Improved Response Modelling on Weak Classifiers for Boosting

Overett, Gary

doi:10.1109/robot.2007.364061

Cited by 10 publications

(20 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a real pedestrian detection application, it makes sense to have a cascade of strong classifiers, with the first few strong classifiers built using HistFeat and the following strong classifiers built using Haar features. All comparisons of HistFeat were made against both a basic version of the Haar feature [3] [6] as well as a much improved version [9]. These were also highly optimised implementations, governing that the results are indeed competitive.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The histogram feature - a resource-efficient Weak Classifier

Pettersson

Andersson

2008

2008 IEEE Intelligent Vehicles Symposium

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents a Weak Classifier that is extremely fast to compute, yet highly discriminant. This Weak Classifier may be used in, for example, a boosting framework and is the result of a novel way of organizing and evaluating Histograms of Oriented Gradients. The method requires only one access to main memory to evaluate each feature, in comparison with the more well-known Haar features which require somewhere between six and nine memory accesses to evaluate each feature. This low memory bandwidth makes the Weak Classifier especially ideal for use in small systems with little or no memory cache available.The presented Weak Classifier has been extensively tested in a boosted framework on data sets consisting of pedestrians and various road signs. The classifier yields detection results that are far superior than the results obtained from Haar features when tested on road signs and similar structures, whereas the detection results are comparable to those of Haar features when tested on pedestrians. In addition, the computational resources necessary for these results have been shown to be considerably smaller for the new weak classifier.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The features used were HistFeat with a 8 × 8 and a 16 × 16 a posteriori map, Haar features as implemented in [6], as well as the improvement on Haar features as implemented in [9]. These features are referred to as h8, h16, vpdf and spdf in the graphs.…”

Section: ) Datasetmentioning

confidence: 99%

The histogram feature - a resource-efficient Weak Classifier

Pettersson

Andersson

2008

2008 IEEE Intelligent Vehicles Symposium

Self Cite

View full text Add to dashboard Cite

show abstract

“…HistFeat is implemented as in [5]. Haar features are implemented in the classical fashion but we use the improved smoothed learning as in [14]. RHOG features are implemented in a similar fashion to the Rectangular HOG features in [2].…”

Section: Methodsmentioning

confidence: 99%

“…These are both fast and discriminative [17] [18]. However, the benefit of improved modelling while keeping the fast lookup table approach has been shown in [19] and [14]. For Haar features this modelling approach yielded a 75% average error reduction [19].…”

Section: ) Finding a 1d Projectionmentioning

confidence: 99%

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

Overett

Andersson

Pettersson

2009

2009 IEEE Intelligent Vehicles Symposium

Self Cite

View full text Add to dashboard Cite

Abstract-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.In terms of computational complexity it is a heterogeneous feature set. I.e. it has fast and slow variants. In order to optimize our feature selections between the faster and slower features available we implement a recently proposed modification to the RealBoost feature selection rule. This modification provides an additional means to balance processing and memory bandwidth on ordinary PC architectures. This feature set is suitable for use within typical boosting frameworks. It is compared to Haar and Rectangular HOG features, as well the related feature HistFeat. The new feature set contains two variants, LiteHOG and LiteHOG+, which we compare. Both LiteHOG and LiteHOG+ features show promising results on road sign and pedestrian detection tasks.

show abstract

“…imposes heavy restrictions on their applications [18], [22]. The more partitions the LUT classifiers have, the faster convergence speed and also the worse generalization performance they probably bear.…”

mentioning

confidence: 99%

Smoothing LUT classifiers for robust face detection

Wen

Xiong

2013

2013 IEEE Third International Conference on Information Science and Technology (ICIST)

View full text Add to dashboard Cite

Look-up table (LUT) classifiers are often used to construct concise classifiers for rapid object detection due to their favorable convergent ability. However, their poor generalization ability imposes restrictions on their applications. A novel improvement to LUT classifiers is proposed in this paper where the new confident of each partition is recalculated by smoothing the old ones within its neighbor partitions. The new confidents are more generalizable than the old ones because each of the new predicts is supported by more training samples and the high frequency components in the old predict sequences are suppressed greatly through smoothing operation. Both weight sum smoothing method and confident smoothing method are introduced here, which all bring negligible extra computation cost in training time and no extra cost in test time. Experimental results in the domain of upright frontal face detection using smoothed LUT classifiers with identical smoothing width and smoothing factor for all partitions based on Haar-like rectangle features show that smoothed LUT classifiers generalize much better and also converge more or less worse than unsmooth LUT classifiers. Specifically, smoothed LUT classifiers can delicately balance between generalization ability and convergent ability through carefully set smoothing parameters. I. INTRODUCTIONRIGINATED from domain-partitioning confidencerated hypotheses [1], Look-up table (LUT) classifiers [5], [2], [17] (response binning classifiers) are often used to construct very concise classifiers through Real AdaBoost [1] for rapid object detection and classification due to their favorable convergent ability, such as face detection [2]-[4], [9]-[16], [19]-[21], gender classification [5], pedestrian detection [6], [22], [23], incident detection [7], etc. The LUT classifiers used in these papers are somewhat revised by the authors to meet their needs, such as using adaptive (much less) partitions for resource-constrained devices [9], discarding negative responses and adding global predicts [7], online adjusting the confidents for online learning [10], using 0-1 version LUT classifiers to meet the needs of Discrete AdaBoost other than Real AdaBoost [5], applying Bayesian error based LUT classifiers for higher performance [4], etc. Besides, various criterions are used to choose optimal LUT classifiers to form strong classifiers, such as minimizing Bhattacharyya distance [1], minimizing Kullback-Leibler divergence [19], minimizing symmetric Jensen-Shannon divergence [12], etc. However, the poor generalization ability of LUT classifiers Manuscript received December 31, 2012 J Wen, corresponding author, is with the College

show abstract

Improved Response Modelling on Weak Classifiers for Boosting

Cited by 10 publications

References 14 publications

The histogram feature - a resource-efficient Weak Classifier

The histogram feature - a resource-efficient Weak Classifier

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

Smoothing LUT classifiers for robust face detection

Contact Info

Product

Resources

About