计算机科学 ›› 2018, Vol. 45 ›› Issue (11A): 222-225.

• 模式识别与图像处理 • 上一篇    下一篇

一种基于四叉树的改进的ORB特征提取算法

禹鑫燚, 詹益安, 朱峰, 欧林林   

  1. 浙江工业大学信息工程学院 杭州310000
  • 出版日期:2019-02-26 发布日期:2019-02-26
  • 通讯作者: 欧林林(1980-),女,博士,副教授,硕士生导师,主要研究方向为以多移动机器人为载体的多智能体系统协同控制满意控制理论研究,E-mail:linlinou@zjut.edu.cn
  • 作者简介:禹鑫燚(1979-),男,博士,讲师,主要研究方向为工业机器人轨迹规划、工业机器人运动控制等,E-mail:yuxinyinet@163.com;詹益安(1993-),男,硕士生,主要研究方向为计算机视觉三维建图;朱 峰(1992-),男,硕士生,主要研究方向为计算机视觉
  • 基金资助:
    本文受国家高技术研究发展计划(863计划)(2014AA041601-05),国家自然科学基金(61273116),浙江省自然科学基金(LYl5F030015)资助。

Improved ORB Feature Extraction Algorithm Based on Quadtree Encoding

YU Xin-yi, ZHAN Yi-an, ZHU Feng, OU Lin-lin   

  1. College of Information Engineering,Zhejiang University of Technology,Hangzhou 310000,China
  • Online:2019-02-26 Published:2019-02-26

摘要: 文中提出了一种基于四叉树的改进的ORB(Oriented FAST and Rotated BRIEF)特征提取算法,它能够解决图像特征提取过程中特征点过于集中而导致的图像局部特征信息丢失的问题。首先,将图片构造成图像金字塔来解决尺度不变性问题;然后,在每一层金字塔图像上检测角点来提取特征点;接着,引入四叉树算法来均匀化分布特征点并计算特征点的方向和描述子;最后,以华硕深度摄像头(Xtion PRO)为实验工具,在室内环境下提取周边特征点,并将提取效果与其他方法进行对比,实验证明了所提算法在图像特征均匀化处理方面的快速性以及准确性。

关键词: ORB算法, 描述子, 四叉树, 特征点, 图像金字塔

Abstract: An improved ORB feature extraction algorithm based on quadtree encoding was proposed in this paper,which can solve the problem that the detected feature points are too dense to show the picture information completely.Firstly,the image pyramid is built to make the scale invariance.Then,the feature points are extracted on each image pyramid and quadtree encoding is introduced to homogenize the feature point.Finally,the direction and descriptor are calculated for each feature points.In this paper,the Xtion PRO was used as an experimental tool to extract the feature points under indoor environment,and the proposed algorithm was compared with others.Experimental results show the effectiveness and accuracy of the proposed method.

Key words: Descriptor, Feature points, Image pyramid, ORB algorithm, Quadtree encoding

中图分类号: 

  • TP391.41
[1]LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[2]BAY H,TUYTELAARS T,VAN GOOL L.Surf:Speeded up robust features[J].European Conference Computer Vision,2006,110(3):404-417.
[3]RUBLEE E,RABAUD V,KONOLIGE K,et al.OR-B:An efficient alternative to SIFT or SUR-F[C]∥International Confe-rence on Computer Vision.2012:2564-2571.
[4]MUR-ARTAL R,MONTIEL J M M,TARDOS J D.ORB-SLAM:a versatile and accurate monoc-ular SLAM system[J].IEEE Transactions on Robotics,2015,31(5):1147-1163.
[5]BENTLEY J L.Multidimensional binary searchtrees used for associative searching[J].Communications of the ACM,1975,18(9):509-517.
[6]MUR-ARTAL R,TARDÓS J D.Orbslam2:An open-source slam system for monocular,stereo,and rgb-d cameras[J].IEEE Transactions on Robotics,2017,33(5):1255-1262.
[7]ROSTEN E,DRUMMOND T.Machine learning for high-speed corner detection[C]∥European Conference on Computer Vision.Springer-Verlag,2006:430-443.
[8]HARRIS C,STEPHENS M.A combined corner and edge detector[C]∥Alvey Vision Conference.Manchester,UK,1988:5244.
[9]CALONDER M,LEPETIT V,STRECHA C,et al.Brief:Binary robust independent elementary features[C]∥European Confe-rence on Computer Vision.2010:778-792.
[10]MUJA M,LOWE D G.Fast Matching of Binary Features[C]∥Computer and Robot Vision.2012:404-410.
[11]LEE M K.Pointing device of augmented reality:U.S.Patent Application 13/581,548[P].2011-2-28.
[12]TRIGGS B,MCLAUCHLAN P F,HARTLEY R I,et al.Bundle adjustment—a modern synthesis[C]∥International Workshop on Vision Algorithms.Berlin Heidelberg Springer:1999:298-372.
[1] 王引娣, 章哲庆, 严丽.
基于双时态RDF模型的索引方法
Indexing Bi-temporal RDF Model
计算机科学, 2021, 48(4): 63-69. https://doi.org/10.11896/jsjkx.200600084
[2] 史文凯, 张昭晨, 喻孟娟, 吴瑞, 聂建辉.
基于特征检测与深度特征描述的点云粗对齐算法
Point Cloud Coarse Alignment Algorithm Based on Feature Detection and Depth FeatureDescription
计算机科学, 2020, 47(12): 252-257. https://doi.org/10.11896/jsjkx.191000069
[3] 李浩翔, 李浩君.
MACTEN:新型大规模布料纹理分类框架
MACTEN:Novel Large Scale Cloth Texture Classification Architecture
计算机科学, 2020, 47(11A): 258-265. https://doi.org/10.11896/jsjkx.191200115
[4] 杨思燕,贺国旗,刘如意.
基于SIFT算法的大场景视频拼接算法及优化
Video Stitching Algorithm Based on SIFT and Its Optimization
计算机科学, 2019, 46(7): 286-291. https://doi.org/10.11896/j.issn.1002-137X.2019.07.044
[5] 孙雪强, 黄旻, 张桂峰, 赵宝玮, 丛麟骁.
基于改进SIFT的多光谱图像匹配算法
Multispectral Image Matching Algorithm Based on Improved SIFT
计算机科学, 2019, 46(4): 280-284. https://doi.org/10.11896/j.issn.1002-137X.2019.04.044
[6] 朱超, 吴素萍.
并行Harris特征点检测算法
Parallel Harris Feature Point Detection Algorithm
计算机科学, 2019, 46(11A): 289-293.
[7] 张美玉, 王洋洋, 侯向辉, 秦绪佳.
基于ORB和改进的RANSAC图像拼接算法
Image Stitching Algorithm Based on ORB and Improved RANSAC
计算机科学, 2019, 46(11A): 294-298.
[8] 刘振宇, 关彤.
基于RGB-D图像的头部姿态检测
Head Posture Detection Based on RGB-D Image
计算机科学, 2019, 46(11A): 334-340.
[9] 刘宇, 杨百龙, 赵文强, 袁志华.
基于自适应块参照值的密文域可逆信息隐藏
Adaptive Pixel Block Reference Value Based Reversible Data Hiding in Encrypted Domain
计算机科学, 2018, 45(8): 151-155. https://doi.org/10.11896/j.issn.1002-137X.2018.08.027
[10] 张真真,王建林.
结合第二代Bandelet变换分块的字典学习图像去噪算法
Dictionary Learning Image Denoising Algorithm Combining Second Generation Bandelet Transform Block
计算机科学, 2018, 45(7): 264-270. https://doi.org/10.11896/j.issn.1002-137X.2018.07.046
[11] 王振武,吕小华,韩晓辉.
基于四叉树分割的地形LOD技术综述
Survey of Terrain LOD Technology Based on Quadtree Segmentation
计算机科学, 2018, 45(4): 34-45. https://doi.org/10.11896/j.issn.1002-137X.2018.04.005
[12] 朱虹,李千目,李德强.
基于单个卷积神经网络的面部多特征点定位
Facial Multi-landmarks Localization Based on Single Convolution Neural Network
计算机科学, 2018, 45(4): 273-277. https://doi.org/10.11896/j.issn.1002-137X.2018.04.046
[13] 周诗豪,张云.
对数极坐标特征指导的迭代就近点法
Log-polar Feature Guided Iterative Closest Point Algorithm
计算机科学, 2018, 45(1): 297-306. https://doi.org/10.11896/j.issn.1002-137X.2018.01.052
[14] 刘红敏,李璐,王志衡.
基于采样点组二值化策略的鲁棒二值描述子研究
Sample Point Group Based Binary Method for Robust Binary Descriptor
计算机科学, 2017, 44(12): 292-297. https://doi.org/10.11896/j.issn.1002-137X.2017.12.053
[15] 潘翔,林俊勉,王学成,刘志,周小龙.
交互标记跟踪的三维动态数据对齐
Marking Points Tracking for 3D Dynamic Data Correspondence
计算机科学, 2017, 44(10): 307-311. https://doi.org/10.11896/j.issn.1002-137X.2017.10.055
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!