半导体光电, 2019, 40 (4): 539, 网络出版: 2019-09-20   

融合特征光流与角点特征的图像特征匹配算法研究

Research on Image Feature Matching Algorithm of Fusion Characteristic Optical Flow and Corner Features
作者单位
重庆理工大学 光纤传感与光电检测重庆市重点实验室, 重庆 400054
摘要
图像特征匹配是视觉里程计的重要环节, 针对视觉图像序列特征点匹配中存在的匹配精度低问题, 提出一种融合金字塔特征光流与角点特征的精确快速图像特征匹配算法。算法首先利用ORB(二进制定向简单描述符)算法快速提取图像特征点, 然后融合金字塔Lucas-Kanade特征光流的追踪特性, 使用局部特征窗口计算图像特征点位移矢量。接着针对图像特征的匹配对齐问题以及特征丢失问题, 算法采用K最近邻半径搜索作为特征滤波器移除混淆的匹配, 最后使用RANSAC(Random Sample Consensus)算法剔除冗余误匹配点对, 提高匹配率。通过多组实验数据对比, 该算法的图像特征匹配率可达到98%。对比传统的ORB特征匹配算法, 该算法在实时性和图像特征匹配精度上均有显著提高。
Abstract
Image feature matching is an important part of the visual odometry. To solve the problem of low accuracy of mismatch in the feature point matching of visual image sequences, an accurate and fast algorithm combining the pyramid festure optical flow and corner features is proposed. Firstly, the ORB algorithm is used to extract the image feature points quickly, then the tracking characteristics of the pyramid Lucas-Kanade feature optical flow are fused, and the local feature window is used to calculate the displacement vector of the image feature points. Then, aiming at the matching alignment problem and feature loss problem of image features, the K nearest neighbor radius search is used as the feature filter to remove the confused matching. Finally, the RANSAC (Random Sample Consensus) algorithm is used to eliminate redundant mismatch points to improve the matching rate. By the comparisons of multiple sets of experimental data, the feature matching rate of the proposed algorithm can reach 98%. Compared with the traditional ORB feature matching algorithm, the proposed algorithm realizes a significant improvement in real-time property and accuracy of image feature matching.
参考文献

[1] 宋文杰, 付梦印, 杨 毅. 一种面向无人驾驶汽车的高效交通标志识别方法[J]. 机器人, 2015, 37(1): 102-111.

    Song Wenjie, Fu Mengyin, Yang Yi. An efficient traffic signs recognition method for autonomous vehicle[J]. Robot, 2015, 37(1): 102-111.

[2] Cadena C, Carlone L, Carrillo H, et al. Past, present and future of simultaneous localization and mapping: toward the robust-perception age[J]. IEEE Trans. on Robotics, 2016, 32(6): 1309-1332.

[3] Hong S, Kim J, Pyo J, et al. A robust loop-closure method for visual SLAM in unstructured seafloor environments[J]. Autonomous Robots, 2016, 40(6): 1095-1109.

[4] Zuo X, Xie X, Liu Y, et al. Robust visual SLAM with point and line features[C]// IEEE Inter. Conf. on Intelligent Robots and Systems, 2017: 1775-1782.

[5] Karlsson N, Bernardo E D, Ostrowski J, et al. The vSLAM algorithm for robust localization and mapping[C]// IEEE Inter. Conf. on Robotics and Automation, 2006: 24-29.

[6] Valiente D, Gil A, Oscar R, et al. Improved omnidirectional odometry for a view-based mapping approach[J]. Sensors, 2017, 17(2): 325.

[7] Liu Y, Cao J Z, Xu Z H, et al. Improvement of image matching algorithm based on gray correlation[J]. J. of Appl. Opt., 2007, 11(1): 68-73.

[8] Zhong W B, Ning X B, Wei C J. A fingerprint matching algorithm based on relative topological relationship among minutiae[C]// IEEE Inter. Conf. on Neural Networks and Signal Proc., 2008: 225-228.

[9] Lowe D G. Object recognition from local scale-invariant features[C]// ICCV IEEE Computer Society, 1999: 1150.

[10] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. Inter. J. of Computer Vision, 2004, 60(2): 91-110.

[11] Bay H, Tuytelaars T, Gool L V. SURF: speeded up robust features[C]// Euro. Conf. on Computer Vision, 2006: 404-417.

[12] Rublee E, Rabaud V, Konolige K, et al. ORB: An efficient alternative to SIFT or SURF[C]// IEEE Inter. Conf. on Computer Vision, 2012: 2564-2571.

[13] Wang L, Qiu Z. Combining color histogram and ORB features for robust visual tracking[C]// IEEE Eighth Inter. Conf. on Natural Computation, 2012: 519-522.

[14] Hu Z, Li B, Hu Y. Fast sign recognition with weighted hybrid K-nearest neighbors based on holistic features from local feature descriptors[J]. J. of Computing in Civil Engin., 2017, 31(5): 04017034.

[15] Zhu Y, Shen X, Chen H. Copy-move forgery detection based on scaled ORB[J]. Multimedia Tools & Applications, 2016, 75(6): 3221-3233.

[16] Murartal R, Montiel J M M, Tardos J D. ORB-SLAM: a versatile and accurate monocular SLAM system[J]. IEEE Trans. on Robotics, 2015, 31(5): 1147-1163.

[17] Wang J, Zheng S, Du Y, et al. Study on the ORB algorithm in the application of monocular SLAM[J]. Nanotechnol., 2015, 2(3): 186.

[18] Murartal R, Tardos J D. ORB-SLAM2: An open-source SLAM system for monocular, stereo and RGB-D cameras[J]. IEEE Trans. on Robotics, 2016, 33(5): 1255-1262.

[19] 侯 毅, 周石琳, 雷 琳, 等. 基于ORB的快速完全仿射不变图像匹配[J]. 计算机工程与科学, 2014, 36(2): 303-310.

    Hou Yi, Zhou Shilin, Lei Lin, et al. Fast fully affine invariant image matching based on ORB[J]. Computer Engin. and Science, 2014, 36(2): 303-310.

[20] 曾庆化, 陈 艳, 王云舒, 等. 一种基于ORB的快速大视角图像匹配算法[J]. 控制与决策, 2017, 32(12): 2233-2239.

    Zeng Qinghua, Chen Yan, Wang Yunshu, et al. A fast matching method for large viewpoint changes images based on ORB algorithm[J]. Control and Decision, 2017, 32(12): 2233-2239.

[21] 贺利乐, 路二伟, 李赵兴, 等. 基于ORB算子的快速立体匹配算法[J]. 计算机工程与应用, 2017, 53(1): 190-194.

    He Lile, Lu Erwei, Li Zhaoxing, et al. Fast stereo matching algorithm based on ORB operator[J]. Computer Engin. and Applications, 2017, 53(1): 190-194.

[22] 卢胜男, 李小和. 结合双向光流约束的特征点匹配车辆跟踪方法[J]. 交通运输系统工程与信息, 2017, 17(4): 76-82.

    Lu Shengnan, Li Xiaohe. Vehicle tracking method using feature point matching combined with bidirectional optical flow[J]. J. of Transportation Systems Engin. and Information Technol., 2017, 17(4): 76-82.

[23] Gibson J J. The Perception of The Visual World[M]. Oxford: Houghton Mifflin, 1950: 172.

[24] Bradski G R, Kaehler A. Learning OpenCV: Computer Vision in C++ with The OpenCV Library[M]. California: OReilly Media, 2013.

[25] Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[C]// Inter. Joint Conf. on Artificial Intelligence, 1981: 674-679.

[26] Bouguet J Y. Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm[J]. Opencv Documents, 1999, 22(2): 363-381.

[27] Fischler M A. Readings in Computer Vision Ⅱ Random Sample Consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Readings in Computer Vision, 1987: 726-740.

[28] Blanco-Claraco J L, Moreno-Duenas F A, Gonzalez-Jimenez J. The Malaga Urban Dataset: High-Rate Stereo and LiDAR in A Realistic Urban Scenario[M]. California: Sage Publications Inc., 2014.

    Smith M, Baldwin I, Churchill W, et al. The new college vision and laser dataset[J]. Inter. J. of Robotics Research, 2009, 28(5): 595-599.

赵明富, 陈兵, 宋涛, 曹利波. 融合特征光流与角点特征的图像特征匹配算法研究[J]. 半导体光电, 2019, 40(4): 539. ZHAO Mingfu, CHEN Bing, SONG Tao, CAO Libo. Research on Image Feature Matching Algorithm of Fusion Characteristic Optical Flow and Corner Features[J]. Semiconductor Optoelectronics, 2019, 40(4): 539.

本文已被 1 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!