Object-oriented land cover classification using HJ-1 remote sensing imagery

Abstract

The object-oriented information extraction technique was used to improve classification accuracy, and addressed the problem that HJ-1 CCD remote sensing images have only four spectral bands with moderate spatial resolution. We used two key techniques: the selection of optimum image segmentation scale and the development of an appropriate object-oriented information extraction strategy. With the principle of minimizing merge cost of merging neighboring pixels/objects, we used spatial autocorrelation index Moran's I and the variance index to select the optimum segmentation scale. The Nearest Neighborhood (NN) classifier based on sampling and a knowledge-based fuzzy classifier were used in the object-oriented information extraction strategy. In this classification step, feature optimization was used to improve information extraction accuracy using reduced data dimension. These two techniques were applied to land cover information extraction for Shanghai city using a HJ-1 CCD image. Results indicate that the information extraction accuracy of the object-oriented method was much higher than that of the pixel-based method. HJ-1 remote sensing imagery, object-oriented, optimum scale of image segmentation, Nearest Neighborhood (NN) classification, fuzzy classification Citation: Sun Z P, Shen W M, Wei B, et al. Object-oriented land cover classification using HJ-1 remote sensing imagery.The HJ-1 satellite was launched successfully on September 6th 2008 from Taiyuan Satellite Launch Center, and carried two satellites: HJ-1A and HJ-1B. HJ-1A carries two CCD sensors with 30 m spatial resolution and a hyper-spectral sensor with 100 m spatial resolution. HJ-1B carries two identical CCD sensors and an infrared sensor with two kinds of spatial resolution (150 m at near, short-wave and middle-infrared band scope and 300 m at far-infrared band). The return period of the HJ-1 satellite is two days, with synergistic operation of HJ-1A and HJ-1B. The scan width exceeds 700 km with the two satellite CCD sensors working together. This enables HJ-1 CCD remote sensing images covering all lands of China to be captured every two to three days. The HJ-1 CCD remote sensing imagery has high temporal resolution and broad width, enabling rapid, large scale land cover change and environmental monitoring. Information extraction from remote sensing imagery is key for transforming remote sensing imagery to usable geographic data. How to increase information extraction accuracy is an important remote sensing research area [1]. Land cover information extraction is the basis of monitoring of land cover change and the environment. The spatial resolution of HJ-1 CCD images is 30 m, and this kind of remote sensing image is suitable for rapid land cover information extraction over large areas. However, associating with the

Modeling Land Surface Reflectance Coupled BRDF for HJ-1/CCD Data of Rugged Terrain in Heihe River Basin, China

“…The instrument has been used extensively for retrieving land surface parameters, such as land cover [22], leaf area index (LAI) [23], photosynthetically active radiation (PAR) [24], and land surface albedo [25]. HJ-1 is uniquely combines two satellites in the constellation (HJ-1A/B) that have a phase difference of 180 • within the same orbit [26].…”

Development of environmental monitoring satellite systems in China

“…The special issue "Key Technologies in Application of HJ-1A/B Satellite Data" has exhibited the new productions and key technologies in the applications of HJ-1A/B satellites, which covered studies in various fields of environmental remote sensing. The research contents include basal technologies of analyses of data features, image registration [18] and analyses of scaling effects [19], environmental monitors of land cover [20], surface water [21,22], urban heat island effect [23] and plague natural epidemic foci [24], and quantitative retrieval of aerosol optical thickness [25], photosynthetically active radiation [26], shrub LAI [27], forest aboveground biomass [28]. These papers reflect the recognitions on the data applications of environmental satellites to various fields, and also demonstrate the directions for the future development of environmental satellites in China.…”

Distributed and hierarchical object-based image analysis for damage assessment: a case study of 2008 Wenchuan earthquake, China

“…It takes into account not only the spectral information but also shape, texture, contextual, topological and semantic information with meaningful image objects (Burnett & Blaschke 2003;Wiseman et al 2009). On the other hand, it can solve the problem of classifying complex objects, addresses the phenomenon of the same objects having different spectra and different objects having the same spectrum (Xie et al 2008;Sun et al 2010). Image segmentation, the first step of OBIA is to subdivide an image with determined criteria of homogeneity and heterogeneity in order to generate objects (Akcay & Aksoy 2008;Blaschke 2010;Martha et al 2011).…”