The performance of a classifier is affected by a number of factors including classifier type, the input features and the desired output. This thesis examines the impact of feature selection and classification problem division on classification accuracy and complexity. Proper feature selection can reduce classifier size and improve classifier performance by minimizing the impact of noisy, redundant and correlated features. Noisy features can cause false association between the features and the classifier output. Redundant and correlated features increase classifier complexity without adding additional information. Output selection or classification problem division describes the division of a large classification problem into a set of smaller problems. Problem division can improve accuracy by allocating more resources to more difficult class divisions and enabling the use of more specific feature sets for each sub-problem. The first part of this thesis presents two methods for creating feature-selected hierarchical classifiers. The feature-selected hierarchical classification method jointly optimizes the features and classification tree-design using genetic algorithms. The multi-modal binary tree (MBT) method performs the class division and feature selection sequentially and tolerates misclassifications in the higher nodes of the tree. This yields a piecewise separation for classes that cannot be fully separated with a single classifier. Experiments show that the accuracy of MBT is comparable to other multi-class extensions, but with lower test time. Furthermore, the accuracy of MBT is significantly higher on multi-modal data sets. The second part of this thesis focuses on input feature selection measures. A number of filter-based feature subset evaluation measures are evaluated with the goal of assessing their performance with respect to specific classifiers. Although there are many feature selection measures proposed in literature, it is unclear which feature selection measures are appropriate for use with different classifiers. Sixteen common filter-based measures are tested on 20 real and 20 artificial data sets, which are designed to probe for specific feature selection challenges. The strengths and weaknesses of each measure are discussed with respect to the specific feature selection challenges in the artificial data sets, correlation with classifier accuracy and their ability to identify known informative features. The results indicate that the best filter measure is classifier-specific. K-nearest neighbours classifiers work well with subset-based RELIEF, correlation feature selection or conditional mutual information maximization, whereas Fisher's interclass separability criterion and conditional mutual information maximization work better for support vector machines. Based on the results of the feature selection experiments, two new filter-based measures are proposed based on conditional mutual information maximization, which performs well but cannot identify dependent features in a set and does not include a check for correlated features. Both new measures explicitly check for dependent features and the second measure also includes a term to discount correlated features. Both measures correctly identify known informative features in the artificial data sets and correlate well with classifier accuracy. The final part of this thesis examines the use of feature selection for time-series data by using feature selection to determine important individual time windows or key frames in the series. Time-series feature selection is used with the MBT algorithm to create classification trees for time-series data. The feature selected MBT algorithm is tested on two human motion recognition tasks: full-body human motion recognition from joint angle data and hand gesture recognition from electromyography data. Results indicate that the feature selected MBT is able to achieve high classification accuracy on the time-series data while maintaining a short test time.

We consider the application of Few-Shot Learning (FSL) and dimensionality reduction to the problem of human motion recognition (HMR). The structure of human motion has unique characteristics such as its dynamic and high-dimensional nature. Recent research on human motion recognition uses deep neural networks with multiple layers. Most importantly, large datasets will need to be collected to use such networks to analyze human motion. This process is both time-consuming and expensive since a large motion capture database must be collected and labeled. Despite significant progress having been made in human motion recognition, state-of-the-art algorithms still misclassify actions because of characteristics such as the difficulty in obtaining large-scale leveled human motion datasets. To address these limitations, we use metric-based FSL methods that use small-size data in conjunction with dimensionality reduction. We also propose a modified dimensionality reduction scheme based on the preservation of secants tailored to arbitrary useful distances, such as the geodesic distance learned by ISOMAP. We provide multiple experimental results that demonstrate improvements in human motion classification.

Abstract This thesis investigates vision based description and recognition of human movements. Automated vision based human motion analysis is a fundamental technology for creating video based human computer interaction systems. Because of its wide range of potential applications, the topic has become an active area of research in the computer vision community. This thesis proposes the use of low level description of dynamics for human movement description and recognition. Two groups of approaches are developed: first, texture based methods that extract dynamic features for human movement description, and second, a framework that considers ballistic dynamics for human movement segmentation and recognition. Two texture based descriptions for human movement analysis are introduced. The first method uses the temporal templates as a preprocessing stage and extracts a motion description using local binary pattern texture features. This approach is then extended to a spatiotemporal space and a dynamic texture based method that uses local binary patterns from three orthogonal planes is proposed. The method needs no accurate segmentation of silhouettes, rather, it is designed to work on image data. The dynamic texture based description is also applied to gait recognition. The proposed descriptions have been experimentally validated on publicly available databases. Psychological studies on human movement indicate that common movements such as reaching and striking are ballistic by nature. Based on the psychological observations this thesis considers the segmentation and recognition of ballistic movements using low level motion features. Experimental results on motion capture and video data show the effectiveness of the method. / Tiivistelmä Tässä väitöskirjassa tutkitaan ihmisen liikkeen kuvaamista ja tunnistamista konenäkömenetelmillä. Ihmisen liikkeen automaattinen analyysi on keskeinen teknologia luotaessa videopohjaisia järjestelmiä ihmisen ja koneen vuorovaikutukseen. Laajojen sovellusmahdollisuuksiensa myötä aiheesta on tullut aktiivinen tutkimusalue konenäön tutkimuksen piirissä. Väitöskirjassa tutkitaan matalan tason piirteiden käyttöä ihmisen liikkeen dynaamiikan kuvaamiseen ja tunnistamiseen. Työssä esitetään kaksi tekstuuripohjaista mentelmää ihmisen liikkeen kuvaamiseen ja viitekehys ballististen liikkeiden segmentointiin ja tunnistamiseen. Työssä esitetään kaksi tekstuuripohjaista menetelmää ihmisen liikkeen analysointiin. Ensimmäinen menetelmä käyttää esikäsittelynä ajallisia kuvamalleja ja kuvaa mallit paikallisilla binäärikuvioilla. Menetelmä laajennetaan myös tila-aika-avaruuteen. Dynaamiseen tekstuuriin perustuva menetelmä irroittaa paikalliset binäärikuviot tila-aika-avaruuden kolmelta ortogonaaliselta tasolta. Menetelmä ei vaadi ihmisen siluetin tarkkaa segmentointia kuvista, koska se on suunniteltu toimimaan suoraan kuvatiedon perusteella. Dynaamiseen tekstuuriin pohjautuvaa menetelmää sovelletaan myös henkilön tunnistamiseen kävelytyylin perusteella. Esitetyt menetelmät on kokeellisesti vahvistettu yleisesti käytetyillä ja julkisesti saatavilla olevilla tietokannoilla. Psykologiset tutkimukset ihmisen liikkumisesta osoittavat, että yleiset liikkeet, kuten kurkoittaminen ja iskeminen, ovat luonteeltaan ballistisia. Tässä työssä tarkastellaan ihmisen liikkeen ajallista segmentointia ja tunnistamista matalan tason liikepiirteistä hyödyntäen psykologisia havaintoja. Kokeelliset tulokset liikkeenkaappaus ja video aineistolla osoittavat menetelmän toimivan hyvin.