CHANGE DETECTION OF MULTI-TEMPORAL REMOTE SENSING IMAGES BASED ON CONTOURLET TRANSFORM AND ICA

2016 ◽  
Vol 59 (3) ◽  
pp. 255-265
Author(s):  
WU Yi-Quan ◽  
CAO Zhao-Qing ◽  
TAO Fei-Xiang
Keyword(s):  
Remote Sensing ◽  
Change Detection ◽  
Contourlet Transform ◽  
Remote Sensing Images ◽  
Multi Temporal

scholarly journals GRAPH NEURAL NETWORK BASED MULTI-FEATURE FUSION FOR BUILDING CHANGE DETECTION

2021 ◽  
Vol XLIII-B3-2021 ◽  
pp. 377-382
Author(s):  
W. Yuan ◽  
X. Yuan ◽  
Z. Fan ◽  
Z. Guo ◽  
X. Shi ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Change Detection ◽  
Point Cloud ◽  
Feature Fusion ◽  
Experimental Comparison ◽  
3D Point Cloud ◽  
Remote Sensing Images ◽  
Illumination Variations ◽  
Multi Temporal

Abstract. Building Change Detection (BCD) via multi-temporal remote sensing images is essential for various applications such as urban monitoring, urban planning, and disaster assessment. However, most building change detection approaches only extract features from different kinds of remote sensing images for change index determination, which can not determine the insignificant changes of small buildings. Given co-registered multi-temporal remote sensing images, the illumination variations and misregistration errors always lead to inaccurate change detection results. This study investigates the applicability of multi-feature fusion from both directly extract 2D features from remote sensing images and 3D features extracted by the dense image matching (DIM) generated 3D point cloud for accurate building change index generation. This paper introduces a graph neural network (GNN) based end-to-end learning framework for building change detection. The proposed framework includes feature extraction, feature fusion, and change index prediction. It starts with a pre-trained VGG-16 network as a backend and uses U-net architecture with five layers for feature map extraction. The extracted 2D features and 3D features are utilized as input into GNN based feature fusion parts. In the GNN parts, we introduce a flexible context aggregation mechanism based on attention to address the illumination variations and misregistration errors, enabling the framework to reason about the image-based texture information and depth information introduced by DIM generated 3D point cloud jointly. After that, the GNN generated affinity matrix is utilized for change index determination through a Hungarian algorithm. The experiment conducted on a dataset that covered Setagaya-Ku, Tokyo area, shows that the proposed method generated change map achieved the precision of 0.762 and the F1-score of 0.68 at pixel-level. Compared to traditional image-based change detection methods, our approach learns prior over geometrical structure information from the real 3D world, which robust to the misregistration errors. Compared to CNN based methods, the proposed method learns to fuse 2D and 3D features together to represent more comprehensive information for building change index determination. The experimental comparison results demonstrated that the proposed approach outperforms the traditional methods and CNN based methods.

Remote Sensing Dynamic Monitoring on Illegal Capacity Occupation of Reservoir

2013 ◽  
Vol 718-720 ◽  
pp. 1124-1128
Author(s):  
Peng Xiao Chen ◽  
Shao Hong Shen ◽  
Xiong Fei Wen
Keyword(s):  
Remote Sensing ◽  
Change Detection ◽  
High Efficiency ◽  
Dynamic Monitoring ◽  
Measurement Technology ◽  
Volume Data ◽  
Thematic Maps ◽  
Remote Sensing Images ◽  
Position Information ◽  
Multi Temporal

Monitoring the illegally occupied channels is very important for the management and regulations of reservoirs. This paper proposes an automatic and efficient approach to identify the changes in the river course with geographic information system and global position system using multi-temporal remote sensing images. Unlike the traditional river course monitoring system, this approach is mainly based on the change detection information extracting from multi-temporal high spatial resolution remote sensing images. Firstly, change detection from different information of multi-temporal remote sensing images are applied to obtain the change information thematic maps which can be used as working maps for on-site investigation are extracted. Secondly, GPS-RTK measurement technology is used to obtain 3-D position information of the terrain features points in those channel occupied areas. Then, an approach for calculating the volume of the channel occupied area is designed and developed by ArcGIS software using multi-temporal remote sensing images, 3-D position information and historical digital terrain date of channel occupied area. Finally, channel occupied area volume data and thematic maps are acquired by ArcGIS software. The data of reservoir is selected as experimental area, and the experiments have confirmed the high efficiency and accuracy of this approach proposed in this paper.

Sign in / Sign up

Export Citation Format

Share Document