Multi-Spectral Imaging and Data Fusion for Real-Time Bleeding Detection
Authors:
- 11 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4561-4568
Abstract
In this paper, we introduce a multi-spectral computer vision system that integrates long-wave infrared (thermal) and near-infrared (depth) imaging for real-time bleeding detection. Our methodology leverages deep learning techniques for robust object detection within each imaging modality. Detecting liquids in vision-based systems is particularly challenging due to their irregular shapes and varying intensity patterns. We address these challenges through extensive experimentation. A key aspect of our approach is the development of an optimized annotation strategy that accounts for the thermal properties of liquid patches, improving model training and reducing false positives. Additionally, we analyze how the nature of the surface beneath the liquid, whether soft or solid, influences detection accuracy. To enhance detection consistency, we introduce a mechanism for aligning and matching detected regions across both imaging modalities, which is crucial for distinguishing blood from other warm liquids. Our findings indicate that reducing the number of bounding boxes, by enclosing entire liquid patches rather than segmenting individual droplets, improves detection reliability. Furthermore, we establish an integrated decisionmaking framework that supports data fusion among detected regions of interest across multiple modalities. In a specific use case, this framework is designed to activate an alarm in the event of bleeding. Rigorous experimental validation demonstrates the effectiveness of the proposed system in accurately detecting blood and differentiating it from other liquid spills across various practical applications.Keywords
This publication has 9 references indexed in Scilit:
- Warm Liquid Spill Detection and Tracking Using Thermal Imaging2022
- Diffuse reflectance infrared Fourier transform spectroscopy (DRIFTS) detection limits for blood on fabric: Orientation and coating uniformity effectsScience & Justice, 2021
- RIFT: Multi-Modal Image Matching Based on Radiation-Variation Insensitive Feature TransformIEEE Transactions on Image Processing, 2019
- You Only Look Once: Unified, Real-Time Object Detection2016
- Detection Limits for Blood on Four Fabric Types Using Infrared Diffuse Reflection Spectroscopy in Mid- and Near-Infrared Spectral WindowsAnalytical Chemistry, 2015
- SURF: Speeded Up Robust Features2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- "GrabCut"ACM Transactions on Graphics, 2004
- Contrast in complex imagesJournal of the Optical Society of America A, 1990