Extraction of subpixel insect wing features in images
-
摘要: 昆虫翅脉、翅脉交点及翅膀边缘是昆虫翅膀运动变形三维重构的主要依据.通过分析这三种特征的图像特点,对于翅脉中心,采用Hessian矩阵求出灰度极值点方向,并用二次曲线拟合该方向的灰度变化,通过确定该曲线极值点位置来提取亚象素翅脉中心;然后通过求灰度图像的梯度,在其梯度变化方向求极值点的方法提取翅膀边缘特征;此外根据翅脉方向变化的连续性提出了邻域角度约束方法确定翅脉交叉点,从而最终提取到亚像素级的翅膀边缘、翅脉及交叉点等特征.实际应用证明该方法是较为有效的.Abstract: Wing vein, junction of veins and wing edges are the fundamental image features for wings 3D reconstruction to obtain insect deformations motion parameters. To determine precise position of the wing features in images, gray properties of wing features were analyzed first. For wing vein features, the gray extreme direction was determined by Hessian matrix. The gray variable was fitted by conic curve along the direction of the gray extreme, so the subpixel location of the vein center was obtained by searching the extremum of the curve. For wing edges, image gray gradient was calculated, and then subpixel step edge of wings was determined by searching the gradient extremum along the gradient change direction. Angle constraint in neighbor was used to determine junctions of wing veins based on the change continuity of vein direction. All wing features were determined at subpixel locations. The experiment results show that the extracting method about wing features is effective.
-
Key words:
- feature extraction /
- image processing /
- insect wing /
- edge /
- angle constraint
-
[1] 钦俊德.动物的运动[M]. 北京:清华大学 版社,2000.53~60 Qin Junde. Movement of animals [M]. Beijing:TsingHua University Press,2000.53~60(in Chinese) [2] 徐光佑.计算机视觉[M]. 北京:清华大学 版社,1999 Xu Guangyou. Computer vision[M]. Beijing:TsingHua University Press,1999(in Chinese) [3] Carsten Steger. Unbiased extraction of curvilinear structure from 2D and 3D images .Munich:School for Information, Technology University Munich, 1998 [4] 崔 屹.数字图像处理技术与应用[M]. 北京:电子工业出版社,1996 Cui Yi. Digital image process technical and application[M]. Beijing:Electronic Industry Press, 1996(in Chinese) [5] Vliet L J, Young I T, Beckers A L D. An edge detection model based on nonlinear Laplace filter [J]. Pattern Recognition and Artificial Intelligence, 1988, 63~73 [6] Canny J. A computational approach to edge detection [J]. IEEE Transaction on Pattern and Machine Intelligence, 1986,PAMI-8(6):679~697 [7] 贾云得.机器视觉[M]. 北京:科学出版社,2000 Jia Yunde. Machine vision[M]. Beijing:Science Press, 2000(in Chinese)
点击查看大图
计量
- 文章访问数: 4697
- HTML全文浏览量: 250
- PDF下载量: 1193
- 被引次数: 0