摘要
由一名新闻记者-机器人与机器学习每日新闻的工作人员新闻编辑-机器人学的研究结果-机器人学和自动化在一份新的报告中讨论。根据NewsRx记者从中华人民共和国广州发回的消息，研究表明：“基于点特征的视觉SLAM系统在低纹理环境下的性能明显下降，因为在提取足够可靠的点方面存在挑战。线和点特征的融合通过提供额外的视觉约束来提高SLAM系统的性能。”本研究的经费来自广州市重点研究开发项目。为提高基于点线的SLAM系统的效率和精度，本文介绍了一种高效的点线融合视觉惯性SLAM系统EPL-VINS，提出了LK-RG线段跟踪方法，该方法将Lucas-Kanade(LK)算法与线段检测器(LSD)的区域生长(RG)算法相结合。提出了一种新的直线表示方法,在此基础上构造直线重投影残差,并对后端的空间直线进行了2自由度(2-DoF)优化,该系统基于vins融合技术,支持原有的三种SENSO R套件:带IMU的单目摄像机、立体摄像机、实验结果表明,lk-rg方法处理速度快,线段匹配成功率高。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Research findings on Robotics - Robotics and Auto mation are discussed in a new report. According to news originating from Guangzh ou, People’s Republic of China, by NewsRx correspondents, research stated, “The performance of a visual SLAM system based on point features significantly dimini shes in low-textured environments due to the challenges in extracting sufficient and reliable points. The fusion of line and point features improves SLAM system performance by providing additional visual constraints.” Financial support for this research came from Guangzhou Key Research and Develop ment Program. Our news journalists obtained a quote from the research from Xidian University, “To improve the efficiency and accuracy of the point-line-based SLAM system, thi s letter introduces EPL-VINS, an efficient point-line fusion visual-inertial SLA M system. We present the LK-RG line segment tracking method, which combines the Lucas-Kanade (LK) algorithm with the Region Growing (RG) algorithm from the Line Segment Detector (LSD). Moreover, we introduce a novel representation for spati al lines, based on which we construct line reprojection residuals and conduct a 2-degrees-of-freedom (2-DoF) optimization of spatial lines in the back-end. The proposed system is built upon VINS-Fusion, and supports the original three senso r suites: a monocular with an IMU, stereo cameras, and stereo cameras with an IM U. The experimental results show that the LK-RG method exhibits rapid processing and a high success rate in line segments matching.”
NETL
NSTL