基于LDSO的机器人视觉定位与稠密建图的应用

李奎霖; 魏武; 高勇; 李艳杰; 王栋梁

Chinese

您当前的位置：

首页 >

文章列表页 >

基于LDSO的机器人视觉定位与稠密建图的应用

更新时间：2026-09-04

- 基于LDSO的机器人视觉定位与稠密建图的应用
- Application of robot visual localization and dense mapping based on LDSO
- 微电子学与计算机 2020年37卷第2期页码：51-56
- 作者机构：
  
  华南理工大学自动化科学与工程学院,广东,广州,510640
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61573148广东省科技计划项目 2016A040403012广东省省级科技计划项目 2017B090901043
- DOI：
  中图分类号：
- 纸质出版：2020
- 稿件说明：
移动端阅览
李奎霖, 魏武, 高勇, 李艳杰, 王栋梁. 基于LDSO的机器人视觉定位与稠密建图的应用[J]. 微电子学与计算机, 2020, 37(2): 51-56.

LI Kui-lin, WEI Wu, GAO Yong, et al. Application of robot visual localization and dense mapping based on LDSO[J]. 2020, 37(2): 51-56.
李奎霖, 魏武, 高勇, 李艳杰, 王栋梁. 基于LDSO的机器人视觉定位与稠密建图的应用[J]. 微电子学与计算机, 2020, 37(2): 51-56. DOI：

LI Kui-lin, WEI Wu, GAO Yong, et al. Application of robot visual localization and dense mapping based on LDSO[J]. 2020, 37(2): 51-56. DOI：

摘要

针对基于特征点匹配的SLAM(Simultaneous Localization and Mapping)系统在缺乏角点的弱纹理区域无法提取足够的特征点而导致位姿估计失败等问题，提出应用直接视觉里程计算法LDSO(Direct Sparse Odometry with Loop Closure)进行室内机器人视觉定位并结合深度估计或深度相机采集到的关键帧深度图，关键帧相机位姿，原始关键帧图像数据，点云拼接生成三维点云稠密地图，实验结果表明，机器人可在复杂环境中准确快速的定位自身位置，且算法在没有全局BA(Bundle Adjustment)的情况下通过位姿图优化显著减少了旋转，平移与尺度漂移等累积误差，算法整体性能与基于特征点匹配的SLAM系统相媲美，耗时更少，实时性更佳，在缺乏角点区域具有较强的鲁棒性.

Abstract

For the SLAM system based on feature point matching

the problem of pose estimation failure is due to the inability to extract enough feature points in weak texture regions lacking corner points. Applying direct visual odometry method LDSO for indoor robot visual localization and combined with depth estimation or depth camera acquired key frame depth image

key frame camera pose

original key frame image data

point cloud stitching to generate 3D point cloud dense map

experimental results shows that the robot can be in a complex environment Accurate and fast localization

and the algorithm significantly reduces the cumulative error of rotation

translation and proportional drift by pose optimization without global Bundle Adjustment

so that the overall performance is comparable to SLAM systems based on feature point matching

the algorithm takes less time

has better real-time performance and is more robust in areas lacking corner points.

关键词

Keywords

references

GAO X, WANG R, DEMMEL N, et al. LDSO: Direct Sparse Odometry with Loop Closure[C]// International Conference on Intelligent Robots and Systems. Madrid, Spain 2018.

SIBLEY G, MEI C, REID I, et al. Vast-scale Outdoor Navigation Using Adaptive Relative Bundle Adjustment[J]. International Journal of Robotics Research, 2010, 29(8):958-980. DOI: 958

GALVEZ-LOPEZ D, TARDOS J D. Bags of Binary Words for Fast Place Recognition in Image Sequences[J]. IEEE Transactions on Robotics, 2012, 28(5):1188-1197. DOI: 1188

MUR-ARTAL R, MONTIEL J M M, TARDOS J D. ORB-SLAM: a Versatile and Accurate Monocular SLAM System[J]. IEEE Transactions on Robotics, 2015, 31(5):1147-1163. DOI: 1147

FORSTER C, PIZZOLI M, DAVIDE SCARAMUZZA*. SVO: Fast Semi- Direct Monocular Visual Odometry[C]// IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 2014. IEEE, 2014.

Berlin, Germany ENGEL J, THOMAS SCHÖPS, CREMERS D. LSD-SLAM: Large-Scale Direct Monocular SLAM[M]. Berlin, Germany: Springer, 2014: 834-849. DOI: 834

ENGEL J, KOLTUN V, CREMERS D. Direct Sparse Odometry[J]. IEEE Transactions on Pattern Analysis % Machine Intelligence, 2018, 40(3): 611- 625. DOI: 611

KLEIN G, MURRAY D. Parallel Tracking and Mapping for Small AR Workspaces[C]// Mixed and Augmented Reality, 2007. ISMAR 2007. 6th IEEE and ACM International Symposium on. ACM, 2007.

HARTLY R, ZISSERMAN A. Multiple view geometry in computer vision[J]. Kybernetes, 2008, 30(9/10):1865-1872. DOI: 1865

TRIGGS B, HARTLEY R I, et al. Bundle Adjustment -A Modern Synthesis[C]// Proceedings of the International Workshop on Vision Algorithms : Theory and Practice, 1999. Springer-Verlag, 1999: 298-372.

ENGEL J, JüRGEN STURM, CREMERS D. Semi-dense Visual Odometry for a Monocular Camera[C]// Proceedings of the 2013 IEEE International Conference on Computer Vision. IEEE, 2013.

PIZZOLI M, FORSTER C, SCARAMUZZA D. Remode: Probabilistic, monocular dense reconstruction in real time[C]. // Proc of IEEE International Conference on Robotics and Automation. Piscataway, NJ: IEEE Press, 2014: 2609-2616.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于变分法的SLAM视觉里程计优化方法

大模型发展综述：从BERT到Deepseek的技术演进

基于反向体偏置的高增益稳定性高温运放设计

注意力机制与改进密集卷积引导的信息隐藏模型

超低功耗实时时钟电路的设计