AI model enhances microgravity combustion flame diameter measurement

Researchers have developed a new AI-driven method for accurately measuring the diameter of droplet flames in microgravity combustion images. This approach integrates the Segment Anything Model 2 (SAM2) with automatic prompt selection and RANSAC-based circle fitting to overcome challenges like soot tails and blurred boundaries that affect manual measurements. The system demonstrated a high degree of agreement with manual measurements, achieving 96.9% relative agreement and a 3.1% mean absolute percentage error, while also offering a significant efficiency improvement over manual methods. AI

IMPACT Enables more precise and efficient quantitative analysis in combustion research, potentially accelerating diagnostics.

RANK_REASON Academic paper detailing a new methodology and its validation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• decane
• Hough circle detection
• n-heptane
• octane
• RANSAC
• Segment Anything Model 2

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →