Robust detection of straight and circular road segments in noisy aerial images'

This paper treats the problem of detecting straight or circular pieces of road in noisy low-resolution aerial images. It first uses a local operator to detect pixels whose neighborhoods are line-like, and then applies (robust) estimation techniques to find sets of such pixels that lie on or near straight or circular loci. An (unbiased) ordinary least squares estimator cannot handle outlying data even for straight loci; on the other hand, conventional robust techniques for fitting circular arcs are severely affected by digitization effects and the fact that circular road segments are typically short and shallow. We therefore introduce an estimator that is both robust and statistically efficient. We also present a simple ad hoc technique that achieves comparable results and can handle road segments that are either straight or circular.

[1]  Mark B. Sandler,et al.  A combinatorial Hough transform , 1990, Pattern Recognit. Lett..

[2]  Donald Geman,et al.  An Active Testing Model for Tracking Roads in Satellite Images , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Andrew Stein,et al.  Robust statistics in shape fitting , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Ruzena Bajcsy,et al.  Computer Recognition of Roads from Satellite Pictures , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[6]  PAUL D. SAMPSON,et al.  Fitting conic sections to "very scattered" data: An iterative refinement of the bookstein algorithm , 1982, Comput. Graph. Image Process..

[7]  P. Rousseeuw.  Least Median of Squares Regression , 1984 .

[8]  Jianying Hu,et al.  Interactive road finding for aerial images , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

[9]  U. M. Landau,et al.  Estimation of a circular arc center and its radius , 1987, Comput. Vis. Graph. Image Process..

[10]  V. Yohai,et al.  Bias- and efficiency-robustness of general M-estimators for regression with random carriers , 1979 .

[11]  William H. Press,et al.  Numerical recipes , 1990 .

[12]  Jacques Verly,et al.  Machine Intelligent Automatic Recognition of Critical Mobile Targets in Laser Radar Imagery , 1993 .

[13]  David M. Mount,et al.  Computationally Efficient Algorithms for High-Dimensional Robust Estimators , 1994, CVGIP Graph. Model. Image Process..

[14]  S. H. Joseph.  Unbiased Least Squares Fitting of Circular Arcs , 1994, CVGIP Graph. Model. Image Process..

[15]  Azriel Rosenfeld,et al.  Symbolic pixel labeling for curvilinear feature detection , 1988, Pattern Recognit. Lett..

[16]  David B. Cooper,et al.  New Geometric Stochastic Technology for Finding and Recognizing Roads and Their Features in Aerial Images , 1995 .

[17]  Paul L. Rosin.  Ellipse fitting by accumulating five-point fits , 1993, Pattern Recognit. Lett..

[18]  Joyce Snell,et al.  6. Alternative Methods of Regression , 1996 .

[19]  H. Theil.  A Rank-Invariant Method of Linear and Polynomial Regression Analysis , 1992 .

[20]  Werner A. Stahel,et al.  Robust Statistics: The Approach Based on Influence Functions , 1987 .

[21]  Martin A. Fischler,et al.  Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique☆ , 1981 .

[22]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[23]  Peter J. Rousseeuw,et al.  Robust regression and outlier detection , 1987 .

[24]  P. Sen.  Estimates of the Regression Coefficient Based on Kendall's Tau , 1968 .

[25]  Ryuzo Takiyama,et al.  A least square error estimation of the center and radii of concentric arcs , 1989, Pattern Recognit. Lett..

[26]  Frederick Mosteller,et al.  Data Analysis and Regression , 1978 .

[27]  Behrooz Kamgar-Parsi,et al.  A Nonparametric Method for Fitting a Straight Line to a Noisy Image , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  A. Stromberg.  Computation of high breakdown nonlinear regression parameters , 1993 .

[29]  A. Siegel.  Robust regression using repeated medians , 1982 .

[30]  David B. Cooper,et al.  Automatic finding of main roads in aerial images by using geometric-stochastic models and estimation , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[31]  F. Bookstein.  Fitting conic sections to scattered data , 1979 .

[32]  Bidyut Baran Chaudhuri,et al.  Detection of linear features in satellite imagery using robust estimation , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[33]  A. Rosenfeld,et al.  Edge and Curve Detection for Visual Scene Analysis , 1971, IEEE Transactions on Computers.

[34]  Bidyut Baran Chaudhuri.  Optimal circular fit to objects in two and three dimensions , 1990, Pattern Recognit. Lett..

[35]  Bidyut Baran Chaudhuri,et al.  Optimum circular fit to weighted data in multi-dimensional space , 1993, Pattern Recognit. Lett..

[36]  Arnold J. Stromberg,et al.  Computing the Exact Least Median of Squares Estimate and Stability Diagnostics in Multiple Linear Regression , 1993, SIAM J. Sci. Comput..

[37]  L. Quam.  Road Tracking and Anomaly Detection in Aerial Imagery , 1978 .

[38]  Yiu-Tong Chan,et al.  A simple approach for the estimation of circular arc center and its radius , 1989, Comput. Vis. Graph. Image Process..

[39]  Lide Wu,et al.  The Robust Algorithms for Finding the Center of an Arc , 1995, Comput. Vis. Image Underst..

[40]  V. Yohai.  HIGH BREAKDOWN-POINT AND HIGH EFFICIENCY ROBUST ESTIMATES FOR REGRESSION , 1987 .

[41]  K. Ramesh Babu,et al.  Linear Feature Extraction and Description , 1979, IJCAI.

[42]  Aviad Zlotnick,et al.  Finding Road Seeds in Aerial Images , 1993 .

[43]  R. Welsch,et al.  Efficient Bounded-Influence Regression Estimation , 1982 .

[44]  David M. McKeown,et al.  Cooperative methods for road tracking in aerial imagery , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.