首页 > 论文 > 液晶与显示 > 29卷 > 4期(pp:598-604)

结合尺度空间FAST角点检测器和SURF描绘器的图像特征

Image features using scale-space FAST corner detector and SURF descriptor

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为了获得能够很好地应用于远距离目标识别且计算快速的图像特征, 本文提出了一种结合尺度空间FAST(加速分割试验特征)角点检测器和SURF(加速鲁棒特征)描绘器的新特征算法。SURF算法利用了基于快速海森矩阵的关键点检测算法, 容易从图像中快速海森矩阵响应值较高但信息匮乏的边缘区域提取大量关键点, 进而导致大量的低独特性特征以及不可忽视的误匹配率; 同时, 其高斯滤波带来的图像模糊使得算法在远距离目标区域内检测到的关键点数量减少, 从而对远距离目标的识别造成困难。针对SURF算法的这些问题, 本文方法利用尺度空间FAST算法代替快速海森矩阵, 并利用具有良好的独特性的SURF描绘器。该方法能够有效地减少对上述类型的干扰性关键点的提取, 对远距离目标的关键点检测的性能相对于快速海森矩阵具有显著优势, 且其独特性优于同样使用FAST角点检测器的BRISK特征。实验结果表明, 对于带有光照变化、尺度变化和3D视角变化目标, 基于本文特征的识别算法的识别正确率高于基于SIFT、SURF和BRISK特征的识别算法; 本文特征适用于远程目标识别, 同时其计算速度达到了与SURF接近的水平。

Abstract

In order to obtain image features that can be well exploited in long distance target recognition and are computationally efficient, an algorithm combining scale-space FAST (Features from Accelerated Segment Test) corner detector and SURF (Speeded Up Robust Features) descriptor, is proposed in this paper. The Fast-Hessian matrix based keypoint detector used SURF algorithm, is apt to extract numerous keypoints from non-informative edges with relatively high Fast-Hessian response, leading to considerable amounts of low-distinctive feature and consequently high rates of mismatch; with Gaussian filters employed, the possible amount of keypoints extracted with Fast-Hessian from regions of small targets is largely reduced due to image blur, which leaves difficulty for recognition of long distance targets. To address these problems, the proposed method uses a scale-space FAST corner detector in place of the Fast-Hessian detector, combining with SURF descriptor for its distinctiveness. The proposed method effectively eliminates the problem of extracting interfering keypoints along image edges, performing a significantly better detection of keypoints on long distance targets than Fast-Hessian, and generates features of better distinctiveness than BRISK features, which uses FAST as well. The experimental results indicate that the recognition algorithm based on the proposed features gives better performance against targets with change in scale, illumination and 3D viewpoint than that either based on SIFT, SURF or BRISK; the proposed feature can be well applied to long distance target recognition, while reaching a comparable computation speed to SURF.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/yjyxs20142904.0598

所属栏目:成像技术与图像处理

基金项目:吉林省重大科技攻关项目(No.11ZDGG001)

收稿日期:2013-07-05

修改稿日期:2013-09-16

网络出版日期:--

作者单位    点击查看

王飞宇:中国科学院 长春光学精密机械与物理研究所 中国科学院航空光学成像与测量重点实验室, 吉林 长春 130033中国科学院大学, 北京 100049
邸男:中国科学院 长春光学精密机械与物理研究所, 吉林 长春 130033
贾平:中国科学院 长春光学精密机械与物理研究所 中国科学院航空光学成像与测量重点实验室, 吉林 长春 130033中国科学院 长春光学精密机械与物理研究所, 吉林 长春 130033

联系人作者:王飞宇(napfeiyu@mail.ustc.edu.cn)

备注:王飞宇(1989-), 男, 安徽合肥人, 硕士研究生, 主要从事图像目标识别技术的研究。

【1】贾平, 徐宁, 张叶.基于局部特征提取的目标自动识别[J].光学 精密工程, 2013, 21(7): 1898-1905.
Jia P, Xu N, Zhang Y. Automatic target recognition based on local feature extraction [J].Opt. Precision Eng., 2013, 21(7): 1898-1905. (in Chinese)

【2】丘文涛, 赵建, 刘杰.结合区域分割的SIFT图像匹配方法[J].液晶与显示, 2012, 27(6): 827-831.
Qiu W T, Zhao J, Liu J. Image matching algorithm combining SIFT with region segmentation [J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(6): 827-831. (in Chinese)

【3】杨云, 岳柱.基于融合图像轮廓矩和Harris角点方法的遮挡人体目标识别研究[J].液晶与显示, 2013, 28(2): 273-277.
Yang Y, Yue Z.Human body target recognition under occlusion based on fusion of image contour moment and harris angular points [J]. Chinese Journal of Liquid Crystals and Displays, 2013, 28(2): 273-277. (in Chinese)

【4】赵建川, 王弟男, 陈长青, 等.红外激光主动成像和识别[J] .中国光学, 2013, 6(5): 795-802.
Zhao J C, Wang D N, Chen C C, et al. Infrared laser active imaging and recognition technology [J]. Chinese Optics, 2013, 6(5): 795-802. (in Chinese)

【5】闫辉, 许廷发, 吴青青, 等.多特征融合匹配的多目标跟踪[J].中国光学, 2013, 6(2): 163-170.
Yan H, Xu T F, Wu Q Q, et al. Multi-object tracking based on multi-feature joint matching [J]. Chinese Optics, 2013, 6(2): 163-170. (in Chinese)

【6】唐永鹤, 卢焕章.基于灰度差分不变量的快速局部特征描述算法[J].光学 精密工程, 2012, 20(2): 447-454.
Tang Y H, Lu H Z. Fast local featuredescription algorithm based on greyvalue differential invariants [J]. Opt. Precision Eng., 2012, 20(2): 447-454. (in Chinese)

【7】Lowe D. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

【8】Bay H, Tuytelaars T, Van Gool L.SURF: Speeded up robust features [C]//Proceedings of the European Confe rence on Computer Vision, 2006: 404-417.

【9】Bay H, Ess A, Tuytelaars T, et al. Speeded-up robust features(SURF) [J]. International Journal on Computer Vision and Image Understanding, 2008, 110(3): 346-359.

【10】Leutenegger S, Chli M, Siegwart R. BRISK: Binary robust invariant scalable keypoints [C].IEEE International Conference on Computer Vision, 2011: 2548-2555.

【11】Mikolajczyk K. Scale and Affine Invariant Interest Point Detectors [D]. INRIA Grenoble, 2002.

【12】Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 10(27): 1615-1630.

【13】Rosten E, Drummond T. Machine learning for high-speed corner detection [C]. Proceedings of the European Conference on Computer Vision, 2006: 430-443.

【14】Alahi A, Vandergheynst P, Bierlaire M, et al. Cascade of descriptors to detect and track objects across any network of cameras [J]. International Journal on Computer Vision and Image Understanding, 2010, 114(6): 624-640.

【15】Calonder M, Lepetit V, Strecha C, et al. BRIEF: Binary robust independent elementary features [C]. Proceedings of the European Conference on Computer Vision, 2010: 778-792.

【16】Brown M, Lowe D. Invariant features from interest point groups [C].British Machine Vision Conference, 2002: 656-665.

【17】Friedman J H, Bentley J L, Finkel R A. An algorithm for finding best matches in logarithmic expected time [J]. ACM Transactions on Mathematical Software, 1977, 3(3): 209-226.

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF