  
Weighted Fusion ◽  
Objects Detection

The characteristics of a wide variety of scales about objects and complex texture features of high-resolution remote sensing images make deep learning-based change detection methods the mainstream method. However, existing deep learning methods have problems with spatial information loss and insufficient feature representation, resulting in unsatisfactory effects of small objects detection and boundary positioning in high-resolution remote sensing images change detection. To address the problems, a network architecture based on 2-dimensional discrete wavelet transform and adaptive feature weighted fusion is proposed. The proposed network takes Siamese network and Nested U-Net as the backbone; 2-dimensional discrete wavelet transform is used to replace the pooling layer; and the inverse transform is used to replace the upsampling to realize image reconstruction, reduce the loss of spatial information, and fully retain the original image information. In this way, the proposed network can accurately detect changed objects of different scales and reconstruct change maps with clear boundaries. Furthermore, different feature fusion methods of different stages are proposed to fully integrate multi-scale and multi-level features and improve the comprehensive representation ability of features, so as to achieve a more refined change detection effect while reducing pseudo-changes. To verify the effectiveness and advancement of the proposed method, it is compared with seven state-of-the-art methods on two datasets of Lebedev and SenseTime from the three aspects of quantitative analysis, qualitative analysis, and efficiency analysis, and the effectiveness of proposed modules is validated by an ablation study. The results of quantitative analysis and efficiency analysis show that, under the premise of taking into account the operation efficiency, our method can improve the recall while ensuring the detection precision, and realize the improvement of the overall detection performance. Specifically, it shows an average improvement of 37.9% and 12.35% on recall, and 34.76% and 11.88% on F1 with the Lebedev and SenseTime datasets, respectively, compared to other methods. The qualitative analysis shows that our method has better performance on small objects detection and boundary positioning than other methods, and a more refined change map can be obtained.

scholarly journals Assessment of High Resolution Air Temperature Fields at Rocky Mountain National Park by Combining Scarce Point Measurements with Elevation and Remote Sensing Data

2020 ◽  
Vol 13 (1) ◽  
pp. 113
Author(s):  
Antonio-Juan Collados-Lara ◽  
Steven R. Fassnacht ◽  
Eulogio Pardo-Igúzquiza ◽  
David Pulido-Velazquez
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Air Temperature ◽  
Land Surface ◽  
National Park ◽  
Rocky Mountain ◽  
Rocky Mountain National Park ◽  
Temperature Fields ◽  
Lapse Rate ◽  
Validation Experiment

There is necessity of considering air temperature to simulate the hydrology and management within water resources systems. In many cases, a big issue is considering the scarcity of data due to poor accessibility and limited funds. This paper proposes a methodology to obtain high resolution air temperature fields by combining scarce point measurements with elevation data and land surface temperature (LST) data from remote sensing. The available station data (SNOTEL stations) are sparse at Rocky Mountain National Park, necessitating the inclusion of correlated and well-sampled variables to assess the spatial variability of air temperature. Different geostatistical approaches and weighted solutions thereof were employed to obtain air temperature fields. These estimates were compared with two relatively direct solutions, the LST (MODIS) and a lapse rate-based interpolation technique. The methodology was evaluated using data from different seasons. The performance of the techniques was assessed through a cross validation experiment. In both cases, the weighted kriging with external drift solution (considering LST and elevation) showed the best results, with a mean squared error of 3.7 and 3.6 °C2 for the application and validation, respectively.

scholarly journals High-Resolution Monitoring and Assessment of Evapotranspiration and Gross Primary Production Using Remote Sensing in a Typical Arid Region

Land ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 396
Author(s):  
Junxia Yan ◽  
Yanfei Ma ◽  
Dongyun Zhang ◽  
Zechen Li ◽  
Weike Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Land Surface ◽  
Arid Region ◽  
Management Practices ◽  
Gross Primary Production ◽  
Irrigation District ◽  
Heihe River ◽  
Freshwater Resource ◽  
Oasis Area

Land surface evapotranspiration (ET) and gross primary productivity (GPP) are critical components in terrestrial ecosystems with water and carbon cycles. Large-scale, high-resolution, and accurately quantified ET and GPP values are important fundamental data for freshwater resource management and help in understanding terrestrial carbon and water cycles in an arid region. In this study, the revised surface energy balance system (SEBS) model and MOD17 GPP algorithm were used to estimate daily ET and GPP at 100 m resolution based on multi-source satellite remote sensing data to obtain surface biophysical parameters and meteorological forcing data as input variables for the model in the midstream oasis area of the Heihe River Basin (HRB) from 2010 to 2016. Then, we further calculated the ecosystem water-use efficiency (WUE). We validated the daily ET, GPP, and WUE from ground observations at a crop oasis station and conducted spatial intercomparisons of monthly and annual ET, GPP, and WUE at the irrigation district and cropland oasis scales. The site-level evaluation results show that ET and GPP had better performance than WUE at the daily time scale. Specifically, the deviations in the daily ET, GPP, and WUE data compared with ground observations were small, with a root mean square error (RMSE) and mean absolute percent error (MAPE) of 0.75 mm/day and 26.59%, 1.13 gC/m2 and 36.62%, and 0.50 gC/kgH2O and 39.83%, respectively. The regional annual ET, GPP, and WUE varied from 300 to 700 mm, 200 to 650 gC/m2, and 0.5 to 1.0 gC/kgH2O, respectively, over the entire irrigation oasis area. It was found that annual ET and GPP were greater than 550 mm and 500 gC/m2, and annual oasis cropland WUE had strong invariability and was maintained at approximately 0.85 gC/kgH2O. The spatial intercomparisons from 2010 to 2016 revealed that ET had similar spatial patterns to GPP due to tightly coupled carbon and water fluxes. However, the WUE spatiotemporal patterns were slightly different from both ET and GPP, particularly in the early and late growing seasons for the oasis area. Our results demonstrate that spatial full coverage and reasonably fine spatiotemporal variation and variability could significantly improve our understanding of water-saving irrigation strategies and oasis agricultural water management practices in the face of water shortage issues.

scholarly journals HRCNet: High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images

2020 ◽  
Vol 13 (1) ◽  
pp. 71
Author(s):  
Zhiyong Xu ◽  
Weicun Zhang ◽  
Tianxiang Zhang ◽  
Jiangyun Li
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
High Resolution ◽  
Spatial Information ◽  
Semantic Segmentation ◽  
Context Information ◽  
Remote Sensing Images ◽  
Global Context ◽  
Boundary Information ◽  
Extraction Stage

Semantic segmentation is a significant method in remote sensing image (RSIs) processing and has been widely used in various applications. Conventional convolutional neural network (CNN)-based semantic segmentation methods are likely to lose the spatial information in the feature extraction stage and usually pay little attention to global context information. Moreover, the imbalance of category scale and uncertain boundary information meanwhile exists in RSIs, which also brings a challenging problem to the semantic segmentation task. To overcome these problems, a high-resolution context extraction network (HRCNet) based on a high-resolution network (HRNet) is proposed in this paper. In this approach, the HRNet structure is adopted to keep the spatial information. Moreover, the light-weight dual attention (LDA) module is designed to obtain global context information in the feature extraction stage and the feature enhancement feature pyramid (FEFP) structure is promoted and employed to fuse the contextual information of different scales. In addition, to achieve the boundary information, we design the boundary aware (BA) module combined with the boundary aware loss (BAloss) function. The experimental results evaluated on Potsdam and Vaihingen datasets show that the proposed approach can significantly improve the boundary and segmentation performance up to 92.0% and 92.3% on overall accuracy scores, respectively. As a consequence, it is envisaged that the proposed HRCNet model will be an advantage in remote sensing images segmentation.

scholarly journals Change Detection Method of High Resolution Remote Sensing Image Based on D-S Evidence Theory Feature Fusion

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 4673-4687
Author(s):  
Jixiang Zhao ◽  
Shanwei Liu ◽  
Jianhua Wan ◽  
Muhammad Yasir ◽  
Huayu Li
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Change Detection ◽  
Detection Method ◽  
Feature Fusion ◽  
Evidence Theory ◽  
Remote Sensing Image

scholarly journals High resolution remote sensing image segmentation based on graph theory and fractal net evolution approach

2015 ◽  
Vol XL-7/W4 ◽  
pp. 197-201 ◽  
Author(s):  
Y. Yang ◽  
H. T. Li ◽  
Y. S. Han ◽  
H. Y. Gu
Keyword(s):  
Remote Sensing ◽  
Image Segmentation ◽  
Graph Theory ◽  
High Resolution ◽  
Spatial Information ◽  
Remote Sensing Image ◽  
Sensing Applications ◽  
Initial Object ◽  
Object Layer ◽  
Evolution Approach

Image segmentation is the foundation of further object-oriented image analysis, understanding and recognition. It is one of the key technologies in high resolution remote sensing applications. In this paper, a new fast image segmentation algorithm for high resolution remote sensing imagery is proposed, which is based on graph theory and fractal net evolution approach (FNEA). Firstly, an image is modelled as a weighted undirected graph, where nodes correspond to pixels, and edges connect adjacent pixels. An initial object layer can be obtained efficiently from graph-based segmentation, which runs in time nearly linear in the number of image pixels. Then FNEA starts with the initial object layer and a pairwise merge of its neighbour object with the aim to minimize the resulting summed heterogeneity. Furthermore, according to the character of different features in high resolution remote sensing image, three different merging criterions for image objects based on spectral and spatial information are adopted. Finally, compared with the commercial remote sensing software eCognition, the experimental results demonstrate that the efficiency of the algorithm has significantly improved, and the result can maintain good feature boundaries.

Sign in / Sign up

Export Citation Format

Share Document