vS-Graphs: Tightly Coupling Visual SLAM and 3D Scene Graphs Exploiting Hierarchical Scene Understanding
Ali Tourani, Saad Ejaz, Hriday Bavle, Miguel Fernandez-Cortizas, David Morilla-Cabello, Jose Luis Sanchez-Lopez, and Holger Voos
当前视觉同步定位和映射(VSLAM)系统经常难以创建语义丰富且易于解释的地图。 虽然将语义场景知识有助于构建更丰富的地图,在映射对象之间具有上下文关联,但以结构化格式(如场景图)表示它们,但并没有被广泛解决,导致复杂的地图理解和有限的可扩展性。 本文介绍了 vS-Graphs,这是一种新颖的实时 VSLAM 框架,将基于视觉的场景理解与地图重建和可理解的基于图形的表示相结合。 该框架从检测到的建筑组件(即墙壁和地面)中推断出结构元素(即房间和地板),并将其集成到可优化的3D场景图中。 此解决方案增强了重建地图的语义丰富性、可理解性和本地化准确性。 对标准基准和真实世界数据集进行的广泛实验表明,与最先进的VSLAM方法相比,vS-Graphs在所有测试数据集中平均获得了15.22%的准确率。 此外,拟议的框架仅使用可视化功能,实现了环境驱动的语义实体检测精度,与基于激光雷达的精确框架相当。 该代码可在https://github.com/snt-arg/visual_sgraphs上公开查阅,并正在积极改进。 此外,可查阅https://snt-arg.github.io/vsgraphs-results/,其中包含更多媒体和评价成果的网页。
Current Visual Simultaneous Localization and Mapping (VSLAM) systems often struggle to create maps that are both semantically rich and easily interpretable. While incorporating semantic scene knowledge aids in building richer maps with contextual associations among mapped objects, representing them in structured formats, such as scene graphs, has not been widely addressed, resulting in complex map comprehension and limited scalability. This paper introduces vS-Graphs, a novel real-time VSLAM fra...