Department of Industrial Engineering, Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju 61186, Korea.
Sensors (Basel). 2022 Aug 26;22(17):6447. doi: 10.3390/s22176447.
Multi-sensor fusion is important in the field of autonomous driving. A basic prerequisite for multi-sensor fusion is calibration between sensors. Such calibrations must be accurate and need to be performed online. Traditional calibration methods have strict rules. In contrast, the latest online calibration methods based on convolutional neural networks (CNNs) have gone beyond the limits of the conventional methods. We propose a novel algorithm for online self-calibration between sensors using voxels and three-dimensional (3D) convolution kernels. The proposed approach has the following features: (1) it is intended for calibration between sensors that measure 3D space; (2) the proposed network is capable of end-to-end learning; (3) the input 3D point cloud is converted to voxel information; (4) it uses five networks that process voxel information, and it improves calibration accuracy through iterative refinement of the output of the five networks and temporal filtering. We use the KITTI and Oxford datasets to evaluate the calibration performance of the proposed method. The proposed method achieves a rotation error of less than 0.1° and a translation error of less than 1 cm on both the KITTI and Oxford datasets.
多传感器融合在自动驾驶领域非常重要。多传感器融合的一个基本前提是传感器之间的校准。这种校准必须准确，并需要在线进行。传统的校准方法有严格的规则。相比之下，基于卷积神经网络 (CNN) 的最新在线校准方法已经超越了传统方法的限制。我们提出了一种使用体素和三维 (3D) 卷积核进行传感器在线自校准的新算法。所提出的方法具有以下特点：(1) 它旨在校准测量 3D 空间的传感器；(2) 所提出的网络能够进行端到端学习；(3) 将输入的 3D 点云转换为体素信息；(4) 使用五个处理体素信息的网络，并通过迭代细化五个网络的输出和时间滤波来提高校准精度。我们使用 KITTI 和牛津数据集来评估所提出方法的校准性能。所提出的方法在 KITTI 和牛津数据集上的旋转误差小于 0.1°，平移误差小于 1cm。
