Optimal Segmentation Scale Selection for Object-Based Change Detection in Remote Sensing Images Using Kullback–Leibler Divergence

2020 ◽  
Vol 17 (7) ◽  
pp. 1124-1128 ◽  
Author(s):  
Junzheng Wu ◽  
Biao Li ◽  
Weiping Ni ◽  
Weidong Yan ◽  
Han Zhang
Keyword(s):  
Remote Sensing ◽  
Change Detection ◽  
Scale Selection ◽  
Remote Sensing Images ◽  
Object Based ◽  
Leibler Divergence ◽  
Optimal Segmentation ◽  
Selection For

Object-based change detection for VHR remote sensing images based on a Trisiamese-LSTM

2020 ◽  
Vol 41 (16) ◽  
pp. 6209-6231
Author(s):  
Ran Jing ◽  
Shuang Liu ◽  
Zhaoning Gong ◽  
Zhiheng Wang ◽  
Hongliang Guan ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Change Detection ◽  
Remote Sensing Images ◽  
Object Based

scholarly journals Detecting Large-Scale Urban Land Cover Changes from Very High Resolution Remote Sensing Images Using CNN-Based Classification

2019 ◽  
Vol 8 (4) ◽  
pp. 189 ◽  
Author(s):  
Chi Zhang ◽  
Shiqing Wei ◽  
Shunping Ji ◽  
Meng Lu
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Land Cover ◽  
Change Detection ◽  
Land Cover Classification ◽  
Remote Sensing Images ◽  
Urban Land Cover ◽  
Object Based ◽  
Very High ◽  
Change Map

The study investigates land use/cover classification and change detection of urban areas from very high resolution (VHR) remote sensing images using deep learning-based methods. Firstly, we introduce a fully Atrous convolutional neural network (FACNN) to learn the land cover classification. In the FACNN an encoder, consisting of full Atrous convolution layers, is proposed for extracting scale robust features from VHR images. Then, a pixel-based change map is produced based on the classification map of current images and an outdated land cover geographical information system (GIS) map. Both polygon-based and object-based change detection accuracy is investigated, where a polygon is the unit of the GIS map and an object consists of those adjacent changed pixels on the pixel-based change map. The test data covers a rapidly developing city of Wuhan (8000 km2), China, consisting of 0.5 m ground resolution aerial images acquired in 2014, and 1 m ground resolution Beijing-2 satellite images in 2017, and their land cover GIS maps. Testing results showed that our FACNN greatly exceeded several recent convolutional neural networks in land cover classification. Second, the object-based change detection could achieve much better results than a pixel-based method, and provide accurate change maps to facilitate manual urban land cover updating.

Sign in / Sign up

Export Citation Format

Share Document