Development of a Nonparametric Active Contour Model for Automatic Extraction of Farmland Boundaries from High-Resolution
- PDF / 2,804,056 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 104 Downloads / 162 Views
RESEARCH ARTICLE
Development of a Nonparametric Active Contour Model for Automatic Extraction of Farmland Boundaries from High-Resolution Satellite Imagery Leila Maghsoodi1
•
Hamid Ebadi1 • Mahmod Reza Sahebi1 • Mostafa Kabolizadeh2
Received: 12 July 2018 / Accepted: 16 December 2018 Ó Indian Society of Remote Sensing 2019
Abstract Agricultural field maps are significant sources of data to achieve precision farming. The present research is a step toward generating land use/land cover maps automatically. The primary goal of this research was to develop an area-based model from nonparametric active contour models for agriculture land boundary extraction from IRS P5 satellite images. After investigating two well-known models created from nonparametric active contours, named local binary fitting and multiphase, the local binary fitting model was selected to develop and enhance. Land boundary detection was improved by adding two texture layers to the input images and the development of the external energy function. The local binary fitting model was advanced as a multi-phase model in order to identify several regions in an image. Also, dull image boundaries were better extracted by changing the sigma parameter and regularization term. Evaluation of the proposed method yielded to the overall accuracy, user accuracy, producer accuracy, and kappa coefficient of 89.53%, 65.93%, 86.13%, and 86.52%, respectively. Keywords Farmland boundaries Automatic extraction Panchromatic imagery Active contour model Local binary fitting model Intensity inhomogeneity
Introduction Farmland boundaries are important to generate land use/land cover maps. Also, accurate information about field sizes helps to correctly estimate requirements of farming such as water resources, pesticide, equipment, and harvesting methods. Satellite images extensively cover vast areas of lands and provide adequate information to produce maps and monitor agriculture. Agriculture boundary extraction is challenging and costly to perform manually. Therefore, developing a method to automatically extract boundaries from satellite images is indispensable. To address this problem, numerous automatic and & Leila Maghsoodi [email protected] 1
Department of Photogrammetry and Remote Sensing, Faculty of Geodesy and Geomatics Engineering, K.N. Toosi University of Technology, Tehran, Iran
2
Department of Remote Sensing and GIS, Earth Science Faculty, Shahid Chamran University, Ahvaz, Iran
semiautomatic methods have been developed of which the most important models are reviewed as follows. Torre and Radeva (2000) presented a region competition algorithm to semiautomatically extract field boundaries from aerial images. They integrated the snake and region growing models. This algorithm uses the merit of each component to detect topological relationships between regions. The method is mainly used to extract two types of fields. First is the parcels of highly homogeneous areas and second the parcels surrounded by linear edges. Mueller et al. (2004) proposed a
Data Loading...
