Analysis on Evolution of Landscape Pattern in Dianchi Basin Based on RS and GIS

2011 ◽  
Vol 291-294 ◽  
pp. 3419-3423 ◽  
Author(s):  
Zhao Qin Han ◽  
Jing Ye ◽  
Zhen Wang ◽  
Jie Liu ◽  
Shu Xia Yu
Keyword(s):  
Remote Sensing ◽  
Landscape Metrics ◽  
Landscape Pattern ◽  
Principal Component ◽  
Landscape Fragmentation ◽  
Remote Sensing Images ◽  
Rs And Gis ◽  
Land Use Types ◽  
Landscape Patches ◽  
Landscape Level

With the support of RS, GIS and FRAGSTATS techniques, the landscape pattern has been analyzed quantitatively in Dianchi basin by 16 commonly used landscape metrics, based on remote sensing images of 1988, 1990, 1994, 1999, 2002 and 2008. After performance of principal component analysis (PCA) on the 16 landscape metrics, three principal components (PCs) were generalized: spatial aggregation of landscape patches, landscape fragmentation and landscape diversity. Then, the characteristics and evolution of landscape pattern in Dianchi basin have been explored at the landscape level. The results showed, that, from 1988 to 1994, the landscape fragmentation was serious and the level of diversity was fluctuant. And for some kinds of landscape patches, the integrity was much undermined, the spatial distribution was scattered and the degree of aggregation was fallen. From 1994 to 2008, the degree of aggregation between patches increased gradually. The situation of landscape fragmentation was under control. And, the land use types had a tendency towards diversification and homogenization.

The Driving Forces of Landscape Pattern in Coastal Urban Belt in Liaoning

2012 ◽  
Vol 610-613 ◽  
pp. 3771-3775
Author(s):  
Hai De Hu
Keyword(s):  
Remote Sensing ◽  
Economic Development ◽  
Population Growth ◽  
Landscape Pattern ◽  
Driving Forces ◽  
Landscape Fragmentation ◽  
Field Investigation ◽  
Rapid Population Growth ◽  
Remote Sensing Images ◽  
Growth Economic

Based on field investigation and social-economical data, in combination with the 1992 and 2007 Landsat TM remote sensing images of Coastal Urban Belt in Liaoning, this paper analyzed the driving forces of landscape pattern in the study area. From 1992 to 2007, the landscape pattern in the study area experienced a significant change. The rapid population growth, economic development and infrastructure construction had exerted strong influences on these changes of landscape pattern, and thus leading to a deeper level of landscape fragmentation

scholarly journals The Comparison of Fusion Methods for HSRRSI Considering the Effectiveness of Land Cover (Features) Object Recognition Based on Deep Learning

2019 ◽  
Vol 11 (12) ◽  
pp. 1435 ◽  
Author(s):  
Shiran Song ◽  
Jianhua Liu ◽  
Heng Pu ◽  
Yuan Liu ◽  
Jingyan Luo
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Object Recognition ◽  
Land Cover ◽  
Feature Recognition ◽  
Color Space ◽  
Principal Component ◽  
Remote Sensing Images ◽  
Visual Effect ◽  
Fusion Methods

The efficient and accurate application of deep learning in the remote sensing field largely depends on the pre-processing technology of remote sensing images. Particularly, image fusion is the essential way to achieve the complementarity of the panchromatic band and multispectral bands in high spatial resolution remote sensing images. In this paper, we not only pay attention to the visual effect of fused images, but also focus on the subsequent application effectiveness of information extraction and feature recognition based on fused images. Based on the WorldView-3 images of Tongzhou District of Beijing, we apply the fusion results to conduct the experiments of object recognition of typical urban features based on deep learning. Furthermore, we perform a quantitative analysis for the existing pixel-based mainstream fusion methods of IHS (Intensity-Hue Saturation), PCS (Principal Component Substitution), GS (Gram Schmidt), ELS (Ehlers), HPF (High-Pass Filtering), and HCS (Hyper spherical Color Space) from the perspectives of spectrum, geometric features, and recognition accuracy. The results show that there are apparent differences in visual effect and quantitative index among different fusion methods, and the PCS fusion method has the most satisfying comprehensive effectiveness in the object recognition of land cover (features) based on deep learning.

scholarly journals Novel Multi-Scale Filter Profile-Based Framework for VHR Remote Sensing Image Classification

2019 ◽  
Vol 11 (18) ◽  
pp. 2153
Author(s):  
Zhiyong Lv ◽  
Guangfei Li ◽  
Yixiang Chen ◽  
Jón Atli Benediktsson
Keyword(s):  
Remote Sensing ◽  
Principal Component ◽  
Remote Sensing Image ◽  
Classification Performance ◽  
Remote Sensing Images ◽  
Multi Scale ◽  
Remote Sensing Image Classification ◽  
Very High Spatial Resolution ◽  
Layer Stacking ◽  
Initial Classification

Filter is a well-known tool for noise reduction of very high spatial resolution (VHR) remote sensing images. However, a single-scale filter usually demonstrates limitations in covering various targets with different sizes and shapes in a given image scene. A novel method called multi-scale filter profile (MFP)-based framework (MFPF) is introduced in this study to improve the classification performance of a remote sensing image of VHR and address the aforementioned problem. First, an adaptive filter is extended with a series of parameters for MFP construction. Then, a layer-stacking technique is used to concatenate the MPFs and all the features into a stacked vector. Afterward, principal component analysis, a classical descending dimension algorithm, is performed on the fused profiles to reduce the redundancy of the stacked vector. Finally, the spatial adaptive region of each filter in the MFPs is used for post-processing of the obtained initial classification map through a supervised classifier. This process aims to revise the initial classification map and generate a final classification map. Experimental results performed on the three real VHR remote sensing images demonstrate the effectiveness of the proposed MFPF in comparison with the state-of-the-art methods. Hard-tuning parameters are unnecessary in the application of the proposed approach. Thus, such a method can be conveniently applied in real applications.

Fusing Remote Sensing Images Using a Statistical Model

2012 ◽  
Vol 263-266 ◽  
pp. 416-420 ◽  
Author(s):  
Xiao Qing Luo ◽  
Xiao Jun Wu
Keyword(s):  
Remote Sensing ◽  
Statistical Model ◽  
Image Fusion ◽  
Spatial Information ◽  
Low Frequency ◽  
Principal Component ◽  
Remote Sensing Images ◽  
Entropy Information ◽  
Remote Sensing Image Fusion ◽  
The One

Enhance spectral fusion quality is the one of most significant targets in the field of remote sensing image fusion. In this paper, a statistical model based fusion method is proposed, which is the improved method for fusing remote sensing images on the basis of the framework of Principal Component Analysis(PCA) and wavelet decomposition-based image fusion. PCA is applied to the source images. In order to retain the entropy information of data, we select the principal component axes based on entropy contribution(ECA). The first entropy component and panchromatic image(PAN) are performed a multiresolution decompositon using wavelet transform. The low frequency subband fused by weighted aggregation approach and high frequency subband fused by statistical model. High resolution multispectral image is then obtained by an inverse wavelet and ECA transform. The experimental results demonstrate that the proposed method can retain the spectral information and spatial information in the fusion of PAN and multi-spectral image(MS).

Sign in / Sign up

Export Citation Format

Share Document