LiDAR (Light Detection and Ranging) is an advanced active remote sensing technique working on the principle of time of travel (ToT) for capturing highly accurate 3D information of the surroundings. LiDAR has gained wide attention in research and development with the LiDAR industry expected to reach 2.8 billion $ by 2025. Although the LiDAR dataset is of rich density and high spatial resolution, it is challenging to process LiDAR data due to its inherent 3D geometry and massive volume. But such a high-resolution dataset possesses immense potential in many applications and has great potential in 3D object detection and recognition. In this research we propose Graph Neural Network (GNN) based framework to learn and identify the objects in the 3D LiDAR point clouds. GNNs are class of deep learning which learns the patterns and objects based on the principle of graph learning which have shown success in various 3D computer vision tasks.
翻译:LiDAR(光探测和测距)是一种先进的主动遥感技术,在飞行时间原则(TT)基础上进行,以捕捉周围高度精确的三维信息。LiDAR在研发中得到了广泛的关注,而LiDAR工业预计到2025年将达到28亿美元。虽然LiDAR数据集密度大,空间分辨率高,但处理LiDAR数据具有挑战性,因为其固有的三维几何学和体积巨大。但是这样的高分辨率数据集在许多应用中具有巨大的潜力,在3D对象探测和识别方面具有巨大的潜力。在这个研究中,我们提出了基于图形神经网络的框架,以学习和识别3DLIDAR点云中的天体。GNNS是深层次的学习班级,根据图表学习的原则学习模式和对象,这些模式和对象在各种3D计算机视觉任务中表现出成功。