The objective of the proposed research project is to develop a realistic color appearance model based on the human visual system’s functioning that addresses the issue of noise under low luminance levels. This will be incorporated into algorithms used in the color reproduction and retargeting algorithms of OLED displays. This model should give rise to reduced power consumption in OLED displays, while maintaining a high perceived quality of images. The project will also explore the effect of changing the white point to manage the circadian rhythm on OLED screens.

Automated human body pose estimation and activity recognition in videos is still one of the challenging problems in computer vision. Generally, it is becomes a significantly difficult task in real world applications due to camera motion, cluttered background, occlusion, and scale/viewpoint/perspective variations. Moreover, the same action performed by two persons can appear to be very different. In addition, clothing, illumination and background changes can increase this dissimilarity.

With over 100,000 mobile health applications currently available and the volume of data collected using them, developing novel automated approaches to learn from biophysical large-scale data is critical. Wearables have become affordable; mobile devices are display-rich and the flow of information from sensors to mobile devices is sufficiently accessible for enthusiasts. A key question here is how ubiquitous wearable sensing can be used to improve user health monitoring.

he goal of this project is to achieve high quality real-time motion deblurring for images captured by cameras mounted on mobile devices. First, we will propose a novel two-camera technique that exploits the trade-off between spatial and temporal resolutions in capturing the photo with the camera movement information to be used in the deblurring process. Second, we will introduce new point-spread function (PSF) estimation algorithms by employing the motion information captured by the two-camera imaging device. Third, we will develop new deconvolution algorithms suitable for mobile devices.

he goal of this project is to achieve high quality real-time motion deblurring for images captured by cameras mounted on mobile devices. First, we will propose a novel two-camera technique that exploits the trade-off between spatial and temporal resolutions in capturing the photo with the camera movement information to be used in the deblurring process. Second, we will introduce new point-spread function (PSF) estimation algorithms by employing the motion information captured by the two-camera imaging device. Third, we will develop new deconvolution algorithms suitable for mobile devices.

This study proposes to evaluate the quality of movement in patients with low back pain using a novel device. We are going to measure and compare the movement of people with back pain to that of healthy people. In addition, we plan on correlating the psychological factors associated with low back pain to tissue pathology. Many previous studies have used self-report measures of movement, and now we will determine whether our method of measuring movement correlates with these self-reports.

This project uses machine learning algorithms to better understand back movement and low back pain. We apply supervised learning time series algorithms to data collected from Backtracks’ wearable de-vice — which consists of a malleable think curve that reads data collected from the participants’ spine movements. At each time step, such movements are represented as a curve; the dynamic evolution of this curve in time represents an individual’s spinal movements.

This project uses machine learning algorithms to better understand back movement and low back pain. We apply supervised learning time series algorithms to data collected from Backtracks’ wearable de-vice — which consists of a malleable think curve that reads data collected from the participants’ spine movements. At each time step, such movements are represented as a curve; the dynamic evolution of this curve in time represents an individual’s spinal movements.

The project is about removing noise from video signals (for example, those taken by a mobile phones or professional cinema camera). Our current software first detects the type and power of the noise and based on that remove the noise from video. This proposal has three objectives. The first is to handle a specific type of noise called structured noise, not handled yet in our denoising software developed in previous MITACS projects.