一种用于无人机室内定位的改进ORB光流算法

doi:10.3778/j.issn.1002-8331.1912-0058

计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (4): 266-271.DOI: 10.3778/j.issn.1002-8331.1912-0058

一种用于无人机室内定位的改进ORB光流算法

於小杰，贺勇，刘盛华

长沙理工大学电气与信息工程学院，长沙 410000

出版日期:2021-02-15 发布日期:2021-02-06

Improved ORB Feature Optical Flow Algorithm for Indoor Positioning of Unmanned Aerial Vehicle

YU Xiaojie, HE Yong, LIU Shenghua

School of Electrical and Information Engineering, Changsha University of Science & Technology, Changsha 410000, China

Online:2021-02-15 Published:2021-02-06

摘要/Abstract

摘要：

针对无人机室内无GPS的导航定位问题，结合ORB特征与LK金字塔光流，提出了一种改进的ORB特征光流算法。采用ORB算法提取每帧图像的特征点，送入金字塔中估计下一帧点集坐标；采用前后双向单追踪策略进行粗匹配；采用FLANN-KNN匹配规则和前后双向双追踪策略组成的精匹配，进行误匹配点集的滤除。通过多种场景提取效果和无人机实际应用两部分实验，从实时性和精确性对算法性能进行了验证分析。仿真结果表明，改进算法具有较好的定位效果和较好的实时性。

关键词: 无人机（UAV）, 光流法, 室内定位, ORB

Abstract:

In view of the navigation and positioning problem of Unmanned Aerial Vehicle（UAV） without GPS in rooms, an improved ORB feature optical flow algorithm is proposed, combined with ORB feature and LK pyramid optical flow. Firstly, the ORB algorithm is used to extract the feature points of each frame, and puts them into the pyramid to estimate the coordinates of these points in next frame. Secondly, the rough matching, a forward and backward tracking strategy, is carried out to filter these points. Finally, the fine matching, which is composed of the FLANN-KNN matching rule and two-way double tracking strategy, is used to filter out mismatched point sets. The algorithm performance is verified and analyzed from real-time and accuracy through the experiments, which include a variety of scene extraction effects and practical application of UAVs. The results of simulations show that the proposed improved algorithm has better positioning effect and better real-time performance.

Key words: Unmanned Aerial Vehicle（UAV）, optical flow, indoor positioning, ORB

於小杰，贺勇，刘盛华. 一种用于无人机室内定位的改进ORB光流算法[J]. 计算机工程与应用, 2021, 57(4): 266-271.

YU Xiaojie, HE Yong, LIU Shenghua. Improved ORB Feature Optical Flow Algorithm for Indoor Positioning of Unmanned Aerial Vehicle[J]. Computer Engineering and Applications, 2021, 57(4): 266-271.

[1]	雍玖，王阳萍，党建武，雷晓妹. 改进TLD与ORB的AR系统长时跟踪注册方法[J]. 计算机工程与应用, 2021, 57(7): 178-184.
[2]	李中道，刘元盛，常飞翔，张军，路铭. 室内环境下UWB与LiDAR融合定位算法研究[J]. 计算机工程与应用, 2021, 57(6): 260-266.
[3]	杨世强，白乐乐，赵成，王国栋，李德信. 一种改进的Qtree_ORB算法[J]. 计算机工程与应用, 2021, 57(20): 82-89.
[4]	杨世强，范国豪，白乐乐，赵成，李德信. 基于几何约束的室内动态环境视觉SLAM[J]. 计算机工程与应用, 2021, 57(16): 203-212.
[5]	张俊，朱庆伟，严俊杰，温波. 改进强化学习算法的UAV室内三维航迹规划[J]. 计算机工程与应用, 2021, 57(16): 175-181.
[6]	张人，何宁. 微表情识别研究综述[J]. 计算机工程与应用, 2021, 57(1): 38-47.
[7]	张博，贾华宇，马珺. RS-GA神经网络无人机受风情况估计[J]. 计算机工程与应用, 2020, 56(4): 209-213.
[8]	杨锦朋，常俊，余江，李晓薇. 免校准的跨异构设备的室内定位方法[J]. 计算机工程与应用, 2020, 56(2): 248-254.
[9]	伍锡如，黄榆媛，王耀南. 改进ORB特征的机器人RGB-D SLAM算法[J]. 计算机工程与应用, 2020, 56(14): 35-44.
[10]	郑晨辉，陈璟，张雨婷，薛伟. 融合粒子滤波与蓝牙地标矫正的定位算法[J]. 计算机工程与应用, 2020, 56(13): 273-278.
[11]	刘安睿劼，王耀力. 基于轮式机器人的实时3D栅格地图构建[J]. 计算机工程与应用, 2020, 56(13): 164-171.
[12]	胡东海，邵元，陈莹，夏士雄. 基于改进粒子滤波的室内自适应定位算法[J]. 计算机工程与应用, 2019, 55(9): 65-71.
[13]	何伟健，陆江城，朱耀磷，李学聪. RFID旋转天线中的椭圆模型室内定位算法[J]. 计算机工程与应用, 2019, 55(9): 87-93.
[14]	曹凯1，2，杨雪梦1，姚敏茹1，2，马天力1，张航1. 基于混合运动估计方法的视觉里程计[J]. 计算机工程与应用, 2019, 55(5): 175-180.
[15]	雍玖，王阳萍，雷晓妹. MEEM跟踪和改进ORB特征检测的三维注册方法[J]. 计算机工程与应用, 2019, 55(24): 147-153.

一种用于无人机室内定位的改进ORB光流算法

Improved ORB Feature Optical Flow Algorithm for Indoor Positioning of Unmanned Aerial Vehicle

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics