An Efficient L-Shape Fitting Method for Vehicle Pose Detection with 2D LiDAR

TL;DR

This paper introduces a fast and robust L-shape fitting algorithm for vehicle detection using 2D LiDAR, offering an efficient alternative to deep learning methods that typically rely on image or 3D data.

Contribution

The paper presents a novel, search-based L-shape fitting method that decomposes the problem into vertex searching and corner localization, reducing computational complexity.

Findings

High efficiency and robustness in on-road experiments

Effective detection of vehicle positions and orientations

Applicable to various driving conditions

Abstract

Detecting vehicles with strong robustness and high efficiency has become one of the key capabilities of fully autonomous driving cars. This topic has already been widely studied by GPU-accelerated deep learning approaches using image sensors and 3D LiDAR, however, few studies seek to address it with a horizontally mounted 2D laser scanner. 2D laser scanner is equipped on almost every autonomous vehicle for its superiorities in the field of view, lighting invariance, high accuracy and relatively low price. In this paper, we propose a highly efficient search-based L-Shape fitting algorithm for detecting positions and orientations of vehicles with a 2D laser scanner. Differing from the approach to formulating LShape fitting as a complex optimization problem, our method decomposes the L-Shape fitting into two steps: L-Shape vertexes searching and L-Shape corner localization. Our approach is computationally efficient due to its minimized complexity. In on-road experiments, our approach is capable of adapting to various circumstances with high efficiency and robustness.