Parallelizing maximum likelihood classification on computer cluster and graphics processing unit for supervised image classification

ABSTRACT

Supervised image classification has been widely utilized in a variety of remote sensing applications. When large volume of satellite imagery data and aerial photos are increasingly available, high-performance image processing solutions are required to handle large scale of data. This paper introduces how maximum likelihood classification approach is parallelized for implementation on a computer cluster and a graphics processing unit to achieve high performance when processing big imagery data. The solution is scalable and satisfies the need of change detection, object identification, and exploratory analysis on large-scale high-resolution imagery data in remote sensing applications.     

Markov random field-based method for super-resolution mapping of forest encroachment from remotely sensed ASTER image

Forest encroachment (FE) is a problem in Andaman and Nicobar Islands (ANI) in India for environment and planning. Small gaps created in the forest slowly expand its periphery disturbing the biodiversity. Therefore, intrusion of poachers, slash and burn and other factors causing FE must be carefully detected and monitored. Remote sensing offers a great opportunity to accomplish this task because of its synoptic view. Conventional classification methods with remotely sensed images are problematic because of small size of FE and mixed landcover composition. This study presents an application of super-resolution mapping (SRM) based on Markov random field for detection of FE using ASTER (15 m) images. The SRM results were validated using multispectral IRS LISS-IV (5.8 m) image. Non-contiguous FE patches of various sizes and shapes are characterized using the spatial contextual information. The novelty of this approach lies in the identification and separability of small FE pockets which could not be achieved with pixel-based maximum likelihood classifier (MLC). The SRM parameters were optimized and found comparable to previous studies. Classification accuracy obtained with SRM at scale factor 3 is κ = 0.62 that is superior to accuracy of MLC (κ = 0.51). SRM is a promising tool for detection and monitoring of FE at Rutland Island in ANI, India.     

视觉感受与Markov随机场相结合的高分辨率遥感影像分割法

鉴于视觉感受对外界强大的感知与识别能力,模拟视觉神经感知的工作机制,并结合Markov随机场模型,提出一种影像分割方法。首先,分析视觉感知系统的工作机制,将其特性归纳为等级层次性、学习能力、特征检测能力和稀疏编码特性,继而利用小波变换、非监督聚类、特征分析和Laplace分布模拟视觉工作机制,然后结合Markov随机场模型实现高分辨率遥感影像的分割。通过不同卫星的真实遥感影像进行了相关试验。试验结果表明本文提出的方法在高分辨率遥感影像分割任务中有非常良好的表现。     

An automated and optimized approach for online spatial biodiversity model: a case study of OGC web processing service

An online spatial biodiversity model (SBM) for optimized and automated spatial modelling and analysis of geospatial data is proposed, which is based on web processing service (WPS) and web service orchestration (WSO) in parallel computing environment. The developed model integrates distributed geospatial data in geoscientific processing workflow to compute the algorithms of spatial landscape indices over the web using free and open source software. A case study for Uttarakhand state of India demonstrates the model outputs such as spatial biodiversity disturbance index (SBDI) and spatial biological richness index (SBRI). In order to optimize and automate, an interactive web interface is developed using participatory GIS approaches for implementing fuzzy AHP. In addition, sensitivity analysis and geosimulation experiments are also performed under distributed GIS environment. Results suggest that parallel algorithms in SBM execute faster than sequential algorithms and validation of SBRI with biological diversity shows significant correlation by indicating high R² values.