My research interests lies in computer graphics, vision, HCI, and machine learning. My interests in computer graphics is primarily non-photorealistic rendering and image processing from image and video sources for artistic effects. My current research is on developing a user interface for creating painterly animations from video sources. I am also interested in computer vision and machine learning problems related to motion analysis including optical flow, gesture and activity recognition, rotoscoping and video segmentation.

I am a PhD student at the University of Toronto's Dynamic Graphics Project lab, working under the supervision of Aaron Hertzmann. Prior to this I worked for 2 years at the SPi Group as a software analyst team lead, where I worked in the operations group and developed interfaces to large-scale billing systems for the energy market. I completed a B.Sc Honours in Computer Science at the University of Saskatchewan where I worked with David Mould in computer graphics and did my honours thesis on optical flow and video stabilization with Mark Eramian.

Felt-Based Rendering
4th International Symposium on Non-Photorealistic Animation and Rendering (NPAR 2006), Jun. 5 - Jun. 7, 2006. Annecy, France.
Peter O'Donovan and David Mould

Felt is mankind's oldest and simplest textile, composed of a pressed mass of fibers. Images can be formed directly in the fabric by arranging the fibers to represent the image before pressure is applied, a process called "felt painting". Here, we describe an automated synthesis method that transforms input images into felt-painted images.
Paper   Animated Felt Test

Using Semantic Web Methods for Distributed Learner Modeling
2nd International Workshop on Applications of Semantic Web Technologies for E-Learning (SW-EL 04) held in conjunction with the International Semantic Web Conference (ISWC 2004), Nov. 7 - Nov. 11, 2004. Hiroshima, Japan
Mike Winter, Chris Brooks, Gord McCalla, Jim Greer, Peter O'Donovan

Here describe a semantic web approach for representing student models based on distributed student data from learning environments where the learner uses multiple applications and resources to accomplish learning tasks. We also present a proposal for revising those student models based on arbitrary, web-based learner actions.
Paper

Learning View-based Mixture of Experts for Human Action Recognition
CSC2539 (Topics in Computer Vision: Visual Motion Analysis)
Peter O'Donovan

Many methods for action recognition use a view-independent approach where actions from different views are treated identically. However, this results in models which must deal with significantly different motions from different views such as classifying a boxer from a rear view versus a side view. In this paper, I explore the use of a view-based Mixture of Experts (MoE) model where each expert is trained on data from a relative view between the camera and the subject. This allows the experts to model a particular view and results in improved classification rates. Seperate view and action classifiers were trained using both SVMs and LD-CRF models and the results compared on the HumanEVA dataset.

Static Gesture Recognition with Restricted Boltzmann Machines
CSC2515 (Introduction to Machine Learning)
Peter O'Donovan

In this paper I investigate a new technique for the recognition of static gestures (poses) from laptop camera images. I apply Restricted Boltzmann Machines (RBMs) to model the manifold of 3 human gestures: pointing, thumbs up, fingers spread, as well as the default no-gesture case. The generative RBM model performs significantly better than other classification techniques including classical discriminative neural networks, and k-Nearest Neighbors on dimensionality reduced images.
Paper  Gesture Examples

Optical Flow: Techniques and Applications
Using Optical Flow for Stabilizing Image Sequences
CMPT400 (Honours Thesis Course)
Peter O'Donovan

This thesis was partly a survey of the optical flow literature and partly a project implementing stablization of shaky video sources. Stabilization was accomplished with a simple region segmentation and classification step to determine the background of the sequence. The movement of the background was then filtered with a Kalman filter and translated to stabilize the video.
Paper   Video 1  Video 2  Video 3