一种改进的地下车库弱纹理下智能汽车即时定位与建图算法  

An Improved Simultaneous Localization and Mapping Algorithm for Smart Cars under Weak Texture in Underground Garages

作　　者：李辉[1] 王金刚[1] 张小俊[1] LI Hui;WANG Jin-gang;ZHANG Xiao-jun(School of Mechanical Engineering, Hebei University of Technology, Tianjin 300130, China)

机构地区：[1]河北工业大学机械工程学院,天津300130

出　　处：《科学技术与工程》2021年第24期10369-10375,共7页Science Technology and Engineering

基　　金：天津市新一代人工智能科技重大专项(18ZXZNGX00230)。

摘　　要：地下车库中纯视觉的即时定位与建图(simultaneous localization and mapping,SLAM)方法无法克服光线不足和弱特征纹理两大不利因素,为此,提出一种基于VINS-Mono框架下改进的视觉惯导融合算法,把原算法中提取Harris角点的方法改进为提取灰度值陡变的像素点,并使用非线性优化方法在初始化阶段进行视觉位姿估计。后端采用滑动窗口的形式建立先验估计残差、惯性测量单元(inertial measurement unit,IMU)残差以及基于灰度值不变原理构建的视觉残差的联合残差模型,进一步提升了系统底层变量的优化效果,从而提高算法的定位准确度。通过基于EuRoc数据集的仿真实验和地下车库实际场景的实车实验,验证了所提算法的鲁棒性和精确性。The pure visual SLAM(simultaneous localization and mapping)method in the underground garage cannot overcome two major disadvantages:insufficient light and weak feature texture.For this reason,a visual inertial navigation fusion algorithm that is improved based on the VINS-Mono framework was proposed.The method of extracting the Harris corner points from the original algorithm was improved to the method of extracting the pixels with sharp changes in gray value,and the nonlinear optimization method was applied to estimate the visual pose in the initialization stage.A sliding window was used at the back-end to establish a priori estimation residual,an inertial measurement unit(IMU)residual,and a joint residual model of visual residual that were constructed based on the principle of invariable gray value.The optimization effect of the system’s underlying variables is thus improved,so is the positioning accuracy of the algorithm.The robustness and accuracy of the proposed algorithm are verified through the EuRoc dataset-based simulation experiments and the real car experiments in the actual scene of the underground garage.

关 键 词：即时定位与建图(SLAM) 弱特征纹理 灰度值陡变 视觉位姿估计 地下车库 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] U461.99[自动化与计算机技术—控制科学与工程]