基于差分响应图的无监督特征点检测网络

林璟怡; 李东; 胡晓瑞

doi:10.12052/gdutxb.200006

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于差分响应图的无监督特征点检测网络

更新时间：2026-05-27

- 基于差分响应图的无监督特征点检测网络
- An Unsupervised Feature Point Detection Network Based on Difference Response Graph
- 广东工业大学学报 2020年37卷第6期页码：63-70
- 作者机构：
  
  广东工业大学自动化学院,广东,广州,510006
- 作者简介：
  
  林璟怡(1994–)，男，硕士研究生，主要研究方向为图像处理、模式识别
  李东(1983–)，男，副教授，博士，硕士生导师，主要研究方向为模式识别、机器学习、人脸识别和机器视觉，E-mail：dong.li@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(61503084);广东省自然科学基金资助项目(2016A030310348)
- DOI：10.12052/gdutxb.200006
  中图分类号： TP391.4
- 网络首发：2020-11-02，
  
  纸质出版：2020
- 稿件说明：
移动端阅览
林璟怡, 李东, 胡晓瑞. 基于差分响应图的无监督特征点检测网络[J]. 广东工业大学学报, 2020, 37(6): 63-70.

Lin Jing-yi, Li Dong, Hu Xiao-rui. An Unsupervised Feature Point Detection Network Based on Difference Response Graph[J]. 2020, 37(6): 63-70.
林璟怡, 李东, 胡晓瑞. 基于差分响应图的无监督特征点检测网络[J]. 广东工业大学学报, 2020, 37(6): 63-70. DOI： 10.12052/gdutxb.200006.

Lin Jing-yi, Li Dong, Hu Xiao-rui. An Unsupervised Feature Point Detection Network Based on Difference Response Graph[J]. 2020, 37(6): 63-70. DOI： 10.12052/gdutxb.200006.

摘要

为了突破基于人工设计的特征点检测器的性能限制

提出了一种新的数据驱动的基于差分特征响应图的无监督特征点检测网络。该网络使用不同尺度的卷积核计算差分输出

利用差分响应图的绝对值大小筛选出大量特征点

并评判这些特征点重要性程度。同时采用旋转、光照、模糊等多种图像变换训练检测器

获得相应特征不变性

使得该网络更适用于小规模数据集训练。通过在3个常用数据集上进行实验

并与现有经典算法进行定性与定量的对比分析，结果表明

基于差分响应图的无监督特征点检测网络能较好地完成特征点检测任务

所需训练时间更短、边缘定位更准确、数据集规模依赖性更低

优化特征点检测性能。

Abstract

In order to break through the performance limitations of hand-craft feature point detectors

a new data-driven unsupervised feature point detection network based on differential feature response graphs is proposed. The network calculates the differential output using convolution kernels of different scales

uses the absolute value of the differential response map to select a large number of feature points and judges the importance of these feature points. The detector is trained by using various image transformations such as rotation

illumination

and blur to obtain corresponding feature invariance

making the network more suitable for small-scale data set training. Through experiments on three commonly used data sets

and qualitative and quantitative comparison analysis with existing classic algorithms

the experimental results show that the proposed unsupervised feature point detection network based on the differential response graph can complete the feature point detection well. The network locates object edges more accurately

requires less training time

and has less dependency on dataset size. The network has optimized and improved feature point detection performance.

关键词

Keywords

references

SCHMID C, MOHR R, BAUCKHAGE C. Evaluation of interest point detectors [J]. International Journal of Computer Vision, 2000, 37(2): 151-172.

CANNY J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.

TRAJKOVIM, HEDLEY M. Fast corner detection [J]. Image and Vision Computing, 1998, 16(2): 75-87.

MATAS J, CHUM O, URBAN M, et al . Robust wide-baseline stereo from maximally stable extremal regions [J ] . Image and Vision Computing, 2004, 22(10): 761-767.

HARRIS C G, STEPHENS M. A combined corner and edge detector[C]//Proceedings of the 4th Alvey Vision Conference. Manchester: Citeseer, 1988: 147-151.

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

BAY H, TUYTELAARS T, VAN GOOL L. SURF: Speeded up robust features[C]//European Conference on Computer Vision. Heidelberg: Springer, 2006: 404-417.

CHENG X N, ZHAO J, YANG R F. Study on visual keywords extraction new method based on points of interest detection [J]. Modern Electronics Technique, 2017, 40(21): 70-73.

LI D L, LIU W. Object location for binocular stereo vision based on improved SIFT feature [J]. Journal of Guangdong University of Technology, 2017, 34(1): 90-94.

YE Z J, WANG F L. An improved FREAK algorithm for image feature point matching [J]. Journal of Guangdong University of Technology, 2017, 34(6): 37-42.

LENC K, VEDALDI A. Learning covariant feature detectors[C]//European Conference on Computer Vision. Amsterdam: Springer, 2016: 100-117.

VERDIE Y, YI K, FUA P, et al. TILDE: A temporally invariant learned detector[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 5279-5288.

SAVINOV N, SEKI A, LADICKY L, et al. Quad-networks: unsupervised learning to rank for interest point detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 1822-1830.

ONO Y, TRULLS E, FUA P, et al. LF-Net: learning local features from images[C]//Advances in Neural Information Processing Systems. San Francisco: Margan Kaufmann, 2018: 6234-6244.

DETONE D, MALISIEWICZ T, RABINOVICH A. Superpoint: self-supervised interest point detection and description[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City: IEEE, 2018: 224-236.

MIKOLAJCZYK K, TUYTELAARS T, SCHMID C, et al . A comparison of affine region detectors [J ] . International Journal of Computer Vision, 2005, 65(1-2): 43-72.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

气相色谱–离子迁移谱检测畜禽有机废物堆肥中的挥发性硫化合物

电磁泄漏型硬件木马设计与检测

基于AAGV-YOLOX模型的输电线路异物检测研究

基于路况参数的混合动力机车能量管理策略研究

融合沟道倾斜角的3D NAND存储单元建模及编程策略优化