Abstract
LiDAR and cameras have been broadly utilized in computer vision and autonomous vehicle applications. However, in order to convert data between the local coordinate systems, we must estimate the rigid body transformation between the sensors. In this paper, we propose a robust extrinsic calibration algorithm that can be implemented easily and has small calibration error. The extrinsic calibration parameters are estimated by minimizing the distance between corresponding features projected onto the image plane. The features are edge and centerline features on a v-shaped calibration target. The proposed algorithm contributes two ways to improve the calibration accuracy. First, we use different weights to distance between a point and a line feature according to the correspondence accuracy of the features. Second, we apply a penalizing function to exclude the influence of outliers in the calibration datasets. Additionally, based on our robust calibration approach for a single LiDAR-camera pair, we introduce a joint calibration that estimates the extrinsic parameters of multiple sensors at once by minimizing one objective function with loop closing constraints. We conduct several experiments to evaluate the performance of our extrinsic calibration algorithm. The experimental results show that our calibration method has better performance than the other approaches.
Highlights
In recent years, an increasing amount of interest and research effort has been put toward autonomous vehicles from both commercial and military sectors
The contributions of this paper are three-fold: (1) we introduce new extrinsic calibration approaches to improve the performance of the existing approaches, the weighted and robust calibration algorithms; (2) we propose a joint calibration method of multiple sensors with loop-closing constraints; (3) we provide extensive experimental comparisons with state-of-the-art approaches and statistical analyses of the proposed calibration approach
We evaluate the performance of the proposed extrinsic calibration approaches explained in Sections 5 and 6 respectively
Summary
An increasing amount of interest and research effort has been put toward autonomous vehicles from both commercial and military sectors. For safer and more robust navigation, autonomous vehicle should utilize all sensors mounted on the vehicle to perceive and understand the scene around. The vehicle should be able to detect objects, classify the environment and analyze the condition of the road surface. A vision sensor provides rich information, it has weaknesses, such as a narrow field of view and poor behavior in rapid illumination changes. LiDAR overcomes such drawbacks of the vision sensor. LiDAR provides sparser data, it is equipped with a wider field of view, highly accurate depth measurement and robustness to environmental change. Perception systems with sensory fusion have shown better results in various literature works [1,2,3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
