2026-09-19T06:48:48Zhttps://ecommons.cornell.edu/server/oai/requestoai:ecommons.cornell.edu:1813/1206322026-05-15T17:53:36Zcom_1813_35col_1813_47
Huang, Hongpufan
Zhang, Ke
Li, Qi
2026-04-02T18:33:19Z
2026-04-02T18:33:19Z
2025-08
ProQuest Submission ID: 12576
ProQuest Publication ID: 32171161
https://hdl.handle.net/1813/120632
https://doi.org/10.7298/f8gz-c457
17422686
52 pages
Estimating the distribution of wood stove appliances is essential for fine-scale air quality management but remains limited by the coarse spatial resolution of survey-based inventories such as the U.S. National Emissions Inventory (NEI). To address this limitation, we proposed a novel computer vision framework that leverages visible chimney features as proxies for wood stove usage. Using data from drones, vehicle-based videos across urban and rural areas, we trained object detection models (YOLOv11) and integrated them with Vision Language Models (VLMs) for semantic verification. This two-stage pipeline substantially improves detection accuracy over YOLO alone. In the urban Fall Creek neighborhood, the YOLO+VLMs approach achieved an F1-score of 61.4%, compared to 29.3% using YOLO alone. In rural video data, the framework reached 74.5%, up from 17.5%. These results demonstrate the viability of context-informed, multimodal models in identifying distributed emission sources. The proposed method is scalable and adaptable, offering a promising tool for real-time residential wood combustion mapping and environmental policy development.
en
AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition
dissertation or thesis
application/pdf
Mechanical Engineering
Cornell University
Master of Science
M.S., Mechanical Engineering
https://hdl.handle.net/1813/59810.2
Publication
Cornell Theses and Dissertations
Huang, Hongpufan
5893a6ea-7af3-41d7-abc6-04bcd26ab5df
open.access
open.access
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="04b927fa-123e-4a27-b69b-fd70de47f1ec">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>en</Language>
<Title>AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-08</PublicationDate>
<DOI>https://doi.org/10.7298/f8gz-c457</DOI>
<Authors>
<Author>
<DisplayName>Huang, Hongpufan</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<OrgUnit />
</Publisher>
</Publishers>
<Abstract>Estimating the distribution of wood stove appliances is essential for fine-scale air quality management but remains limited by the coarse spatial resolution of survey-based inventories such as the U.S. National Emissions Inventory (NEI). To address this limitation, we proposed a novel computer vision framework that leverages visible chimney features as proxies for wood stove usage. Using data from drones, vehicle-based videos across urban and rural areas, we trained object detection models (YOLOv11) and integrated them with Vision Language Models (VLMs) for semantic verification. This two-stage pipeline substantially improves detection accuracy over YOLO alone. In the urban Fall Creek neighborhood, the YOLO+VLMs approach achieved an F1-score of 61.4%, compared to 29.3% using YOLO alone. In rural video data, the framework reached 74.5%, up from 17.5%. These results demonstrate the viability of context-informed, multimodal models in identifying distributed emission sources. The proposed method is scalable and adaptable, offering a promising tool for real-time residential wood combustion mapping and environmental policy development.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>