基于规则的多种类型海岸线TM/ETM+影像智能检测方法

A coastline is defined as the average spring tide line. Different types of seacoast, such as sandy, silty, and bio- logical coast, have different indicators of interpretation. It is very difficult to develop a universal method for interpreting all shorelines. Therefore, the sandy, the silty, and the biological coast are regarded as research objects, and with data mining technolog,found the rules of interpretation of those three types of coastlines. Then, an intelligent coastline interpretation method based on rules was proposed. Firstly, the rules for ex- tracting the waterline in Landsat TM/ETM＋ （Thematic Mapper/Enhanced Thematic Mapper Plus） imagery were discovered. Then, through analyzing the features of sandy, silty and biological coast, the indicators of interpreting different types of shoreline were determined. According to the indicators, the waterline could be corrected to the real coastline. In order to verify the validity of the proposed algorithms, three Landsat TM/ETM＋ imageries were selected for case studies. The experimental results showed that the proposed methods could interpret the coastlines of sandy; silty, and biological coasts with high precision and without human intervention, which exceeded three pixels.

An intelligent coastline interpretation of several types of seacoasts from TM/ETM+ images based on rules

A coastline is defined as the average spring tide line. Different types of seacoast, such as sandy, silty, and biological coast, have different indicators of interpretation. It is very difficult to develop a universal method for interpreting all shorelines. Therefore, the sandy, the silty, and the biological coast are regarded as research objects, and with data mining technology, found the rules of interpretation of those three types of coastlines. Then, an intelligent coastline interpretation method based on rules was proposed. Firstly, the rules for extracting the waterline in Landsat TM/ETM+ (Thematic Mapper/Enhanced Thematic Mapper Plus) imagery were discovered. Then, through analyzing the features of sandy, silty and biological coast, the indicators of interpreting different types of shoreline were determined. According to the indicators, the waterline could be corrected to the real coastline. In order to verify the validity of the proposed algorithms, three Landsat TM/ETM+ imageries were selected for case studies. The experimental results showed that the proposed methods could interpret the coastlines of sandy, silty, and biological coasts with high precision and without human intervention, which exceeded three pixels.