Jonathan Cameron

Applications of conformal geometric algebra in computer vision and graphics

This paper introduces the mathematical framework of conformal geometric algebra (CGA) as a language for computer graphics and computer vision. Specifically it discusses a new method for pose and position interpolation based on CGA which firstly allows for existing interpolation methods to be cleanly extended to pose and position interpolation, but also allows for this to be extended to higher-dimension spaces and all conformal transforms (including dilations). In addition, we discuss a method of dealing with conics in CGA and the intersection and reflections of rays with such conic surfaces. Possible applications for these algorithms are also discussed.

Real-Time Estimation of Missing Markers in Human Motion Capture

This paper considers the problem of taking marker locations from optical motion capture data to identify and parameterise the underlying human skeleton structure and motion over time. It is concerned with real-time algorithms suitable for use within a visual feedback system. A common problem in motion capture is marker occlusion. Most current methods are only useful for offline processing or become ineffective when a significant portion of markers are missing for a long period of time. This paper presents a prediction algorithm, using a Kalman filter approach in combination with inferred information from neighbouring markers, to provide a continuous flow of data. The results are accurate and reliable even in cases where all markers on a limb are occluded, or one or two markers are not visible for a large sequence of frames. Pre-defined models are not required and skeleton fitting to this complete data can then be updated in real-time.

A real-time sequential algorithm for human joint localization

We present a novel approach to locating the centres of rotation (CoRs) of joints of a human skeleton from position only data. Unlike previous algorithms [Silaghi et al. 1998; Gamage and Lasenby 2002], this algorithm can be implemented in a sequential fashion and as such the computational cost of updating the centres of rotation is independent of the number of data points previously available. The method is closed form, enabling realtime implementation.

SLP: A Zero-Contact Non-Invasive Method for Pulmonary Function Testing

Structured Light Plethysmography (SLP) is a novel non-invasive method that uses structured light to perform pulmonary function testing that does not require physical contact with a patient. The technique produces an estimate of chest wall volume changes over time. A patient is observed continuously by two cameras and a known pattern of light (i.e. structured light) is projected onto the chest using an off-the-shelf projector. Corner features from the projected light pattern are extracted, tracked and brought into correspondence for both camera views over successive frames. A novel self calibration algorithm recovers the intrinsic and extrinsic camera parameters from these point correspondences. This information is used to reconstruct a surface approximation of the chest wall and several novel ideas for ‘cleaning up’ the reconstruction are used. The resulting volume and derived statistics (e.g. FVC, FEV) agree very well with data taken with a spirometer.

Towards real-time profiling of sprints using wearable pressure sensors

On-body sensor systems for sport are challenging since the sensors must be lightweight and small to avoid discomfort, and yet robust and highly accurate to withstand and capture the fast movements associated with sport. In this work, we detail our experience of building such an on-body system for track athletes. The paper describes the design, implementation and deployment of an on-body sensor system for sprint training sessions. We autonomously profile sprints to derive quantitative metrics to improve training sessions. Inexpensive Force Sensitive Resistors (FSRs) are used to capture foot events that are subsequently analysed and presented back to the coach. We show how to identify periods of sprinting from the FSR data and how to compute metrics such as ground contact time. We evaluate our system using force plates and show that millisecond-level accuracy is achievable when estimating contact times.

Predicting Missing Markers to Drive Real-Time Centre of Rotation Estimation

This paper addresses the problem of real-time location of the joints or centres of rotation (CoR) of human skeletons in the presence of missing data. The data is assumed to be 3dmarker positions from a motion capture system. We present an integrated framework which predicts the occluded marker positions using a Kalman filter in combination with inferred information from neighbouring markers and thereby maintains a continuous data-flow. The CoR positions can be calculated with high accuracy even in cases where markers are occluded for a long period of time.

Estimating Human Skeleton Parameters and Configuration in Real-Time from Markered Optical Motion Capture

This paper is concerned with real-time approaches to using marker-based optical motion capture to identify, parametrize, and estimate the frame by frame configuration of the human skeleton. An overview of the stages of a system is provided with the main emphasis devoted to two new methods for refining the rotation estimates used within the transformational algorithm class of joint parameter estimation methods. Virtual Marker Insertion uses additional markers inserted at the current estimates of joint location to partially enforce the concurrency of available joint location estimates. This simple algorithm is shown to outperform the methods presented in the literature. A conjugate gradient optimization on a minimal parameterization of the standard transformational algorithm cost function gives superior results, but at considerable computational cost, limiting its probable application to those frames which are actually rendered in a feedback system.

Profiling sprints using on-body sensors

This paper describes the design, implementation and deployment of a wireless sensor system for athletes. The system is designed to profile sprints based on input from on-body sensors that are wirelessly connected to a nearby infrastructure. We discuss the choice and use of inexpensive Force Sensitive Resistors (FSRs) to measure foot event timings and provide a detailed analysis of the profiling method used to represent high-level information to the coaches and athletes. In this profiling method, we detect sprinting intervals from high-resolution sensor data, and compute the ground contact times for sprinting performances. We validate our results using force plates and show that the system achieves comparable accuracy in measuring the foot contact times (millisecond accuracy) without the limitations of one or few steps.

The perceptual influences on gait transition of step parameters and optic flow in virtual environment locomotion simulators

Simulation of natural locomotion in virtual environments requires an understanding of self-motion perception derived from both gait and sensory parameters. The walk-run transition (WRT) is a clearly-defined physical gait descriptor that emerges largely from a users assessment of their own speed. The WRT depends not only on the biomechanics, kinetics and energetics of gait, but also on perceptual and cognitive factors, such as optic flow [Mohler et al. 2004; 2007], attention [Pelah et al 2006] and step frequency [Durgin et al 2007]. To further investigate gait transitions and the mechanisms for perception of self motion speed, 15 subjects were required to advance at prescribed step frequencies with increasing speeds on a treadmill, with or without optic flow, in a large-screen virtual environment. WRT speed reached its highest value at approximately 145 steps/min (0.61 Fr) for all conditions, decreasing at higher step frequencies. Above this frequency, optic flow reduced WRT speeds as step frequency increased, suggesting an enhancement of visuomotor interactions in locomotion simulators due to step frequency being forced beyond the natural step frequency range.

Influence of step frequency on visual speed perception during locomotion

[Thurrell et al. 1998] first observed that the perceived speed of optic flow decreases in linear proportion to the increasing physical speed of locomotion on a treadmill and proposed this as a mechanism to discount from the visual signal retinal motion due to self-motion, described as an arthrovisual effect [Thurrell and Pelah 2005]. Since human locomotion consists of a complex of articulated movement, step parameters and associated afferent, efferent and efference copy signals, questions arise as to the relative contributions of these component messages to the reduction in the perception of optic flow speed (POFS). Here we report experiments [Casey 2010] on the role of step frequency (SF) previously proposed as a reliable estimate for perception of the speed of self-motion [Durgin et al. 2007; Dong et al. 2008].