Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Rural Geo-Information Extraction Based on GNSS Data Mining

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Paper number  131595114,  2013 Kansas City, Missouri, July 21 - July 24, 2013. (doi: http://dx.doi.org/10.13031/aim.20131595114) @2013
Authors:   Yaping Cai, Caicong Wu, Jing Zhao
Keywords:   GNSS data mining rural geo-information object extraction information update

Abstract. The number of agricultural machinery association (AMS) has risen with an annual increase over ten thousands in China. To meet the management and scheduling demand of agricultural machinery for AMS, we have developed the agricultural machinery monitoring and scheduling system based on Google Map, and collected millions of historical position data of agricultural machinery using GNSS terminals. Since POIs, farmland, and road networks in rural area are often missing on electronic maps, they should be marked on map manually and update at least once a year, which are both time-consuming and labor-intensive. To meet this demand, we use data mining method to extract rural geo-information from historical position database, which contains geo-information such as garages, gas stations, repair shops, farmland, and rural road networks. In this paper, with the datasets of divided position points, the method to calculate point, line, and surface characteristics are generated. Method for dividing point sets is based on agricultural machinery operation statuses, which can be recognized automatically by our already developed data mining method. Since point information extraction is relatively simple, this paper mainly discusses the method of extracting line and surface information that are road topology and farmland shape. Remote sensing image with high resolution is used to examine the effectiveness of this method in order to improve accuracy of extracted geo-information. Some rural geo-information of two districts in Beijing is extracted through this method, which shows that it is applicable.

(Download PDF)    (Export to EndNotes)