Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments
Semantic SLAM With More Accurate Point Cloud Map in Dynamic Environments
复制标题
DOI：
10.1109/access.2020.3003160
复制
发表时间：
2020-01-01
期刊：
影响因子：
3.9
通讯作者：
Han, Hong
中科院分区：
文献类型：
--
作者：
Fan, Yingchun;Zhang, Qichi;Han, Hong
静态环境是目前大多数基于视觉的SLAM系统正常工作的前提条件，这极大地限制了SLAM在现实环境中的应用。动态环境下SLAM系统构建的全局点云地图的质量与相机位姿估计和局部点云地图中噪声块的去除有关。大多数动态SLAM系统主要是提高摄像机定位精度，而很少研究噪声块去除。在本文中，我们提出了一种新的语义SLAM系统，更准确的点云地图在动态环境中。我们通过BlitzNet获得了图像中动态对象的遮罩和包围盒。通过分析动态对象的遮罩在包围盒中的深度统计信息，实现动态对象遮罩的扩展。通过几何分割后的形态学操作去除由动态对象的残留信息产生的孤岛。利用包围盒将图像快速划分为环境区域和动态区域，利用环境区域中深度稳定的匹配点构造极线约束，定位动态区域中的静态匹配点。为了验证我们提出的SLAM系统的偏好，我们在TUM RGB-D数据集上进行了实验。与现有的动态SLAM系统相比，本系统构建的全局点云地图是最好的。
Static environment is a prerequisite for most existing vision-based SLAM (simultaneous localization and mapping) systems to work properly, which greatly limits the use of SLAM in real-world environments. The quality of the global point cloud map constructed by the SLAM system in a dynamic environment is related to the camera pose estimation and the removal of noise blocks in the local point cloud maps. Most dynamic SLAM systems mainly improve the accuracy of camera localization, but rarely study on noise blocks removal. In this paper, we proposed a novel semantic SLAM system with a more accurate point cloud map in dynamic environments. We obtained the masks and bounding boxes of the dynamic objects in the images by BlitzNet. The mask of a dynamic object was extended by analyzing the depth statistical information of the mask in the bounding box. The islands generated by the residual information of dynamic objects were removed by a morphological operation after geometric segmentation. With the bounding boxes, the images can be quickly divided into environment regions and dynamic regions, so the depth-stable matching points in the environment regions are used to construct epipolar constraints to locate the static matching points in the dynamic regions. In order to verify the preference of our proposed SLAM system, we conduct the experiments on the TUM RGB-D datasets. Compared with the state-of-the-art dynamic SLAM systems, the global point cloud map constructed by our system is the best.