Method and system for learning about road signs using hierarchical clustering

摘要

A method, system, and computer program product is provided, for example, for learning about a road sign using clustering of pre-processed road sign recognition observations. In an example embodiment, the method may include receiving, by a layered clustering system, the pre-processed road sign recognition observations generated by at least one sensor installed on a vehicle. The pre-processed road sign recognition observations include at least two continuous-value attributes. The method may further include creating, by the layered clustering system, a first clustering label corresponding to a first attribute of the at least two continuous-value attributes for generating a plurality of first clusters. Additionally, the method may include sequentially clustering, by the layered clustering system, the pre-processed road sign recognition observations in the plurality of first clusters with the created first clustering label based on a second attribute of the at least two continuous-value attributes for generating a plurality of second clusters. Further, once the clustering of the pre-processed road sign recognition observations has been performed in this way, the method may further include filtering and removing, by the layered clustering system, outliers of the plurality of first clusters and the plurality of second clusters.