Feature extraction and matching are the basic parts of many robotic vision tasks, such as 2D or 3D object detection, recognition, and registration. As known, 2D feature extraction and matching have already been achieved great success. Unfortunately, in the field of 3D, the current methods fail to support the extensive application of 3D LiDAR sensors in robotic vision tasks, due to the poor descriptiveness and inefficiency. To address this limitation, we propose a novel 3D feature representation method: Linear Keypoints representation for 3D LiDAR point cloud, called LinK3D. The novelty of LinK3D lies in that it fully considers the characteristics (such as the sparsity, and complexity of scenes) of LiDAR point clouds, and represents the keypoint with its robust neighbor keypoints, which provide strong distinction in the description of the keypoint. The proposed LinK3D has been evaluated on two public datasets (i.e., KITTI, Steven VLP16), and the experimental results show that our method greatly outperforms the state-of-the-art in matching performance. More importantly, LinK3D shows excellent real-time performance, faster than the sensor frame rate at 10 Hz of a typical rotating LiDAR sensor. LinK3D only takes an average of 32 milliseconds to extract features from the point cloud collected by a 64-beam LiDAR, and takes merely about 8 milliseconds to match two LiDAR scans when executed in a notebook with an Intel Core i7 @2.2 GHz processor. Moreover, our method can be widely extended to various 3D vision applications. In this paper, we apply the proposed LinK3D to the LiDAR odometry and place recognition task of LiDAR SLAM. The experimental results show that our method can improve the efficiency and accuracy of LiDAR SLAM system.

翻译：特征提取与匹配是许多机器人视觉任务（如2D或3D目标检测、识别与配准）的基础环节。众所周知，2D特征提取与匹配已取得巨大成功。然而在3D领域，由于现有方法描述能力弱且效率低下，无法支持3D LiDAR传感器在机器人视觉任务中的广泛应用。为解决这一局限，我们提出一种新颖的3D特征表示方法：面向3D LiDAR点云的线性关键点表示（Linear Keypoints representation for 3D LiDAR point cloud），简称LinkK3D。LinkK3D的创新之处在于充分考虑LiDAR点云特性（如稀疏性和场景复杂性），通过鲁棒邻域关键点表征目标关键点，从而为关键点描述提供强区分性。所提出的LinkK3D已在两个公开数据集（即KITTI、Steven VLP16）上进行评估，实验结果表明，该方法在匹配性能上大幅超越当前最优技术。更重要的是，LinkK3D展现出卓越的实时性能，处理速度超过典型旋转式LiDAR传感器10Hz的帧率。当在配备Intel Core i7 @2.2 GHz处理器的笔记本上运行时，LinkK3D平均仅需32毫秒即可从64线LiDAR采集的点云中提取特征，仅需约8毫秒即可完成两帧LiDAR扫描的匹配。此外，我们的方法可广泛扩展到各类3D视觉应用。本文还将所提出的LinkK3D应用于LiDAR SLAM的里程计与位置识别任务，实验结果表明，该方法能够提升LiDAR SLAM系统的效率与精度。