An Intelligent Agent Based Land Encroachment Detection Approach

Abstract

Land management and planning is essential to assist the economic growth, sustainable resource use and environmental protection of a city. This paper describes a novel approach to automatic encroachment detection to assist in land management decision making. The approach begins with training the agent to identify and understand the land cover/use features (such as buildings, parks, trees and roads) that are predominant in the region of interest, and carries out segmentation on the park data using the intelligent agent developed from the training samples. Experiments on park images from Auckland New Zealand show the effectiveness of the proposed approach.