The Development of GPS Trajectory Filter for Agricultural Machinery Application

In Taiwan, the number of licensed agricultural machinery has exceeded 200,000 according to the latest statistics from the Ministry of Agriculture (MOA). Therefore, intelligent management of these machinery becomes both interesting and important. In most research studies, a GPS tracker is installed on some target machine, so that the working efficiency of such machine can be analyzed with its movement trajectory. However, we have observed that the pre-processing stage of agricultural trajectories is rarely discussed. By referring to the concept of image processing, in this paper we propose a filter for trajectories from agricultural machinery. The motivation of this filter is to generate a new trajectory, which keeps the shape of the raw trajectory but achieves better data presentation. Experimental results show that our approach can benefit the application of GPS on agricultural machinery, which offers a potential opportunity for intelligent services.