Congratulations to Philip Kelly

Congratulations to Philip Kelly who successfully defended his thesis and will be awarded the degree of PhD.

The title of Philip's thesis is "Pedestrian Detection and Tracking using Stereo Vision Techniques".

He completed his PhD in the Centre for Digital Video Processing (CDVP), Adaptive Information Cluster (AIC) and the School of Electronic Engineering, DCU under the supervision of Dr. Noel E. O’Connor.

Philip is currently working as a post-doctoral researcher with the CDVP.

Brief description of Project:
Accurate detection and tracking of pedestrians are two essential components required by a variety of applications that include, amongst others, Ambient Intelligence, automated surveillance, image compression and content-based multimedia storage and retrieval. Given this large number of potential applications, pedestrian detection and tracking has become an extremely active research area in computer vision. This has resulted in a significant amount of prior art proposing pedestrian segmentation techniques using a myriad of approaches. Many of the person detection techniques described so far in the literature work well in controlled environments, such as laboratory settings with a small number of people. This allows various assumptions to be made that simplify this complex problem. The performance of these techniques, however, tends to deteriorate when presented with unconstrained environments where pedestrian appearances, numbers, orientations, movements, occlusions and lighting conditions violate these convenient assumptions. Recently, 3D stereo information has been proposed as a technique to overcome some of these issues and to guide pedestrian detection.

This thesis presents such an approach, whereby after obtaining robust 3D information via a novel disparity estimation technique, pedestrian detection is performed via a 3D point clustering process within a region-growing framework. This clustering process avoids using hard thresholds by using bio-metrically inspired constraints and a number of plan view statistics. This pedestrian detection technique requires no external training and is able to robustly handle challenging real-world unconstrained environments from various camera positions and orientations. In addition, this thesis presents a continuous detect-and-track approach, with additional kinematic constraints and explicit occlusion analysis, to obtain robust temporal tracking of pedestrians over time.

This project was generously funded by Science Foundation Ireland (SFI).