John Illingworth

A survey of the Hough transform

We present a comprehensive review of the Hough transform, HT, in image processing and computer vision. It has long been recognized as a technique of almost unique promise for shape and motion analysis in images containing noisy, missing, and extraneous data but its adoption has been slow due to its computational and storage complexity and the lack of a detailed understanding of its properties. However, in recent years much progress has been made in these areas. In this review we discuss ideas for the efficient implementation of the HT and present results on the analytic and empirical performance of various methods. We also report the relationship of Hough methods and other transforms and consider applications in which the HT has been used. It seems likely that the HT will be an increasingly used technique and we hope that this survey will provide a useful guide to quickly acquaint researchers with the main literature in this research area.

Minimum error thresholding

Abstract A computationally efficient solution to the problem of minimum error thresholding is derived under the assumption of object and pixel grey level values being normally distributed. The method is applicable in multithreshold selection.

Comparative study of Hough transform methods for circle finding

Abstract A variety of circle detection methods which are based on variations of the Hough Transform are investigated. The five methods considered are the standard Hough Transform, the Fast Hough Transform of Li et al. 1 , a two stage Hough method, and two space saving approaches based on the method devised by Gerig and Klein 2 . The performance of each of the methods has been compared on synthetic imagery and real images from a metallurgical application. Figures and comments are presented concerning the accuracy, reliability, computational efficiency and storage requirements of each of the methods.

On threshold selection using clustering criteria

The threshold selection method of N. Otsu (ibid., vol.SMC-9, p.62-6, 1979) is shown to break down for a certain range of object-to-background pixel population ratios. Modifications to Otsus method are proposed to overcome some of its limitations. The findings are also relevant to the closely related methods of T. Ridler (1978) and H.J. Trussell (1979).

THRESHOLD SELECTION BASED ON A SIMPLE IMAGE STATISTIC

Abstract The problem of automatic threshold selection is considered. After a brief review of available techniques, a novel method is proposed. It is based on image statistics which can be computed without histogramming the grey level values of the image. A detailed analysis of the properties of the algorithm is then carried out. The effectiveness of the method is shown on a number of practical examples.

Reliable Surface Reconstructiuon from Multiple Range Images

This paper addresses the problem of reconstructing an integrated 3D model from multiple 2.5D range images. A novel integration algorithm is presented based on a continuous implicit surface representation. This is the first reconstruction algorithm to use operations in 3D space only. The algorithm is guaranteed to reconstruct the correct topology of surface features larger than the range image sampling resolution. Reconstruction of triangulated models from multi-image data sets is demonstrated for complex objects. Performance characterization of existing range image integration algorithms is addressed in the second part of this paper. This comparison defines the relative computational complexity and geometric limitations of existing integration algorithms.

Detecting partially occluded ellipses using the Hough transform

Abstract This paper considers the problem of detecting elliptical curves using Hough transform (HT) methods. Storage and efficiency problems are overcome by decomposing the problem into two stages. The first stage uses a novel constraint as the basis for a Hough transform to detect the ellipse centre while the second stage finds the remaining parameters using a simple but efficient focusing implementation of the HT. The method is applicable in many situations where previous HT schemes would fail. Results are demonstrated for complicated image data containing several overlapping and occluding ellipses.

Evidence for planar events in e+e− annihilation at high energies

Abstract Hadron jets produced in e+e− annihilation between 13 GeV and 31.6 GeV in c.m. at PETRA are analyzed. The transverse momentum of the jets is found to increase strongly with c.m. energy. The broadening of the jets is not uniform in azimuthal angle around the quark direction but tends to yield planar events with large and growing transverse momenta in the plane and smaller transverse momenta normal to the plane. The simple q q collinear jet picture is ruled out. The observation of planar events shows that there are three basic particles in the final state. Indeed, several events with three well-separated jets of hadrons are observed at the highest energies. This occurs naturally when the outgoing quark radiates a hard noncollinear gluon, i.e., e + e − → q q g with the quarks and the gluons fragmenting into hadrons with limited transverse momenta.

Relaxation labelling algorithms-a review

Abstract An important research topic in image processing and image interpretation methodology is the development of methods to incorporate contextual information into the interpretation of objects. Over the last decade, relaxation labelling has been a useful and much studied approach to this problem. It is an attractive technique because it is highly parallel, involving the propagation of local information via iterative processing. The paper. surveys the literature pertaining to relaxation labelling and highlights the important theoretical advances and the interesting applications for which it has proven useful.

Action Recognition Using Mined Hierarchical Compound Features

The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single-frame object recognition and adapting them for temporal-based action recognition. Inspired by the success of interest points in the 2D spatial domain, their 3D (space-time) counterparts typically form the basic components used to describe actions, and in action recognition the features used are often engineered to fire sparsely. This is to ensure that the problem is tractable; however, this can sacrifice recognition accuracy as it cannot be assumed that the optimum features in terms of class discrimination are obtained from this approach. In contrast, we propose to initially use an overcomplete set of simple 2D corners in both space and time. These are grouped spatially and temporally using a hierarchical process, with an increasing search area. At each stage of the hierarchy, the most distinctive and descriptive features are learned efficiently through data mining. This allows large amounts of data to be searched for frequently reoccurring patterns of features. At each level of the hierarchy, the mined compound features become more complex, discriminative, and sparse. This results in fast, accurate recognition with real-time performance on high-resolution video. As the compound features are constructed and selected based upon their ability to discriminate, their speed and accuracy increase at each level of the hierarchy. The approach is tested on four state-of-the-art data sets, the popular KTH data set to provide a comparison with other state-of-the-art approaches, the Multi-KTH data set to illustrate performance at simultaneous multiaction classification, despite no explicit localization information provided during training. Finally, the recent Hollywood and Hollywood2 data sets provide challenging complex actions taken from commercial movie sequences. For all four data sets, the proposed hierarchical approach outperforms all other methods reported thus far in the literature and can achieve real-time operation.