<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T06:42:00Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/26254" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/26254</identifier><datestamp>2026-09-24T03:38:57Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Kirubarajan, Thia</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">akbari, behzad</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2021-03-15T20:19:20Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2021-03-15T20:19:20Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2021</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/26254</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/14967</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Detection of multiple-lane markings (lane-line) on road surfaces is an essential aspect&#xd;
of autonomous vehicles. Although several approaches have been proposed to detect&#xd;
lanes, detecting multiple lane-lines consistently, particularly across a stream of frames&#xd;
and under varying lighting conditions is still a challenging problem. Since the road's&#xd;
markings are designed to be smooth and parallel, lane-line sampled features tend&#xd;
to be spatially and temporally correlated inside and between frames. In this thesis,&#xd;
we develop novel methods to model these spatial and temporal dependencies in the&#xd;
form of the target tracking problem. In fact, instead of resorting to the conventional&#xd;
method of processing each frame to detect lanes only in the space domain, we treat&#xd;
the overall problem as a Multiple Extended Target Tracking (METT) problem.&#xd;
In the first step, we modelled lane-lines as multiple "independent" extended targets&#xd;
and developed a spline mathematical model for the shape of the targets. We showed&#xd;
that expanding the estimations across the time domain could improve the result of&#xd;
estimation. We identify a set of control points for each spline, which will track over&#xd;
time. To overcome the clutter problem, we developed an integrated probabilistic data&#xd;
association fi lter (IPDAF) as our basis, and formulated a METT algorithm to track&#xd;
multiple splines corresponding to each lane-line.In the second part of our work, we investigated the coupling between multiple extended targets. We considered the non-parametric case and modeled target dependency&#xd;
using the Multi-Output Gaussian Process. We showed that considering&#xd;
dependency between extended targets could improve shape estimation results. We&#xd;
exploit the dependency between extended targets by proposing a novel recursive approach&#xd;
called the Multi-Output Spatio-Temporal Gaussian Process Kalman Filter&#xd;
(MO-STGP-KF). We used MO-STGP-KF to estimate and track multiple dependent&#xd;
lane markings that are possibly degraded or obscured by traffic. Our method tested&#xd;
for tracking multiple lane-lines but can be employed to track multiple dependent&#xd;
rigid-shape targets by using the measurement model in the radial space&#xd;
In the third section, we developed a Spatio-Temporal Joint Probabilistic Data&#xd;
Association Filter (ST-JPDAF). In multiple extended target tracking problems with&#xd;
clutter, sometimes extended targets share measurements: for example, in lane-line&#xd;
detection, when two-lane markings pass or merge together. In single-point target&#xd;
tracking, this problem can be solved using the famous Joint Probabilistic Data Association&#xd;
(JPDA)  filter. In the single-point case, even when measurements are dependent,&#xd;
we can stack them in the coupled form of JPDA. In this last chapter, we expanded&#xd;
JPDA for tracking multiple dependent extended targets using an approach called&#xd;
ST-JPDAF. We managed dependency of measurements in space (inside a frame) and&#xd;
time (between frames) using different kernel functions, which can be learned using&#xd;
the trained data. This extension can be used to track the shape and dynamic of&#xd;
dependent extended targets within clutter when targets share measurements.&#xd;
The performance of the proposed methods in all three chapters are quanti ed on&#xd;
real data scenarios and their results are compared against well-known model-based,&#xd;
semi-supervised, and fully-supervised methods. The proposed methods offer very promising results.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Doctor of Philosophy (PhD)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Lane detection</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">lane tracking</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Multi target tracking</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Probability data association</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Joint probability data association coupled filter</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Multi output Gaussian process</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Dependent multiple target tracking</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Kernel based JPDACF</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">LANE TRACKING USING DEPENDENT EXTENDED TARGET MODELS</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>