Scan Science and Technology
Contact Leading Edge Experts & Companies
Built-Up Area
The Experts below are selected from a list of 17868 Experts worldwide ranked by ideXlab platform
Zuoqi Chen – 1st expert on this subject based on the ideXlab platform
-
Urban Built-Up Area Extraction From Log- Transformed NPP-VIIRS Nighttime Light Composite Data
IEEE Geoscience and Remote Sensing Letters, 2018Co-Authors: Bailang Yu, Min Tang, Qiusheng Wu, Chengshu Yang, Shunqiang Deng, Chen Peng, Jianping Wu, Zuoqi ChenAbstract:Accurate information on urban Areas at regional and global scales is required for various socioeconomic and environmental applications. The nighttime light (NTL) composite data have proven to be an effective data source for extracting urban Areas. Various urban mapping methods have been proposed in the literature to extract urban Built-Up Areas from the Defense Meteorological Satellite Program’s Operational Linescan System NTL data with a variable accuracy. However, most of the previous methods cannot be directly applied to the NTL data derived from the Suomi National Polar-orbiting Partnership Satellite with the Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) sensor onboard. In this letter, we introduced a logarithmic transformation to preprocess the NPP-VIIRS NTL composite data. Then, four popular methods for urban Built-Up Area extraction were tested using the original and log-transformed NTL data, respectively. The selected methods included the thresholding technique, Sobel-based edge detection, neighborhood statistics analysis, and watershed segmentation. The accuracy of the results was evaluated through validating the urban Areas derived using each method against the referenced urban Areas obtained from the National Land Cover Database for the U.S.. The results indicated that logarithmic transformation is an effective procedure for enhancing the difference between urban Built-Up Areas and nonurban Areas. The selected methods for urban Built-Up Area extraction were found to perform better on the log-transformed NTL data than the original NTL data.
Shengzhou Xiong – 2nd expert on this subject based on the ideXlab platform
-
Multi-branch convolutional neural network for Built-Up Area extraction from remote sensing image
Neurocomputing, 2019Co-Authors: Shengzhou XiongAbstract:Abstract Built-Up Area is one of the most important objects of remote sensing images analysis, therefore extracting Built-Up Area from remote sensing image automatically has attracted wide attention. It is common to treat Built-Up Area extraction as image segmentation task. However, it’s hard to devise a handcrafted feature to describe Built-Up Area since it contains many non-Built-Up elements, such as trees, grasslands, and small ponds. Besides, Built-Up Area corresponds to large size local region without precise boundary in remote sensing image so that the precision of segmentation in pixel level is not reliable. To cope with the problem of Built-Up Area extraction, a segmentation framework based on deep feature learning and graph model is proposed. The segmentation procedure comprises of three steps. Firstly, the image is divided into small patches whose deep features are extracted by the devised lightweight multi-branch convolutional neural network (LMB-CNN). Secondly, a patch-wise graph model is constructed according to the learnt features, and then is optimized to segment Built-Up Area with patch-level precision in full frame of remote sensing image. At last, post-processing step is also adopted to make the segmentation result visually intact. The experiments verify that the proposed method shows excellent performance by achieving high overall accuracy over 98.6% on Gaofen-2 remote sensing image data with size of 10240 × 10240.
-
Precise Extraction of Built-Up Area Using Deep Features
IGARSS 2018 – 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018Co-Authors: Shengzhou Xiong, Yaming LiAbstract:Built-Up Area is one of the most important objects in remote sensing image analysis, therefore extracting Built-Up Area automatically has attracted wide attention. Deep convolution neural network (CNN) was proposed to improve poor generalization ability of artificial features which had been adopted by traditional automatic extraction methods. In this paper, a more efficient CNN model is proposed to extract the deep features of remote sensing images, and then a graph model based on deep features is constructed to the full image for Built-Up Area extraction. The experiments demonstrate that it has very good performance on the satellite remote sensing image data set.
-
IGARSS – Precise Extraction of Built-Up Area Using Deep Features
IGARSS 2018 – 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018Co-Authors: Shengzhou Xiong, Yaming LiAbstract:Built-Up Area is one of the most important objects in remote sensing image analysis, therefore extracting Built-Up Area automatically has attracted wide attention. Deep convolution neural network (CNN) was proposed to improve poor generalization ability of artificial features which had been adopted by traditional automatic extraction methods. In this paper, a more efficient CNN model is proposed to extract the deep features of remote sensing images, and then a graph model based on deep features is constructed to the full image for Built-Up Area extraction. The experiments demonstrate that it has very good performance on the satellite remote sensing image data set.
Peijun Li – 3rd expert on this subject based on the ideXlab platform
-
Urban Built-Up Area Change Detection Using Multi-Band Temporal Texture and One-Class Random Forest
2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp), 2019Co-Authors: Xiaoxue Feng, Peijun LiAbstract:High spatial resolution multi-temporal data provide more spatial details for mapping and monitoring urban land change from unbuilt to Built-Up Areas. Spatio-temporal contextual information has been recognized as useful features in identification of urban land expansion. This paper adopts a multi-band temporal texture measure with pseudo cross multivariate variogram (PCMV) to quantify local spatiotemporal dependence between bi-temporal multispectral images. The multi-band temporal texture features obtained are combined with bi-temporal multispectral images to detect urban Built-Up Area change using direct multi-temporal image classification. One-class random forest (OCRF), a recently proposed one-class classifier, is used in multi-temporal image classification by sampling one specific class of interest, i.e., Built-Up Area expansion. Experimental results demonstrated that the incorporation of multi-band temporal textures outperformed that using spectral features alone, with increases of 10.55% and 1.74% in overall accuracy, for SPOT-5 and Sentinel-2 data, respectively. Similarly, its overall accuracy is 11.08% and 0.24% higher than incorporating single-band temporal textures. The inclusion of PCMV multi-band temporal texture in direct multi-temporal image classification by OCRF is found effective in urban Built-Up Area change detection.
-
An alternative method of urban Built-Up Area extraction using Landsat time series data
2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016Co-Authors: Jun Zhang, Peijun Li, Hongwei Zhang, Shu Peng, Ming LiAbstract:Urban Built-Up Area information is pivotal to understand complex drivers and mechanisms in global climate change application. However, Built-Up Area extraction using Landsat time series data is a challenging task due to spatial-temporal expression and modeling of land cover types. To provide insights into the intra-annual dynamics of land use change, focusing on how time series characteristics improves recognition of urban , this paper presents an alternative method to Built-Up Area extraction using intra-annual time series of Landsat images. The central premise of the approach is that time series characteristics is firstly expressed by using spectral data, index and feature. The random forests algorithm is then used in classification process for Built-Up Area extraction. The proposed method is further compared with methods using single temporal Landsat data, using features selected by laplacian score and using different classifiers. Results demonstrate that the proposed method improves the accuracy of urban Area extraction.
-
IGARSS – An alternative method of urban Built-Up Area extraction using Landsat time series data
2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016Co-Authors: Jun Zhang, Peijun Li, Hongwei Zhang, Shu Peng, Ming LiAbstract:Urban Built-Up Area information is pivotal to understand complex drivers and mechanisms in global climate change application. However, Built-Up Area extraction using Landsat time series data is a challenging task due to spatial-temporal expression and modeling of land cover types. To provide insights into the intra-annual dynamics of land use change, focusing on how time series characteristics improves recognition of urban , this paper presents an alternative method to Built-Up Area extraction using intra-annual time series of Landsat images. The central premise of the approach is that time series characteristics is firstly expressed by using spectral data, index and feature. The random forests algorithm is then used in classification process for Built-Up Area extraction. The proposed method is further compared with methods using single temporal Landsat data, using features selected by laplacian score and using different classifiers. Results demonstrate that the proposed method improves the accuracy of urban Area extraction.