3D planes detection is an important task that has numerous applications in urban environments. However, current methods do not deal appropriately with the noise and quantization artifacts of low-cost sensors. In this paper, we present the Scaled Diﬀerence of Normals, a points ﬁlter that addresses these issues and is implemented on top of the Fast and Deterministic Planes Detection Based on Hough Transform. We evaluated its precision by comparing the detected planes coeﬃcients with semi-automatically generated ground truth data and conﬁrmed that when compared to state of the art methods, the proposed method is fast and has superior precision even in the presence of high noise levels, quantization artifacts and several variations in the points distribution caused by registration.
Jaime SANDOVAL†(Student Member), Kazuma UENISHI†(Member), Munetoshi IWAKIRI††(Member), Kiyoshi TANAKA†(Fellow)
†Shinshu University, ††National Defense Academy of Japan