论文标题
视觉大满贯的动态对象跟踪和掩盖
Dynamic Object Tracking and Masking for Visual SLAM
论文作者
论文摘要
在动态环境中，视觉大满贯技术的性能会受到移动对象采取的视觉特征的损害。一种解决方案是识别这些对象，以便可以删除其视觉特征以进行本地化和映射。本文提出了一条简单而快速的管道，该管道使用深度神经网络，扩展的卡尔曼过滤器和视觉量来改善动态环境中的本地化和映射（在GTX 1080上约为14 fps）。与其他最新方法相比，使用RTAB-MAP作为Visual SLAM，使用RTAB-MAP作为视觉量的动态序列的结果表明，与其他最先进的方法相比，该方法实现了相似的定位性能，同时还提供了跟踪的动态对象的位置，没有这些动态对象的3D映射，没有这些动态对象，可以更好地循环闭合检测，可以在机器人以中等速度上运行整个旋转式。
In dynamic environments, performance of visual SLAM techniques can be impaired by visual features taken from moving objects. One solution is to identify those objects so that their visual features can be removed for localization and mapping. This paper presents a simple and fast pipeline that uses deep neural networks, extended Kalman filters and visual SLAM to improve both localization and mapping in dynamic environments (around 14 fps on a GTX 1080). Results on the dynamic sequences from the TUM dataset using RTAB-Map as visual SLAM suggest that the approach achieves similar localization performance compared to other state-of-the-art methods, while also providing the position of the tracked dynamic objects, a 3D map free of those dynamic objects, better loop closure detection with the whole pipeline able to run on a robot moving at moderate speed.
