arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.00072cs.CVeess.IV
收藏

基于视觉SLAM的动态目标跟踪与掩蔽

Dynamic Object Tracking and Masking for Visual SLAM

Institut du Véhicule Innovant (IVI)(创新车辆研究所(IVI))

Jonathan Vincent, Mathieu Labbé, Jean-Samuel Lauzon, François Grondin, Pier-Marc Comtois-Rivet, François Michaud

摘要:

在动态环境中,视觉SLAM技术的性能可能受到从移动对象获取的视觉特征的损害。一种解决方案是识别这些对象,以便可以移除它们的视觉特征以进行定位和映射。本文提出了一种简单而快速的流水线,该流水线使用深度神经网络、扩展卡尔曼滤波器和视觉SLAM来改进动态环境中的定位和映射(在GTX 1080上约14 fps)。使用RTAB-Map作为视觉SLAM的TUM数据集的动态序列的结果表明,与其他最先进的方法相比,该方法实现了类似的定位性能,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地图,更好的环路闭合检测,整个管道能够在以中等速度移动的机器人上运行。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑