Joint Calibration of Panoramic Camera and Lidar Based on Supervised Learning

Objective: In view of contemporary panoramic camera-laser scanner system, the accuracy of traditional calibration method based on the target feature is not stable and multiple calibrations are needed. The method based on statistical optimization has the disadvantage that the requirement of the number of laser scanner’s channels is relatively high. Calibration equipments with extreme accuracy for panoramic camera-laser scanner system are costly. Facing all these in the calibration of panoramic camera-laser scanner system, a method based on supervised learning is proposed. Method: Firstly, corresponding feature points of panoramic images and point clouds are gained to generate the training dataset by designing a round calibration object. Furthermore, the traditional calibration problem is transformed into a multiple nonlinear regression optimization problem by designing a supervised learning network with preprocessing of the panoramic imaging model. Back propagation algorithm is utilized to regress the rotation and translation matrix with high accuracy. Result: Experimental results show that this method can quickly regress the calibration parameters and the accuracy is better than the traditional calibration method based on the target feature and the method based on statistical optimization. Conclusion: The calibration accuracy of this method meets the practical requirements, and it is less time-consuming and more highly-automated.