The invention relates to 3D surface reconstruction with point cloud densification using deep neural networks for autonomous systems and applications. In various examples, a 3D surface structure, such as a 3D surface structure of a road (3D pavement), may be observed and estimated to generate a 3D point cloud or other representation of the 3D surface structure. Since the estimated representation may be sparse, a value of a dense representation of the 3D surface structure may be predicted from the sparse representation using a deep neural network (DNN). For example, a sparse 3D point cloud may be projected to form a sparse projection image (e.g., a sparse 2D height map), which may be fed to a DNN to predict a dense projection image (e.g., a dense 2D height map). The predicted dense representation of the 3D surface structure may be provided to an autonomous vehicle driving stack to enable safe and comfortable planning and control of the autonomous vehicle.
本公开涉及用于自主系统和应用的使用深度神经网络利用点云致密化的3D表面重建。在各种示例中,可以观察和估计诸如道路的3D表面结构(3D路面)的3D表面结构以生成3D表面结构的3D点云或其他表示。由于估计的表示可能是稀疏的,因此可以使用深度神经网络(DNN)从稀疏表示中预测3D表面结构的致密表示的值。例如,稀疏的3D点云可以被投影以形成稀疏的投影图像(例如,稀疏的2D高度图),该图像可以被馈送到DNN以预测致密的投影图像(例如,致密的2D高度图)。3D表面结构的预测的致密表示可以提供给自主车辆驾驶堆栈,以实现对自主车辆的安全和舒适的规划和控制。
3D surface reconstruction with point cloud densification using deep neural networks for autonomous systems and applications
用于自主系统和应用的使用深度神经网络利用点云致密化的3D表面重建
2023-05-02
Patent
Elektronische Ressource
Chinesisch
IPC: | G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Europäisches Patentamt | 2023
|Europäisches Patentamt | 2023
|Europäisches Patentamt | 2023
|Europäisches Patentamt | 2023
|Navigability Assessment for Autonomous Systems Using Deep Neural Networks
BASE | 2017
|