[IEEE 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) - Xi'an (2018.9.13-2018.9.16)] 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) - A Deep-Learning Based Multi-Modality Sensor Calibration Method for USV

摘要： The automatic obstacle avoidance and other tasks of the unmanned surface vehicle rely on the fusion of multi-modality onboard sensors. The accurate calibration method is the foundation of sensor fusion. This paper proposes an online calibration method based on the deep learning for visual sensor and depth sensor. Through an end-to-end network, we combine feature extraction, feature matching and global optimization process of sensor calibration. After initial training, the network can continuously calibrate multi-modality sensors. It solves the challenges under USV operating environment. In the simulation environment and realistic environment, we conducted a fast online calibration of the camera, LIDAR and depth camera, which showed the effectiveness of the algorithm.