Target local feature extraction combined MSER and HSOG

Han-zhou GUO; Li-hong GUO; You LV

doi:10.3788/YJYXS20163111.1070

您当前的位置：

首页 >

文章列表页 >

Target local feature extraction combined MSER and HSOG

Display and Image | 更新时间：2020-08-12

- Target local feature extraction combined MSER and HSOG
- Chinese Journal of Liquid Crystals and Displays Vol. 31, Issue 11, Pages: 1070-1078(2016)
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
  2.中国科学院大学, 北京 100049
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20163111.1070
  CLC： TP391
- Received：11 July 2016，
  
  Accepted：22 August 2016，
  
  Published：2016-11
- 稿件说明：
移动端阅览
Han-zhou GUO, Li-hong GUO, You LV. Target local feature extraction combined MSER and HSOG[J]. Chinese journal of liquid crystals and displays, 2016, 31(11): 1070-1078.
DOI：

Han-zhou GUO, Li-hong GUO, You LV. Target local feature extraction combined MSER and HSOG[J]. Chinese journal of liquid crystals and displays, 2016, 31(11): 1070-1078. DOI： 10.3788/YJYXS20163111.1070.

摘要

针对SIFT在视点变化下对物体几何特征描述的缺陷，本文提出一种结合最稳极值区域检测和改进的二阶梯度直方图描述子的目标局部特征提取方法。首先，采用一种新的最稳定度判断准则，提高了不规则形状区域和模糊条件下的检测效果；然后，利用改进的二阶梯度直方图提取MSER区域的局部特征描述子，采用高斯函数加权的方法考虑了不同像素对区域中心像素的影响，提高了稳定性；最后，通过标准测试图像和实际拍摄图像的匹配对算法进行验证。实验结果表明，本文方法在视点变化下仍能获得70%以上的匹配率，匹配效果优于SIFT。本文方法相比于传统方法检测效果更为稳定，对于不规则形状区域仍有较好的检测效果，适用于视点变化下的目标匹配。

Abstract

For the defect in describing object geometry features of SIFT at viewpoint variation

a new local feature extraction method is proposed in this paper

which combined maximally stable extremal region(MSER) and histogram of second order gradient(HSOG). First

a new most stability criterion is adopted to improve the detection effect at irregular shaped regions and under blur conditions. Then

the local feature descriptors of MSER is extracted by the improved histogram of second-order gradient; the influences of different pixels on central pixel of MESR region are considered by weighted Gaussian function method and the stability is improved. Finally

the method proposed is verified through image match with standard test images and real images. Experimental results show that the method proposed can still achieve more than 70% matching rate at different viewpoint

which is better than SIFT. Compared with the traditional method

the presented method achieves an excellent detection effect for irregularly shaped areas

which is suitable for target matching when viewpoint is current.

关键词

Keywords

references

柯洪昌, 孙宏彬. 图像序列的显著性目标区域检测方法[J]. 中国光学, 2015,8(5):768-774.

KE H C, SUN Hong-bin. A saliency target area detection method of image sequence[J]. Chinese Optics , 2015,8(5):768-774.

王灿进, 孙涛, 李正炜. 基于快速轮廓转动力矩特征的激光主动成像目标识别[J]. 中国光学, 2015,8(5):775-784.

WANG C J, SUN T, LI Zheng-wei. Target Recognition in laser active imaging based on fast contour torque features[J]. Chinese Optics , 2015,8(5):775-784.

LOWE D G. Distinctive image features from scale-invariant keypoints[C]. International Journal of ComputerVision, 2004:91-110. http://www.oalib.com/references/13326872

MIKOLAJCZYK K, TUYTELAARS T, SCHMID C, et al. A comparison of affine region detectors[C]. International Journal of Computer Vision, 2005:2005. http://www.oalib.com/references/18715548

MATAS J, CHUM O. Robust wide-baseline stereo from maximally stable extremal regions[J]. Bmvc, 2002, 22(10):761-767.

Per-Erik Forssen, David G. Lowe. Shape descriptors for maximally stable extremal regions[J]. Proceedings, 2007:1-8.

MIKOLAJCZIK K, SCHMID C. A performance evaluation of local descriptors[J]. Pattern Analysis & Machine Intelligence IEEE Transactions on , 2005, 27(10):1615-1630.

HU J, PENG X, FU C. A comparison of feature description algorithms[J]. Optik-International Journal for Light and Electron Optics , 2015, 126:274-278.

沈同圣,张建,娄树理. 面向目标检测的空间观测图像精确配准[J]. 光学精密工程, 2015,22(8):2205-2213.

SHEN T S, ZHANG J, LOU S L. Precise registration of space observation images for target detection[J]. Optics and Prescision Engineering , 2015,22(8):2205-2213.

Fan B. Rotationally Invariant Descriptors using Intensity Order Pooling[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on , 2012,34(10):2031-2045. http://www.oalib.com/references/17185742

HUANG D, ZHHU C, BICHOT C E, et al. HSOG:a novel local descriptor based on histograms of second order gradients for object categorization[C]. Proceedings of the 3rd ACM conference on International conference on multimedia retrieval. ACM, 2013.

王新华, 黄玮, 欧阳继红. 多探测器拼接成像系统实时图像配准[J]. 中国光学, 2015,8(2):211-219

WANG X H, HUANG W, OUYANG Ji-hong. Real-time image registration of the multi-detectors mosaic imaging system[J]. Chinese Optics , 2015,8(2):211-219.

ZHANG C, BRONSTEIN A M, KIMMEL R, et al. Are MSER features really interesting?[J] . IEEE Transactions on Software Engineering , 2011, 33(11):2316-2320.

贺柏根. 电视末制导自动目标识别研究[D]. 中国科学院研究生院(长春光学精密机械与物理研究所), 2012. http://www.irgrid.ac.cn/handle/1471x/519811

He B G. Study on automatic target recognition of the TV-guided missile[D]. University of Chinese Academy of Sciences(Changchun Institute of Optics, Fine Mechanics and Physics), 2012.

蔡红苹. 基于局部特征的图像分类识别关键技术研究[D]. 国防科学技术大学, 2010. http://cdmd.cnki.com.cn/Article/CDMD-90002-1011074011.htm

CAI H P. TechniquesforLocalFeatureBasedImageCategorization[D]. National University of Defense Technology, 2010.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-granularity feature fusion for person re-identification

Related Author

Liang ZHANG

Jin CHE

Qi Yang

Related Institution

School of Physics and Electronic-Electrical Engineering, Ningxia University

Key Laboratory of Intelligent Sensing for Desert Information, Ningxia University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰