-
Mehrnaz Fani
My research interests are mainly in AI and machine learning, particularly deep learning and computer vision. I am especially interested in working with video and image data and designing novel solutions to address the real-world problems.
-
Xiaodan (Charlotte) Hu
My research interests include image processing and computer vision. My current research primarily focuses on content-adaptive projector resolution enhancement. Other projects include GANs-based text-to-image generation, medical imaging synthesis, super-resolution, semantic segmentation, and face recognition.
-
Mohamed Naiel
I’m a Postdoctoral Fellow at the Systems Design Engineering Department, University of Waterloo, and Vision and Image Processing Lab, Waterloo, Canada. I did part of my research in human action recognition in videos, object detection and multi-object tracking. My research interests include signal, image and video processing, computer vision, machine learning and pattern recognition.
-
Audrey Chung
My research interests include image processing and computer vision, with specific emphasis on biomedical imaging. My current research primarily focuses on computer-aided prostate cancer detection and grading via multi-parametric MRI. Other projects include lung nodule segmentation, video photoplethysmography, and illumination-robust feature detection.
-
Francis Li
My research interests are in 3D computer vision, image processing, and object recognition. I’m currently working on 3D reconstruction using low-cost hardware.
-
Brendan Chwyl
My research interests include topics in image processing and computer vision. I am primarily interested in photopletyhsmography imaging and its application to the analysis of remote heart rate, respiratory rate, and cognitive stress. In addition, I am interested in affect recognition and illumination robust keypoint detection.
-
VIP-HARPET Dataset
The VIP-HARPET dataset is a dataset of hockey action recognition and pose estimation in temporal space (HARPET) which consists of sequences of 3 images. Each sequence is pose annotated with respective classes labeled.
-
VIP-HARPE Dataset
The VIP-HARPE is a custom dataset of static images for hockey action recognition and pose estimation (HARPE). The dataset consists of images of hand annotated images of 18 joints locations which include, head, thorax, hips, elbows, stick, etc., and grouped into classes such as skating, firm-feet, shooting and passing.
-
VIP-Sal Dataset
The VIP-Sal is a custom dataset of objects against a non-uniform background, under 3 drastic lighting conditions. Ground truth was obtained through manual segmentation.
-
VIP-LowLight Dataset
The VIP-LowLight dataset is a set of natural images captured in very low-light conditions. The dynamic range of the images were scaled to show the image content and the corresponding amplification of the ISO noise.