This paper demonstrates a visual SLAM system that utilizes point and line cloud for robust camera localization, simultaneously, with an embedded piece-wise planar reconstruction (PPR) module which in all provides a structural map. To build a scale consistent map in parallel with tracking, such as employing a single camera brings the challenge of reconstructing geometric primitives with scale ambiguity, and further introduces the difficulty in graph optimization of bundle adjustment (BA). We address these problems by proposing several run-time optimizations on the reconstructed lines and planes. The system is then extended with depth and stereo sensors based on the design of the monocular framework. The results show that our proposed SLAM tightly incorporates the semantic features to boost both frontend tracking as well as backend optimization. We evaluate our system exhaustively on various datasets, and open-source our code for the community (https://github.com/PeterFWS/Structure-PLP-SLAM).
翻译:本文展示了一个视觉的SLMM系统,该系统利用点和线云进行稳健的照相机定位,同时有一个嵌入的片段计划重建模块(PPR)提供结构图。要建立一个与跟踪平行的、规模一致的地图,例如使用单一的相机带来重建具有比例模糊度的几何原始的挑战,并进一步引入了捆绑调整(BA)的图形优化方面的困难。我们提出在重建的线条和飞机上进行一些运行时间优化的建议,以解决这些问题。然后根据单体框架的设计,以深度和立体传感器扩展该系统。结果显示,我们提议的SLAM严格结合了语义特征,以推进前端跟踪和后端优化。我们对各种数据集进行了详尽的评估,并为社区打开了我们的代码(https://github.com/PeterFWS/strucure-PLP-SLAM)。