多尺度光斑中心的快速检测

孙慧涛; 李木国

doi:10.3788/OPE.20172505.1348

您当前的位置：

首页 >

文章列表页 >

多尺度光斑中心的快速检测

信息科学 | 更新时间：2020-07-07

- 多尺度光斑中心的快速检测
- Fast and accurate detection of multi-scale light spot centers
- 光学精密工程 2017年25卷第5期页码：1348-1356
- 作者机构：
  
  1.大连理工大学海岸与近海工程国家重点实验室, 辽宁大连 116024
  2.大连理工大学电子信息与电气工程学部, 辽宁大连 116024
- 作者简介：
  
  孙慧涛 (1988-), 男, 黑龙江牡丹江人, 博士研究生, 2010年于燕山大学获得学士学位, 现为大连理工大学博士研究生, 主要从事机器视觉及模式识别方面的研究。E-mail:sht229@163.com SUN Hui-tao, E-mail:sht229@163.com
- 基金信息：
  
  国家自然科学基金资助项目(61202253)
- DOI：10.3788/OPE.20172505.1348
  中图分类号： TP391
- 收稿日期：2016-05-06，
  
  录用日期：2016-7-12，
  
  纸质出版日期：2017-05-25
- 稿件说明：
移动端阅览
孙慧涛, 李木国. 多尺度光斑中心的快速检测[J]. 光学精密工程, 2017,25(5):1348-1356.

Hui-tao SUN, Mu-guo LI. Fast and accurate detection of multi-scale light spot centers[J]. Optics and precision engineering, 2017, 25(5): 1348-1356.
孙慧涛, 李木国. 多尺度光斑中心的快速检测[J]. 光学精密工程, 2017,25(5):1348-1356. DOI： 10.3788/OPE.20172505.1348.

Hui-tao SUN, Mu-guo LI. Fast and accurate detection of multi-scale light spot centers[J]. Optics and precision engineering, 2017, 25(5): 1348-1356. DOI： 10.3788/OPE.20172505.1348.

摘要

分析了光斑图像成像特点和理想光斑灰度分布模型，针对含有多个不同尺度光斑的图像，提出了一种可以在复杂环境下一次性快速检测出多个光斑中心的方法。该方法基于高斯模糊后光斑中心不变的性质，先对含有大量光斑的图像进行快速多级高斯模糊，构建其高斯尺度空间；然后，使用加速的非极大值抑制方法在尺度空间内寻找多个尺度的局部极值，初步确定各光斑中心的像素级坐标；最后，联合这些坐标的邻域像素，拟合局部曲面，得到光斑中心的亚像素级精确位置。利用仿真实验和实物实验验证了提出方法的有效性。结果表明：该算法对640 pixel×480 pixel图像，处理时间仅需50ms，每千个光斑的平均检测时间为23 ms，在复杂环境下正确率可达89%。此外，该方法对弱光斑较敏感，适合快速处理含有大量不同尺度光斑的图像，并能够有效减少光斑的错检和漏检。由于检测速度快，自适应性强，在实际应用中取得了良好的检测效果。

Abstract

The imaging characteristics of an image with light spots and the grey-level distribution model of an ideal light spot were analyzed. A fast and accurate algorithm to detect simultaneously multiple light spot centers in a complex imaging environment was proposed for the image with multi-scale light spots. As the centers of light spots would not be changed after blurring the spot image with Gaussian kernels

the image with massive multi-scale light spots was blurred firstly with multilevel Gaussian kernels to fast establish a Gaussian scale-space of the spot image. Then an efficient non-maximum suppression algorithm was applied to find local extremums in multiple scales and to determine the pixel level coordinates of the light spot centers in the scale-space preliminarily. Finally

combined with the neighboring pixels of these pixel level coordinates

sub-pixel accurate locations of the spot centers were obtained by local surface fitting. The validity of proposed algorithm was verified by simulation and experiments. The results for an image of 640 pixel×480 pixel show that the processing time is 50 ms

average detection time for per thousand light spots is only 23 ms and the detection accuracy is 89% in many complex situations. Moreover

the algorithm is sensitive to low-light spots and can process the images with different scale spots in low contrast scenes

usually offering a low error rate and miss rate. Due to the high detection speed and good stabilitiy

the proposed algorithm performs well in real vision measurement systems.

关键词

Keywords

references

林义闽, 吕乃光, 娄小平, 等.用于弱纹理三维重建的机器人视觉系统[J].光学精密工程, 2015, 23(2):540-549.

LIN Y M, LV N G, LOU X P, et al. Robot vision system for 3D reconstruction in low texture environment[J]. Opt. Precision Eng., 2015, 23(2):540-549. (in Chinese)

霍炬, 杨宁, 杨明.飞行器仿真测试中合作目标投影光斑的跟踪识别[J].光学精密工程, 2015, 23(8):2134-2142.

HUO J, YANG N, YANG M. Tracking and recognition of projective spots for cooperation targets in vehicle simulation test[J]. Opt. Precision Eng., 2015, 23(8):2134-2142. (in Chinese)

杨景豪, 刘巍, 刘阳, 等.双目立体视觉测量系统的标定[J].光学精密工程, 2016, 24(2):301-308.

YANG J H, LIU W, LIU Y, et al. Calibration of binocular vision measurement system[J]. Opt. Precision Eng., 2016, 24(2):301-308. (in Chinese)

FU S J, BIWOLE PH, MATHIS C.Numerical and experimental comparison of 3D Particle Tracking Velocimetry (PTV) and Particle Image Velocimetry (PIV) accuracy for indoor airflow study.[J]. Building and Environment, 2016, 100:40-49.

XU Y, WU W Y, CHANG E I C, et al. A two-layer structure prediction framework for microscopy cell detection[J]. Computerized Medical Imaging and Graphics, 2015, 41:29-36.

刘震, 尚砚娜.多尺度光点图像中心的高精度定位[J].光学精密工程, 2013, 21(6):1586-1591.

LIU ZH, SHANG Y N. High precision location for multi-scale light spot center[J]. Opt. Precision Eng., 2013, 21(6):1586-1591. (in Chinese)

曹世康, 李东坚, 许瑞华, 等.基于最优弧的激光光斑中心检测算法[J].红外与激光工程, 2014, 43(10):3492-3496.

CAO SH K, LI D J, XU R H, et al. Algorithm of laser spot detection based on optimal arc[J]. Infrared and Laser Engineering, 2014, 43(10):3492-3496. (in Chinese)

魏振忠, 高明, 张广军, 等.一种光斑图像中心的亚像素提取方法[J].光电工程, 2009(4):7-12.

WEI ZH ZH, GAO M, ZHANG G J, et al. Sub-pixel extraction method for the center of light-spot image[J]. Opto-Electronic Engineering, 2009(4):7-12. (in Chinese)

LINDEBERG T. Feature detection with automatic scale selection[J]. International Journal of Computer Vision, 1998, 30(2):79-116.

LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision (S0920-5691), 2004, 60(2):91-110.

BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding (S1077-3142), 2008, 110(3):346-359.

LINDEBERG T. Image matching using generalized scale-space interest points[J]. Journal of Mathematical Imaging and Vision, 2015, 52(1S):3-36.

ALEXANDER N, LUC V. Efficient non-maximum suppression[C].18th International Conference on Pattern Recognition, 2006, 3:850-855.

ZHANG Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11):1330-1334.

浏览量

549

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

电力巡检中的偏振图像特征融合

基于机器视觉的透明软管内微量液体体积测量

基于圆卷积神经网络的粘连导电粒子检测

融合多尺度特征的蜗杆表面缺陷检测

相位测量的不连续位置自适应分割