论文信息 - Occlusion analysis for object detection using the generalised Hough transform

Occlusion analysis for object detection using the generalised Hough transform

Abstract This paper examines the use of the generalised Hough transform for object detection and finds it to be highly resistant to the effects of occlusions for curved shapes. When objects possess straight edges the situation regarding occlusions is only optimal if a particular line parameterisation scheme is employed. In that case object localisation remains accurate so long as the ends of straight edges are visible. The results presented here are also relevant when parts of objects are broken off rather than occluded.

E. R. Davies

[1] Edward Roy Davies. A new parametrisation of the straight line and its application for the optimal detection of objects with straight edges , 1987, Pattern Recognit. Lett..

[2] Christopher M. Brown. Inherent Bias and Noise in the Hough Transform , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3] Saburo Tsuji,et al. Detection of Ellipses by a Modified Hough Transformation , 1978, IEEE Transactions on Computers.

[4] Jack Sklansky,et al. Finding circles by an array of accumulators , 1975, Commun. ACM.

[5] Richard O. Duda,et al. Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[6] Dana H. Ballard,et al. Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[7] Jack Sklansky,et al. On the Hough Technique for Curve Detection , 1978, IEEE Transactions on Computers.

[8] E. R. Davies. A new framework for analysing the properties of the generalised Hough transform , 1987, Pattern Recognit. Lett..

[9] Edward Roy Davies. The Performance of the Generalised Hough Transform: Concavities, Ambiguities and Positional Accuracy , 1987, Alvey Vision Conference.