Gary Overett - Academia.edu (original) (raw)

Papers by Gary Overett

Research paper thumbnail of On the importance of accurate weak classifier learning for boosted weak classifiers

2008 IEEE Intelligent Vehicles Symposium, 2008

, has shown that improving model learning for weak classifiers can yield significant gains in the... more , has shown that improving model learning for weak classifiers can yield significant gains in the overall accuracy of a boosted classifier. However, most published classifier boosting research relies only on rudimentary learning techniques for weak classifiers. So while it is known that improving the model learning can greatly improve the accuracy of the resulting strong classifier, it remains to be shown how much can yet be gained by further improving the model learning at the weak classifier level. This paper derives a very accurate model learning method for weak classifiers based on the popular Haar-like features and presents an investigation of its usefulness compared to the standard and recent approaches. The accuracy of the new method is shown by demonstrating the new models ability to predict ROC performance on validation data. A discussion of the problems in learning accurate weak hypotheses is given, along with example solutions. It is also shown that a previous simpler method can be further improved. Lastly, we show that improving model accuracy does not continue to yield improved overall classification beyond a certain point. At this point the learning technique, in this case RealBoost, is unable to make gains from the improved model data.

Research paper thumbnail of Fast features for time constrained object detection

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2009

This paper concerns itself with the development and design of fast features suitable for time con... more This paper concerns itself with the development and design of fast features suitable for time constrained object detection. Primarily we consider three aspects of feature design; the form of the precomputed datatype (e.g. the integral image), the form of the features themselves (i.e. the measurements made of an image), and the models/weaklearners used to construct weak classifiers (class, non-class statistics). The paper is laid out as a guide to feature designers, demonstrating how appropriate choices in combining the above three characteristics can prevent bottlenecks in the run-time evaluation of classifiers. This leads to reductions in the computational time of the features themselves and, by providing more discriminant features, reductions in the time taken to reach specific classification error rates.

Research paper thumbnail of Large scale sign detection using HOG feature variants

2011 IEEE Intelligent Vehicles Symposium (IV), 2011

In this paper we present two variant formulations of the well-known Histogram of Oriented Gradien... more In this paper we present two variant formulations of the well-known Histogram of Oriented Gradients (HOG) features and provide a comparison of these features on a large scale sign detection problem. The aim of this research is to find features capable of driving further improvements atop a preexisting detection framework used commercially to detect traffic signs on the scale of entire national road networks (1000's of kilometres of video). We assume the computationally efficient framework of a cascade of boosted weak classifiers. Rather than comparing features on the general problem of detection we compare their merits in the final stages of a cascaded detection problem where a feature's ability to reduce error is valued more highly than computational efficiency.

Research paper thumbnail of Boosting a heterogeneous pool of fast HOG features for pedestrian and sign detection

2009 IEEE Intelligent Vehicles Symposium, 2009

This paper presents a fast Histogram of Oriented Gradients (HOG) based weak classifier that is ex... more This paper presents a fast Histogram of Oriented Gradients (HOG) based weak classifier that is extremely fast to compute and highly discriminative. This feature set has been developed in an effort to balance the required processing and memory bandwidth so as to eliminate bottlenecks during run time evaluation. The feature set is the next generation in a series of features based on a novel precomputed image for HOG based features. It contains features which are more balanced in terms of processing and memory requirements than its predecessors, has a larger and richer feature space, and is more discriminant on a per feature basis.

Research paper thumbnail of A new pedestrian dataset for supervised learning

2008 IEEE Intelligent Vehicles Symposium, 2008

This paper presents a comparative analysis of different pedestrian dataset characteristics. The m... more This paper presents a comparative analysis of different pedestrian dataset characteristics. The main goal of the research is to determine what characteristics are desirable for improved training and validation of pedestrian detectors and classifiers. The work focuses on those aspects of the dataset which affect classification success using the most common boosting methods.

Research paper thumbnail of Boosting with Multiple Classifier Families

2007 IEEE Intelligent Vehicles Symposium, 2007

This paper demonstrates the importance of creating an even playing field between weak classifiers... more This paper demonstrates the importance of creating an even playing field between weak classifiers and classifier families in the RealBoost boosting algorithm. Classifier families are constructed based on Haar-like features in various color spaces, which are then trained simultaneously in RealBoost to create a strong classifier rule. It is shown that the usual method for minimising error at each RealBoost round may express a bias against some weak classifier families. A particular bias toward overfitting features is found. An initial method for achieving parity between families of weak classifiers is applied to improve classification.

Research paper thumbnail of Creating robust high-throughput traffic sign detectors using centre-surround HOG statistics

Machine Vision and Applications, 2014

ABSTRACT In this paper, we detail a system for creating object detectors which meet the extreme d... more ABSTRACT In this paper, we detail a system for creating object detectors which meet the extreme demands of real-world traffic sign detection applications such as GPS map making and real-time in-car traffic sign detection. The resulting detectors are designed to detect and locate multiple traffic sign types in high-definition video (high throughput) from several cameras captured along thousands of kilometers of road with minimal false-positives and detection rates in excess of 99%. This allows for the accurate detection and location of traffic signs in geo-tagged video datasets of entire national road networks in reasonable time using only moderate computing infrastructure. A key to the success of the methods described in this paper is the use of extremely efficient classifier features. In this paper, we identify two obstacles to achieving the desired performance for all target traffic sign types, feature memory bandwidth requirements and feature discriminance. We introduce our use of centre-surround histogram of oriented gradient (HOG) statistics which greatly reduce the per-feature memory bandwidth requirements. Subsequently we extend our use of centre-surround HOG statistics to the color domain, raising the discriminant power of the final classifiers for more challenging sign types.

Research paper thumbnail of DÉTECTION D'OBJETS REPRÉSENTÉS DANS DES IMAGES

Research paper thumbnail of Stereo vision motion detection from a moving platform

Stereo Vision Motion Detection from a Moving Platform Gary Overett1 David Austin1,2gary@syseng.an... more Stereo Vision Motion Detection from a Moving Platform Gary Overett1 David Austin1,2gary@syseng.anu.edu.au d.austin@computer.org ... Some very effective tracking systems such as [Sogo et al., 2000] and [Mittal and Davis, 2002] rely on multiple views from around the room. ...

Research paper thumbnail of Fast sum of absolute differences visual landmark detector

Abstract-This paper presents various opthisations that can be applied to the Sum of Absolute Diff... more Abstract-This paper presents various opthisations that can be applied to the Sum of Absolute Differences (SAD) correlation algorithm for automated landmark detection. This has applica-tions in mobile robotic navigation and mapping. We show how some assumptions about ...

Research paper thumbnail of Improved Response Modelling on Weak Classifiers for Boosting

Proceedings 2007 IEEE International Conference on Robotics and Automation, 2007

This paper demonstrates a method of increasing the quality of weak classifiers in the boosting co... more This paper demonstrates a method of increasing the quality of weak classifiers in the boosting context by using improved response modelling. The new method improves upon the results of a recent response binning approach proposed by Rasolzadeh et al. . For experimental purposes the improved method is applied to the familiar Haar features as used by Viola and Jones in their face/pedestrian detection systems. However, the methods benefits are general and therefore not restricted to this particular feature type. Unlike many previous methods, this method is suitable for modelling multi-modal responses and is highly resistant to overfitting. It does this by adaptively choosing suitable support regions around the values taken by the standard response binning method. More accurate models are produced, with particular improvement around the final decision boundary. It is shown that the new method can be trained with one tenth of the training data required to achieve similar results on previous methods. This substantially lowers the overall training time of the system. The method's ability to consistently produce better hypotheses over a variety of pedestrian detection tasks is shown.

Research paper thumbnail of On the importance of accurate weak classifier learning for boosted weak classifiers

2008 IEEE Intelligent Vehicles Symposium, 2008

, has shown that improving model learning for weak classifiers can yield significant gains in the... more , has shown that improving model learning for weak classifiers can yield significant gains in the overall accuracy of a boosted classifier. However, most published classifier boosting research relies only on rudimentary learning techniques for weak classifiers. So while it is known that improving the model learning can greatly improve the accuracy of the resulting strong classifier, it remains to be shown how much can yet be gained by further improving the model learning at the weak classifier level. This paper derives a very accurate model learning method for weak classifiers based on the popular Haar-like features and presents an investigation of its usefulness compared to the standard and recent approaches. The accuracy of the new method is shown by demonstrating the new models ability to predict ROC performance on validation data. A discussion of the problems in learning accurate weak hypotheses is given, along with example solutions. It is also shown that a previous simpler method can be further improved. Lastly, we show that improving model accuracy does not continue to yield improved overall classification beyond a certain point. At this point the learning technique, in this case RealBoost, is unable to make gains from the improved model data.

Research paper thumbnail of Fast features for time constrained object detection

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2009

This paper concerns itself with the development and design of fast features suitable for time con... more This paper concerns itself with the development and design of fast features suitable for time constrained object detection. Primarily we consider three aspects of feature design; the form of the precomputed datatype (e.g. the integral image), the form of the features themselves (i.e. the measurements made of an image), and the models/weaklearners used to construct weak classifiers (class, non-class statistics). The paper is laid out as a guide to feature designers, demonstrating how appropriate choices in combining the above three characteristics can prevent bottlenecks in the run-time evaluation of classifiers. This leads to reductions in the computational time of the features themselves and, by providing more discriminant features, reductions in the time taken to reach specific classification error rates.

Research paper thumbnail of Large scale sign detection using HOG feature variants

2011 IEEE Intelligent Vehicles Symposium (IV), 2011

In this paper we present two variant formulations of the well-known Histogram of Oriented Gradien... more In this paper we present two variant formulations of the well-known Histogram of Oriented Gradients (HOG) features and provide a comparison of these features on a large scale sign detection problem. The aim of this research is to find features capable of driving further improvements atop a preexisting detection framework used commercially to detect traffic signs on the scale of entire national road networks (1000's of kilometres of video). We assume the computationally efficient framework of a cascade of boosted weak classifiers. Rather than comparing features on the general problem of detection we compare their merits in the final stages of a cascaded detection problem where a feature's ability to reduce error is valued more highly than computational efficiency.

Research paper thumbnail of Boosting a heterogeneous pool of fast HOG features for pedestrian and sign detection

2009 IEEE Intelligent Vehicles Symposium, 2009

This paper presents a fast Histogram of Oriented Gradients (HOG) based weak classifier that is ex... more This paper presents a fast Histogram of Oriented Gradients (HOG) based weak classifier that is extremely fast to compute and highly discriminative. This feature set has been developed in an effort to balance the required processing and memory bandwidth so as to eliminate bottlenecks during run time evaluation. The feature set is the next generation in a series of features based on a novel precomputed image for HOG based features. It contains features which are more balanced in terms of processing and memory requirements than its predecessors, has a larger and richer feature space, and is more discriminant on a per feature basis.

Research paper thumbnail of A new pedestrian dataset for supervised learning

2008 IEEE Intelligent Vehicles Symposium, 2008

This paper presents a comparative analysis of different pedestrian dataset characteristics. The m... more This paper presents a comparative analysis of different pedestrian dataset characteristics. The main goal of the research is to determine what characteristics are desirable for improved training and validation of pedestrian detectors and classifiers. The work focuses on those aspects of the dataset which affect classification success using the most common boosting methods.

Research paper thumbnail of Boosting with Multiple Classifier Families

2007 IEEE Intelligent Vehicles Symposium, 2007

This paper demonstrates the importance of creating an even playing field between weak classifiers... more This paper demonstrates the importance of creating an even playing field between weak classifiers and classifier families in the RealBoost boosting algorithm. Classifier families are constructed based on Haar-like features in various color spaces, which are then trained simultaneously in RealBoost to create a strong classifier rule. It is shown that the usual method for minimising error at each RealBoost round may express a bias against some weak classifier families. A particular bias toward overfitting features is found. An initial method for achieving parity between families of weak classifiers is applied to improve classification.

Research paper thumbnail of Creating robust high-throughput traffic sign detectors using centre-surround HOG statistics

Machine Vision and Applications, 2014

ABSTRACT In this paper, we detail a system for creating object detectors which meet the extreme d... more ABSTRACT In this paper, we detail a system for creating object detectors which meet the extreme demands of real-world traffic sign detection applications such as GPS map making and real-time in-car traffic sign detection. The resulting detectors are designed to detect and locate multiple traffic sign types in high-definition video (high throughput) from several cameras captured along thousands of kilometers of road with minimal false-positives and detection rates in excess of 99%. This allows for the accurate detection and location of traffic signs in geo-tagged video datasets of entire national road networks in reasonable time using only moderate computing infrastructure. A key to the success of the methods described in this paper is the use of extremely efficient classifier features. In this paper, we identify two obstacles to achieving the desired performance for all target traffic sign types, feature memory bandwidth requirements and feature discriminance. We introduce our use of centre-surround histogram of oriented gradient (HOG) statistics which greatly reduce the per-feature memory bandwidth requirements. Subsequently we extend our use of centre-surround HOG statistics to the color domain, raising the discriminant power of the final classifiers for more challenging sign types.

Research paper thumbnail of DÉTECTION D'OBJETS REPRÉSENTÉS DANS DES IMAGES

Research paper thumbnail of Stereo vision motion detection from a moving platform

Stereo Vision Motion Detection from a Moving Platform Gary Overett1 David Austin1,2gary@syseng.an... more Stereo Vision Motion Detection from a Moving Platform Gary Overett1 David Austin1,2gary@syseng.anu.edu.au d.austin@computer.org ... Some very effective tracking systems such as [Sogo et al., 2000] and [Mittal and Davis, 2002] rely on multiple views from around the room. ...

Research paper thumbnail of Fast sum of absolute differences visual landmark detector

Abstract-This paper presents various opthisations that can be applied to the Sum of Absolute Diff... more Abstract-This paper presents various opthisations that can be applied to the Sum of Absolute Differences (SAD) correlation algorithm for automated landmark detection. This has applica-tions in mobile robotic navigation and mapping. We show how some assumptions about ...

Research paper thumbnail of Improved Response Modelling on Weak Classifiers for Boosting

Proceedings 2007 IEEE International Conference on Robotics and Automation, 2007

This paper demonstrates a method of increasing the quality of weak classifiers in the boosting co... more This paper demonstrates a method of increasing the quality of weak classifiers in the boosting context by using improved response modelling. The new method improves upon the results of a recent response binning approach proposed by Rasolzadeh et al. . For experimental purposes the improved method is applied to the familiar Haar features as used by Viola and Jones in their face/pedestrian detection systems. However, the methods benefits are general and therefore not restricted to this particular feature type. Unlike many previous methods, this method is suitable for modelling multi-modal responses and is highly resistant to overfitting. It does this by adaptively choosing suitable support regions around the values taken by the standard response binning method. More accurate models are produced, with particular improvement around the final decision boundary. It is shown that the new method can be trained with one tenth of the training data required to achieve similar results on previous methods. This substantially lowers the overall training time of the system. The method's ability to consistently produce better hypotheses over a variety of pedestrian detection tasks is shown.