低光照环境下基于轻量级SuperPoint的单目VI-SLAM算法  

Monocular VI-SLAM Algorithm Based on Lightweight SuperPoint Network in Low-Light Environment

作　　者：曾旭东 樊绍胜[1,2] 续尚植 周宇霆 Zeng Xudong;Fan Shaosheng;Xu Shangzhi;Zhou Yuting(School of Electrical and Information Engineering,Changsha University of Science and Technology,Changsha 410111,Hunan,China;Hunan Provincial Key Laboratory of Electric Power Robotics,Changsha 410111,Hunan,China)

机构地区：[1]长沙理工大学电气与信息工程学院,湖南长沙410111 [2]电力机器人湖南省重点实验室,湖南长沙410111

出　　处：《激光与光电子学进展》2024年第18期177-188,共12页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(62271087);湖南省研究生科研创新项目(CX20220918)。

摘　　要：视觉惯性同时定位与建图技术(SLAM)通过融合视觉与惯性约束项提升建图与定位的精度,然而在低光照环境下,视觉前端提取特征点的质量与跟踪稳定性差,导致视觉惯性SLAM算法跟踪易丢失,定位精度低。因此,基于VINSMono框架,提出一种单目视觉惯性SLAM算法——GS-VINS:首先,采用自适应图像增强算法,改善低光照图像的灰度分布;其次,提出基于SuperPoint的GN2_SuperPoint特征检测网络,结合特征点动态跟踪模块,提高光流跟踪的稳定性。在EuRoc数据集与现实场景的实验表明,所提算法定位精度较VINS-Mono提升了26.57%,且对光照变化具有较强的鲁棒性,在对比实验中特征跟踪成功率提高了8%,现实场景中闭合误差缩小约45.73%。所提算法在低光照环境中具有较好的精度与稳定性,为低光照下的视觉导航提供了新的解决方案,具有工程应用价值。Visual inertial simultaneous localization and mapping(SLAM)technology improves the accuracy of mapping and positioning by considering relevant visual and inertial constraints.However,in low-light environments,the quality of feature point extraction and tracking stability at the visual front-end are poor,which leads to easy loss of tracking and low positioning accuracy in the visual inertial SLAM algorithm.Therefore,we propose a monocular inertial SLAM algorithm called GSVINS based on the VINS-Mono framework.First,an adaptive image enhancement algorithm is used to enhance the grayscale distribution of low-light images.Then,a GN2_SuperPoint feature point detection network is proposed,and it is combined with a feature point dynamic tracking module to improve the stability of optical flow tracking.Experiments on the EuRoC dataset and in real-world scenarios show that the proposed algorithm improves localization accuracy by 26.57%compared to VINS-Mono and it demonstrates strong robustness to changes in lighting.In the comparison experiment,the success rate of the feature tracking increases by 8%,and the closure error in real-world scenarios is reduced by~45.73%.The proposed algorithm shows good accuracy and stability in low-light environments and provides a novel solution for visual navigation under low-light conditions,thereby offering valuable engineering applications.

关 键 词：同时定位与建图 视觉惯性系统 低光照环境 光流跟踪 位姿估计 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]