Prediction-based geometric feature extraction for 2D laser scanner

This paper presents a novel algorithm for detecting line and circle features from 2D laser range scans. Unlike the conventional methods that use two stages for separating the features: data segmentation and feature separation in each segment, the proposed algorithm adopts a new structure and thus the computation complexity is much reduced. Moreover, it does not depend on prior knowledge of the environment, and it requires a minimum number of points per segment. We utilize prediction to achieve the above goals, so the algorithm is named prediction-based feature extraction (PFE). The efficiency and accuracy of the method is demonstrated by the experiments results.

Research highlights
► A novel method to extract geometric features from 2D laser data is proposed.
► New process structure, compacter and faster, low computation complexity are proposed.
► Running independently, no prior knowledge is needed.
► It has a minimal number of points per segment, adaptive to different environments.