Traffic state estimation is a fundamental task of Intelligent Transportation Systems. Recent advances in sensor technology and emerging computer and vehicular communications paradigms have brought the task of estimating traffic state parameters in real-time within reach.
This has led to the main research question of this thesis: Can a vehicle accurately estimate traffic parameters using onboard resources shared through CV technology in a lightweight manner without utilizing centralized or roadside infrastructure?
In 1954 Wardrop and Charlesworth proposed the Moving Observer method to measure traffic parameters based on an observed number of vehicle passes. We start by proposing methods for detecting vehicle passes using both radar and V2X as a well as with V2X only.
Next, a modernization of the Moving Observer method, called the MO1 method, using the capabilities of modern vehicles is proposed which mitigates some of the limitations of the original method. The results show our method is able to provide estimates comparable to stationary observer methods, even in low ow scenarios.
The MO2 method also utilizes two vehicles traveling in the same direction to determine a density between the two vehicles. Again, the results show this method provides estimates comparable to stationary observer methods, even in low ow scenarios.
The MO3 method is similar to the MO2 method; however, here the two vehicles travel in oncoming traffic. In doing so, the vehicles' relative velocity is large, leading us to hypothesize that the method will work well in urban traffic. The results for the MO3 method in urban traffic did not meet our expectations, which inspired us to develop the MO3-Flow method. The MO3-Flow method aggregates the counts of multiple vehicles to determine flow.
The MO3-Flow method requires additional roadside infrastructure. To remove this need, a Virtual Road Side Unit architecture is proposed. This architecture uses vehicles on the roadway to act in place of roadside infrastructure. We show this architecture provides ample service coverage if the data image is sufficiently small.
","abstract_html":"<p>Traffic state estimation is a fundamental task of Intelligent Transportation Systems. Recent advances in sensor technology and emerging computer and vehicular communications paradigms have brought the task of estimating traffic state parameters in real-time within reach.</p> <p>This has led to the main research question of this thesis: Can a vehicle accurately estimate traffic parameters using onboard resources shared through CV technology in a lightweight manner without utilizing centralized or roadside infrastructure?</p> <p>In 1954 Wardrop and Charlesworth proposed the Moving Observer method to measure traffic parameters based on an observed number of vehicle passes. We start by proposing methods for detecting vehicle passes using both radar and V2X as a well as with V2X only.</p> <p>Next, a modernization of the Moving Observer method, called the MO1 method, using the capabilities of modern vehicles is proposed which mitigates some of the limitations of the original method. The results show our method is able to provide estimates comparable to stationary observer methods, even in low ow scenarios.</p> <p>The MO2 method also utilizes two vehicles traveling in the same direction to determine a density between the two vehicles. Again, the results show this method provides estimates comparable to stationary observer methods, even in low ow scenarios.</p> <p>The MO3 method is similar to the MO2 method; however, here the two vehicles travel in oncoming traffic. In doing so, the vehicles' relative velocity is large, leading us to hypothesize that the method will work well in urban traffic. The results for the MO3 method in urban traffic did not meet our expectations, which inspired us to develop the MO3-Flow method. The MO3-Flow method aggregates the counts of multiple vehicles to determine flow.</p> <p>The MO3-Flow method requires additional roadside infrastructure. To remove this need, a Virtual Road Side Unit architecture is proposed. This architecture uses vehicles on the roadway to act in place of roadside infrastructure. We show this architecture provides ample service coverage if the data image is sufficiently small.</p>","abstract_has_math":false,"creators":["Florin, Ryan"],"institution":null,"degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Stephan Olariu","Michele C. Weigle","Ravi Mukkamala","Dimitrie Popescu"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-07-01T07:00:00Z","date_published":"2021-07-01T07:00:00Z","updated_at":"2026-07-24T03:35:38Z","subjects":["Automotive Engineering","Computer Sciences","Transportation"],"languages":[],"rights":["In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["9798460432868"],"render_values":[{"text":"9798460432868","href":null,"code":true}]}]},"links":{"outbound_url":"https://digitalcommons.odu.edu/computerscience_etds/130","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Stephan Olariu","Michele C. Weigle","Ravi Mukkamala","Dimitrie Popescu"]},{"key":"dc:creator","label":"Author","values":["Florin, Ryan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2021-09-15T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Automotive Engineering","Computer Sciences","Transportation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["9798460432868","https://digitalcommons.odu.edu/computerscience_etds/130"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Traffic state estimation is a fundamental task of Intelligent Transportation Systems. Recent advances in sensor technology and emerging computer and vehicular communications paradigms have brought the task of estimating traffic state parameters in real-time within reach.
This has led to the main research question of this thesis: Can a vehicle accurately estimate traffic parameters using onboard resources shared through CV technology in a lightweight manner without utilizing centralized or roadside infrastructure?
In 1954 Wardrop and Charlesworth proposed the Moving Observer method to measure traffic parameters based on an observed number of vehicle passes. We start by proposing methods for detecting vehicle passes using both radar and V2X as a well as with V2X only.
Next, a modernization of the Moving Observer method, called the MO1 method, using the capabilities of modern vehicles is proposed which mitigates some of the limitations of the original method. The results show our method is able to provide estimates comparable to stationary observer methods, even in low ow scenarios.
The MO2 method also utilizes two vehicles traveling in the same direction to determine a density between the two vehicles. Again, the results show this method provides estimates comparable to stationary observer methods, even in low ow scenarios.
The MO3 method is similar to the MO2 method; however, here the two vehicles travel in oncoming traffic. In doing so, the vehicles' relative velocity is large, leading us to hypothesize that the method will work well in urban traffic. The results for the MO3 method in urban traffic did not meet our expectations, which inspired us to develop the MO3-Flow method. The MO3-Flow method aggregates the counts of multiple vehicles to determine flow.
The MO3-Flow method requires additional roadside infrastructure. To remove this need, a Virtual Road Side Unit architecture is proposed. This architecture uses vehicles on the roadway to act in place of roadside infrastructure. We show this architecture provides ample service coverage if the data image is sufficiently small.
"]},{"key":"dc:title","label":"Title","values":["MOVE: Mobile Observers Variants and Extensions"]}]}],"canonical_facts":{"dc:contributor":["Stephan Olariu","Michele C. Weigle","Ravi Mukkamala","Dimitrie Popescu"],"dc:creator":["Florin, Ryan"],"dc:date.available":["2021-09-15T07:00:00Z"],"dc:description.abstract":["Traffic state estimation is a fundamental task of Intelligent Transportation Systems. Recent advances in sensor technology and emerging computer and vehicular communications paradigms have brought the task of estimating traffic state parameters in real-time within reach.
This has led to the main research question of this thesis: Can a vehicle accurately estimate traffic parameters using onboard resources shared through CV technology in a lightweight manner without utilizing centralized or roadside infrastructure?
In 1954 Wardrop and Charlesworth proposed the Moving Observer method to measure traffic parameters based on an observed number of vehicle passes. We start by proposing methods for detecting vehicle passes using both radar and V2X as a well as with V2X only.
Next, a modernization of the Moving Observer method, called the MO1 method, using the capabilities of modern vehicles is proposed which mitigates some of the limitations of the original method. The results show our method is able to provide estimates comparable to stationary observer methods, even in low ow scenarios.
The MO2 method also utilizes two vehicles traveling in the same direction to determine a density between the two vehicles. Again, the results show this method provides estimates comparable to stationary observer methods, even in low ow scenarios.
The MO3 method is similar to the MO2 method; however, here the two vehicles travel in oncoming traffic. In doing so, the vehicles' relative velocity is large, leading us to hypothesize that the method will work well in urban traffic. The results for the MO3 method in urban traffic did not meet our expectations, which inspired us to develop the MO3-Flow method. The MO3-Flow method aggregates the counts of multiple vehicles to determine flow.
The MO3-Flow method requires additional roadside infrastructure. To remove this need, a Virtual Road Side Unit architecture is proposed. This architecture uses vehicles on the roadway to act in place of roadside infrastructure. We show this architecture provides ample service coverage if the data image is sufficiently small.
"],"dc:identifier":["9798460432868","https://digitalcommons.odu.edu/computerscience_etds/130"],"dc:rights":["In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
"],"dc:subject":["Automotive Engineering","Computer Sciences","Transportation"],"dc:title":["MOVE: Mobile Observers Variants and Extensions"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-24T03:35:38Z"}