Activity recognition using binary tree SVM

This paper presents an effective classification method based on Support Vector Machines (SVM) in the context of activity recognition. Local features that capture both spatial and temporal information in activity videos have made significant progress recently. Efficient and effective features, feature representation and classification plays a crucial role in activity recognition. For classification, SVMs are popularly used because of their simplicity and efficiency; however the common multi-class SVM approaches applied suffer from limitations including having easily confused classes and been computationally inefficient. We propose using a binary tree SVM to address the shortcomings of multi-class SVMs in activity recognition. We proposed constructing a binary tree using Gaussian Mixture Models (GMM), where activities are repeatedly allocated to subnodes until every new created node contains only one activity. Then, for each internal node a separate SVM is learned to classify activities, which significantly reduces the training time and increases the speed of testing compared to popular the `one-against-the-rest' multi-class SVM classifier. Experiments carried out on the challenging and complex Hollywood dataset demonstrates comparable performance over the baseline bag-of-features method.

Physical activity recognition from accelerometer data using a multi-scale ensemble method

Accurate and detailed measurement of an individual's physical activity is a key requirement for helping researchers understand the relationship between physical activity and health. Accelerometers have become the method of choice for measuring physical activity due to their small size, low cost, convenience and their ability to provide objective information about physical activity. However, interpreting accelerometer data once it has been collected can be challenging. In this work, we applied machine learning algorithms to the task of physical activity recognition from triaxial accelerometer data. We employed a simple but effective approach of dividing the accelerometer data into short non-overlapping windows, converting each window into a feature vector, and treating each feature vector as an i.i.d training instance for a supervised learning algorithm. In addition, we improved on this simple approach with a multi-scale ensemble method that did not need to commit to a single window size and was able to leverage the fact that physical activities produced time series with repetitive patterns and discriminative features for physical activity occurred at different temporal scales.

Machine learning for activity recognition : hip versus wrist data

Problem addressed Wrist-worn accelerometers are associated with greater compliance. However, validated algorithms for predicting activity type from wrist-worn accelerometer data are lacking. This study compared the activity recognition rates of an activity classifier trained on acceleration signal collected on the wrist and hip. Methodology 52 children and adolescents (mean age 13.7 +/- 3.1 year) completed 12 activity trials that were categorized into 7 activity classes: lying down, sitting, standing, walking, running, basketball, and dancing. During each trial, participants wore an ActiGraph GT3X+ tri-axial accelerometer on the right hip and the non-dominant wrist. Features were extracted from 10-s windows and inputted into a regularized logistic regression model using R (Glmnet + L1). Results Classification accuracy for the hip and wrist was 91.0% +/- 3.1% and 88.4% +/- 3.0%, respectively. The hip model exhibited excellent classification accuracy for sitting (91.3%), standing (95.8%), walking (95.8%), and running (96.8%); acceptable classification accuracy for lying down (88.3%) and basketball (81.9%); and modest accuracy for dance (64.1%). The wrist model exhibited excellent classification accuracy for sitting (93.0%), standing (91.7%), and walking (95.8%); acceptable classification accuracy for basketball (86.0%); and modest accuracy for running (78.8%), lying down (74.6%) and dance (69.4%). Potential Impact Both the hip and wrist algorithms achieved acceptable classification accuracy, allowing researchers to use either placement for activity recognition.

Elliptical summary randomisation for sensor-based human activity recognition

Many conventional statistical machine learning al- gorithms generalise poorly if distribution bias ex- ists in the datasets. For example, distribution bias arises in the context of domain generalisation, where knowledge acquired from multiple source domains need to be used in a previously unseen target domains. We propose Elliptical Summary Randomisation (ESRand), an efficient domain generalisation approach that comprises of a randomised kernel and elliptical data summarisation. ESRand learns a domain interdependent projection to a la- tent subspace that minimises the existing biases to the data while maintaining the functional relationship between domains. In the latent subspace, ellipsoidal summaries replace the samples to enhance the generalisation by further removing bias and noise in the data. Moreover, the summarisation enables large-scale data processing by significantly reducing the size of the data. Through comprehensive analysis, we show that our subspace-based approach outperforms state-of-the-art results on several activity recognition benchmark datasets, while keeping the computational complexity significantly low.

Multiple instance dictionary learning for activity representation

This paper presents an effective feature representation method in the context of activity recognition. Efficient and effective feature representation plays a crucial role not only in activity recognition, but also in a wide range of applications such as motion analysis, tracking, 3D scene understanding etc. In the context of activity recognition, local features are increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational requirements, their performance is still limited for real world applications due to a lack of contextual information and models not being tailored to specific activities. We propose a new activity representation framework to address the shortcomings of the popular, but simple bag-of-words approach. In our framework, first multiple instance SVM (mi-SVM) is used to identify positive features for each action category and the k-means algorithm is used to generate a codebook. Then locality-constrained linear coding is used to encode the features into the generated codebook, followed by spatio-temporal pyramid pooling to convey the spatio-temporal statistics. Finally, an SVM is used to classify the videos. Experiments carried out on two popular datasets with varying complexity demonstrate significant performance improvement over the base-line bag-of-feature method.

Semi-supervised intelligent surveillance system for secure environments

This paper proposes a semi-supervised intelligent visual surveillance system to exploit the information from multi-camera networks for the monitoring of people and vehicles. Modules are proposed to perform critical surveillance tasks including: the management and calibration of cameras within a multi-camera network; tracking of objects across multiple views; recognition of people utilising biometrics and in particular soft-biometrics; the monitoring of crowds; and activity recognition. Recent advances in these computer vision modules and capability gaps in surveillance technology are also highlighted.

The HarmonyGrid : music, space and performance in grid music systems

This research explores music in space, as experienced through performing and music-making with interactive systems. It explores how musical parameters may be presented spatially and displayed visually with a view to their exploration by a musician during performance. Spatial arrangements of musical components, especially pitches and harmonies, have been widely studied in the literature, but the current capabilities of interactive systems allow the improvisational exploration of these musical spaces as part of a performance practice. This research focuses on quantised spatial organisation of musical parameters that can be categorised as grid music systems (GMSs), and interactive music systems based on them. The research explores and surveys existing and historical uses of GMSs, and develops and demonstrates the use of a novel grid music system designed for whole body interaction. Grid music systems provide plotting of spatialised input to construct patterned music on a two-dimensional grid layout. GMSs are navigated to construct a sequence of parametric steps, for example a series of pitches, rhythmic values, a chord sequence, or terraced dynamic steps. While they are conceptually simple when only controlling one musical dimension, grid systems may be layered to enable complex and satisfying musical results. These systems have proved a viable, effective, accessible and engaging means of music-making for the general user as well as the musician. GMSs have been widely used in electronic and digital music technologies, where they have generally been applied to small portable devices and software systems such as step sequencers and drum machines. This research shows that by scaling up a grid music system, music-making and musical improvisation are enhanced, gaining several advantages: (1) Full body location becomes the spatial input to the grid. The system becomes a partially immersive one in four related ways: spatially, graphically, sonically and musically. (2) Detection of body location by tracking enables hands-free operation, thereby allowing the playing of a musical instrument in addition to “playing” the grid system. (3) Visual information regarding musical parameters may be enhanced so that the performer may fully engage with existing spatial knowledge of musical materials. The result is that existing spatial knowledge is overlaid on, and combined with, music-space. Music-space is a new concept produced by the research, and is similar to notions of other musical spaces including soundscape, acoustic space, Smalley's “circumspace” and “immersive space” (2007, 48-52), and Lotis's “ambiophony” (2003), but is rather more textural and “alive”—and therefore very conducive to interaction. Music-space is that space occupied by music, set within normal space, which may be perceived by a person located within, or moving around in that space. Music-space has a perceivable “texture” made of tensions and relaxations, and contains spatial patterns of these formed by musical elements such as notes, harmonies, and sounds, changing over time. The music may be performed by live musicians, created electronically, or be prerecorded. Large-scale GMSs have the capability not only to interactively display musical information as music representative space, but to allow music-space to co-exist with it. Moving around the grid, the performer may interact in real time with musical materials in music-space, as they form over squares or move in paths. Additionally he/she may sense the textural matrix of the music-space while being immersed in surround sound covering the grid. The HarmonyGrid is a new computer-based interactive performance system developed during this research that provides a generative music-making system intended to accompany, or play along with, an improvising musician. This large-scale GMS employs full-body motion tracking over a projected grid. Playing with the system creates an enhanced performance employing live interactive music, along with graphical and spatial activity. Although one other experimental system provides certain aspects of immersive music-making, currently only the HarmonyGrid provides an environment to explore and experience music-space in a GMS.

Class-specific sparse codes for representing activities

In this paper we investigate the effectiveness of class specific sparse codes in the context of discriminative action classification. The bag-of-words representation is widely used in activity recognition to encode features, and although it yields state-of-the art performance with several feature descriptors it still suffers from large quantization errors and reduces the overall performance. Recently proposed sparse representation methods have been shown to effectively represent features as a linear combination of an over complete dictionary by minimizing the reconstruction error. In contrast to most of the sparse representation methods which focus on Sparse-Reconstruction based Classification (SRC), this paper focuses on a discriminative classification using a SVM by constructing class-specific sparse codes for motion and appearance separately. Experimental results demonstrates that separate motion and appearance specific sparse coefficients provide the most effective and discriminative representation for each class compared to a single class-specific sparse coefficients.

The delta-phase spectrum with application to voice activity detection and speaker recognition

For several reasons, the Fourier phase domain is less favored than the magnitude domain in signal processing and modeling of speech. To correctly analyze the phase, several factors must be considered and compensated, including the effect of the step size, windowing function and other processing parameters. Building on a review of these factors, this paper investigates a spectral representation based on the Instantaneous Frequency Deviation, but in which the step size between processing frames is used in calculating phase changes, rather than the traditional single sample interval. Reflecting these longer intervals, the term delta-phase spectrum is used to distinguish this from instantaneous derivatives. Experiments show that mel-frequency cepstral coefficients features derived from the delta-phase spectrum (termed Mel-Frequency delta-phase features) can produce broadly similar performance to equivalent magnitude domain features for both voice activity detection and speaker recognition tasks. Further, it is shown that the fusion of the magnitude and phase representations yields performance benefits over either in isolation.

Spatial Sciences Student Awards Recognition : News from School of Urban Development, QUT

Summary of Spatial Sciences (Surveying) Student Prize Ceremony were recently held at The Old Government House - QUT Cultural Precinct. This short industry article briefly outlines the 15 student award descriptions and some photos of 2011 recipients and thanks industry sponsors.

Towards bio-inspired place recognition over multiple spatial scales

This paper presents a new multi-scale place recognition system inspired by the recent discovery of overlapping, multi-scale spatial maps stored in the rodent brain. By training a set of Support Vector Machines to recognize places at varying levels of spatial specificity, we are able to validate spatially specific place recognition hypotheses against broader place recognition hypotheses without sacrificing localization accuracy. We evaluate the system in a range of experiments using cameras mounted on a motorbike and a human in two different environments. At 100% precision, the multiscale approach results in a 56% average improvement in recall rate across both datasets. We analyse the results and then discuss future work that may lead to improvements in both robotic mapping and our understanding of sensory processing and encoding in the mammalian brain.

Pre-experimental familiarization increases hippocampal activity for both targets and lures in recognition memory: An fMRI study

In the present study, items pre-exposed in a familiarization series were included in a list discrimination task to manipulate memory strength. At test, participants were required to discriminate strong targets and strong lures from weak targets and new lures. This resulted in a concordant pattern of increased "old" responses to strong targets and lures. Model estimates attributed this pattern to either equivalent increases in memory strength across the two types of items (unequal variance signal detection model) or equivalent increases in both familiarity and recollection (dual process signal detection [DPSD] model). Hippocampal activity associated with strong targets and lures showed equivalent increases compared with missed items. This remained the case when analyses were restricted to high-confidence responses considered by the DPSD model to reflect predominantly recollection. A similar pattern of activity was observed in parahippocampal cortex for high-confidence responses. The present results are incompatible with "noncriterial" or "false" recollection being reflected solely in inflated DPSD familiarity estimates and support a positive correlation between hippocampal activity and memory strength irrespective of the accuracy of list discrimination, consistent with the unequal variance signal detection model account.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

Aging, retirement, and changes in physical activity : prospective cohort findings from the globe study

There is increased recognition that determinants of health should be investigated in a life-course perspective. Retirement is a major transition in the life course and offers opportunities for changes in physical activity that may improve health in the aging population. The authors examined the effect of retirement on changes in physical activity in the GLOBE Study, a prospective cohort study known by the Dutch acronym for "Health and Living Conditions of the Population of Eindhoven and surroundings," 1991–2004. They followed respondents (n = 971) by postal questionnaire who were employed and aged 40–65 years in 1991 for 13 years, after which they were still employed (n = 287) or had retired (n = 684). Physical activity included 1) work-related transportation, 2) sports participation, and 3) nonsports leisure-time physical activity. Multinomial logistic regression analyses indicated that retirement was associated with a significantly higher odds for a decline in physical activity from work-related transportation (odds ratio (OR) = 3.03, 95% confidence interval (CI): 1.97, 4.65), adjusted for sex, age, marital status, chronic diseases, and education, compared with remaining employed. Retirement was not associated with an increase in sports participation (OR = 1.12, 95% CI: 0.71, 1.75) or nonsports leisure-time physical activity (OR = 0.80, 95% CI: 0.54, 1.19). In conclusion, retirement introduces a reduction in physical activity from work-related transportation that is not compensated for by an increase in sports participation or an increase in nonsports leisure-time physical activity.

Exploratory spatial analysis of social and environmental factors associated with the incidence of Ross River Virus in Brisbane, Australia

We used geographic information systems and a spatial analysis approach to explore the pattern of Ross River virus (RRV) incidence in Brisbane, Australia. Climate, vegetation and socioeconomic data in 2001 were obtained from the Australian Bureau of Meteorology, the Brisbane City Council and the Australian Bureau of Statistics, respectively. Information on the RRV cases was obtained from the Queensland Department of Health. Spatial and multiple negative binomial regression models were used to identify the socioeconomic and environmental determinants of RRV transmission. The results show that RRV activity was primarily concentrated in the northeastern, northwestern, and southeastern regions in Brisbane. Multiple negative binomial regression models showed that the spatial pattern of RRV disease in Brisbane seemed to be determined by a combination of local ecologic, socioeconomic, and environmental factors.