A Computer Vision-Based Approach to Vehicle Detection and Classification for CO₂ Emission Estimation

Proponent/s Name/s (Last Name, First Name, Middle Initial)

• Andariel Rashamon Rayne Cruz Lim, De La Salle University, ManilaFollow
• Mayan Denise Francisco Hilario, De La Salle University, ManilaFollow
• Kiersten Sarte Jimenez, De La Salle University, ManilaFollow
• Gabrielle Sarmiento Santos, De La Salle University, ManilaFollow
• Renann G. Baldovino, De La Salle University, ManilaFollow
• Immanuel Jose C. Valencia, De La Salle University, ManilaFollow

Document Types

Paper Presentation

Research Theme (for Paper Presentation and Poster Presentation submissions only)

Computer and Software Technology, and Robotics (CSR)

School Name

De La Salle University Manila

Track or Strand

Science, Technology, Engineering, and Mathematics (STEM)

Research Advisor (Last Name, First Name, Middle Initial)

Baldovino, Renann G.

Start Date

25-6-2026 10:30 AM

End Date

25-6-2026 12:00 PM

Zoom Link/ Room Assignment

Online- https://zoom.us/j/94569671692?pwd=Fj3c3ELOebE6QbqbJOOH9wMuildoEc.1 Meeting ID: 945 6967 1692 | Passcode: research

Abstract/Executive Summary

Vehicle diversity in Philippine urban transport heavily contributes to congestion and air pollution, necessitating localized monitoring tools to assess vehicle ubiquity and emission impacts. This study introduces an integrated, data-driven method for estimating carbon dioxide (CO₂) emissions tailored to vehicles found in the Philippines. The developed framework combines a Computer Vision (CV) system with a custom Python-based Carbon Emission Calculator (CEC). The CV component utilizes the You Only Look Once (YOLO) framework to detect, classify, and generate activity data for specific Philippine vehicle categories from the video footage. The CEC then integrates these activity datasets with local, context-specific emission factors (Ef) to automate quantitative emission assessments. Validation results demonstrate that the most efficient YOLO model (YOLOv26-M) achieves a vehicle classification accuracy of 98.0%, and the integrated CEC converts detected vehicle counts into class-based carbon emission estimates using assigned emission values. This integrated method enables automated, quantitative assessment of traffic composition and its corresponding CO₂ emissions, offering a scalable tool for urban transport planning.

Keywords

Computer Vision, Carbon Dioxide Estimation, YOLO, Carbon Emissions, Graphical User Interface (GUI)

Initial Consent for Publication

yes

Statement of Originality

yes