Brendan Chwyl

TIGGER: A Texture-Illumination Guided Global Energy Response Model for Illumination Robust Object Saliency

Global saliency is an important aspect of many computerand robotic vision tasks, and with the increased interest infields such as autonomous navigation, a significant area ofresearch. A challenging aspect of modelling global saliencyin practical applications is the presence of varying or non-uniform illumination conditions. Many current models fail toaccurately detect salient regions in non-uniform illuminationconditions and often produce different saliency maps for thesame image under changing illumination. In this paper, wepropose a novel model for illumination robust global saliency. For a given input image, texture-illumination guided energyresponses (TIGERs) are computed at different scales usinga novel multi-scale extension of TIGER. To acquire theseresponses, image intensity is modelled as the summationof the low frequency illumination component and the highfrequency texture component. A captured image is disassociatedinto these components via Bayesian minimization, with the required posterior probability estimated through animportance-weighted Monte Carlo sampling approach. Thetexture-illumination guided global energy response (TIGGER) is computed as the aggregate sum of TIGERs acrossall scales. The global saliency map is obtained via a k-meansclustering-based region adjacency graph (RAG) model. Experimentalresults produce global saliency maps with improvedperformance in non-uniform lighting conditions andgreater consistency when compared to other state-of-the-artmethods.

Time-Frequency Domain Analysis via Pulselets for Non-contact Heart Rate Estimation from Remotely Acquired Photoplethysmograms

A novel method for remote heart rate estimation via analysis in the time-frequency domain is proposed. A photoplethysmogram (PPG) waveform is constructed via a Bayesian minimization approach with the required posterior probability obtained through an importance-weighted Monte Carlo sampling method. A pulselet (wavelet chosen for its similarities with a finger pulse oximiter PPG waveform), is used in the continuous wavelet transform to produce a map of the wavelet energy response in the time-frequency domain. This allows the heart rate frequency to be estimated at each time step, accounting for naturally occurring changes in heart rate over time which may cause error with frequency domain based methods. The frequency corresponding to the highest wavelet response at each time step is averaged across the entire time series to estimate the average heart rate. Experimental results against a data set of 30 videos show an improvement over current state-of-the-art methods.

High dynamic range map estimation via fully connected random fields with stochastic cliques

The reconstruction of high dynamic range (HDR) images via conventional camera systems and low dynamic range (LDR) images is a growing field of research in image acquisition. The radiance map associated with the HDR image of a scene is typically computed using multiple images of the same scene captured at different exposures (i.e., bracketed LDR imzages). This approach, though inexpensive, is sensitive to noise under high camera ISO. Each bracketed image is associated with a different level of noise due to the change in exposure time, and the noise is further amplified when tone-mapping the HDR image for display. A new framework is proposed to address the associated noise in the context of random fields. The estimation of the HDR image from a set of LDR images is formulated as a stochastically fully connected conditional random field where the spatial information is incorporated to compute the HDR value in combination with the LDR image values. Experimental results show that the proposed framework compensated the non-stationary ISO noise while preserving the boundaries in the estimated HDR images.

Tiger: A texture-illumination guided energy response model for illumination robust local saliency.

Local saliency models are a cornerstone in image processing and computer vision, used in a wide variety of applications ranging from keypoint detection and feature extraction, to image matching and image representation. However, current models exhibit difficulties in achieving consistent results under varying, non-ideal illumination conditions. In this paper, a novel texture-illumination guided energy response (TIGER) model for illumination robust local saliency is proposed. In the TIGER model, local saliency is quantified by a modified Hessian energy response guided by a weighted aggregate of texture and illumination aspects from the image. A stochastic Bayesian disassociation approach via Monte Carlo sampling is employed to decompose the image into its texture and illumination aspects for the saliency computation. Experimental results demonstrate that higher correlation between local saliency maps constructed from the same scene under different illumination conditions can be achieved using the TIGER model when compared to common local saliency approach, i.e., Laplacian of Gaussian, Difference of Gaussians, and Hessian saliency models.

Specular Reflectance Suppression in Endoscopic Imagery via Stochastic Bayesian Estimation

A novel stochastic Bayesian estimation method is introduced for the purpose of suppressing specular reflectance in endoscopic imagery, benefiting both computer aided and manual analysis of endoscopic data. The maximum diffuse chromaticity, which is necessary for the calculation of the specular reflectance, is estimated via Bayesian least-squares minimization, with the posterior probability of maximum diffuse chromaticity given maximum chromaticity constructed via an adaptive Monte Carlo sampling approach. Experimental results using a set of clinical endoscopic imagery showed that the proposed method resulted in lower coefficient of variation values when compared to existing methods in homogeneous regions contaminated by strong specular highlights, which is indicative of improved specular reflectance suppression. These findings are further reinforced by visual assessment of the specular suppressed endoscopic imagery produced by the proposed method.

DeepPredict: A deep predictive intelligence platform for patient monitoring

A novel platform, DeepPredict, for predicting hospital bed exit events from video camera systems is proposed. DeepPredict processes video data with a deep convolutional neural network consisting of five main layers: a 1 × 1 3D convolutional layer used for generating feature maps from raw video data, a context-aware pooling layer used for rectifying data from different camera angles, two fully connected layers used for applying pre-trained deep features, and an output layer used to provide a likelihood of a bed exit event. Results for a model trained on 180 hours of data demonstrate accuracy, sensitivity, and specificity of 86.47%, 78.87%, and 94.07%, respectively, when predicting a bed exit event up to seven seconds in advance.

SAPPHIRE: Stochastically acquired photoplethysmogram for heart rate inference in realistic environments

A novel method, Stochastically Acquired Photoplethysmo-gram for Heart rate Inference in Realistic Environments (SAPPHIRE), is proposed for robust remote heart rate measurement through broadband video. A set of stochastically sampled points from the cheek region is tracked and used to construct corresponding time series observations via skin erythema transforms. From these observations, a photo-plethysmogram (PPG) waveform is estimated via Bayesian minimization, with the required posterior probability inferred using a Monte Carlo approach. To mitigate the effects of noise, the contribution of each observation is weighted based on the observations likelihood to contain relevant data. A bandpass filter is applied to the estimated PPG waveform to omit implausible heart rate frequencies, and the heart rate is estimated through frequency domain analysis. Experimental results acquired from a set of thirty videos indicate significantly improved performance in comparison to state-of-the-art methods.

Photoplethysmographic imaging via spectrally demultiplexed erythema fluctuation analysis for remote heart rate monitoring

Traditional photoplethysmographic imaging (PPGI) systems use the red, green, and blue (RGB) broadband measurements of a consumer digital camera to remotely estimate a patients heart rate; however, these broadband RGB signals are often corrupted by ambient noise, making the extraction of subtle fluctuations indicative of heart rate difficult. Therefore, the use of narrow-band spectral measurements can significantly improve the accuracy. We propose a novel digital spectral demultiplexing (DSD) method to infer narrow-band spectral information from acquired broadband RGB measurements in order to estimate heart rate via the computation of motion- compensated skin erythema fluctuation. Using high-resolution video recordings of human participants, multiple measurement locations are automatically identified on the cheeks of an individual, and motion-compensated broadband reflectance measurements are acquired at each measurement location over time via measurement location tracking. The motion-compensated broadband reflectance measurements are spectrally demultiplexed using a non-linear inverse model based on the spectral sensitivity of the cameras detector. A PPG signal is then computed from the demultiplexed narrow-band spectral information via skin erythema fluctuation analysis, with improved signal-to-noise ratio allowing for reliable remote heart rate measurements. To assess the effectiveness of the proposed system, a set of experiments involving human motion in a front-facing position were performed under ambient lighting conditions. Experimental results indicate that the proposed system achieves robust and accurate heart rate measurements and can provide additional information about the participant beyond the capabilities of traditional PPGI methods.

Illumination Robust Facial Feature Detection via Decoupled Illumination and Texture Features

A method for illumination robust facial feature detection on frontal images of the human face is proposed. Illumination robust features are produced from weighted contributions of the texture and illumination components of an image where the illumination is estimated via Bayesian least-squares minimization with the required posterior probability inferred using an adaptive Monte-Carlo sampling approach. This estimate is used to decouple the illumination and texture components, from which Haar-like features are extracted. A weighted aggregate of each component’s features is then compared with a cascade of pre-trained classifiers for the face, eyes, nose, and mouth. Experimental results against the Yale Face Database B suggest higher sensitivity and \(F_1\) score values than current methods while maintaining comparable specificity and accuracy in the presence of non-ideal illumination conditions.