Image: Research suggests low-cost thermal cameras attached to mobile phones can track breathing patterns (Photo courtesy of Youngjun Cho / UCL).
Novel algorithms could allow portable, low-cost thermal cameras connected to mobile devices to detect breathing problems and monitor stress.
Researchers at University College London (UCL; United Kingdom) have developed a novel approach for respiration tracking which observes the human nostril, using local temperature variations to infer inhalation and exhalation cycles. Three methods are involved; an adaptive technique that quantifies and constructs a color mapping of absolute temperature that improves segmentation, classification and tracking; a thermal gradient flow method that computes thermal gradient magnitude maps to enhance the accuracy of the nostril region tracking; and a thermal voxel method that increases the reliability of the captured respiration signals, compared to the traditional averaging method.
The researchers demonstrated the robustness of the system to track the nostril-region and measure the respiratory rate by evaluating it during controlled respiration exercises in high thermal dynamic scenes, and also showed how the algorithm outperformed standard photoplethysmography (PPG) algorithms in settings with different amounts of environmental thermal changes and human motion. The new system also compensates for the negative effects of variations in the ambient temperature and motion artifacts. The study was published on September 13, 2017, In Biomedical Optics Express.
“As thermal cameras continue to get smaller and less expensive, we expect that phones, computers and augmented reality devices will one day incorporate thermal cameras that can be used for various applications,” said senior author Nadia Bianchi-Berthouze, PhD. “By using low-cost thermal cameras, our work is a first step toward bringing thermal imaging into people's everyday lives. This approach can be used in places other sensors might not work or would cause concern.”
“Thermal cameras can detect breathing at night and during the day without requiring the person to wear any type of sensor. Compared to a traditional video camera, a thermal camera is more private because it is more difficult to identify the person,” said lead author PhD candidate Youngjun Cho. “We wanted to use the new portable systems to do the same thing by creating a smartphone based respiratory tracking method that could be used in almost any environment or activity.”
Respiration rate is a critical vital sign that provides early identification of respiratory compromise and patient distress, and is especially important for post-surgical patients receiving patient-controlled analgesia (PCA) for pain management, as the sedation can induce respiratory depression and place patients at considerable risk of serious injury or even death.
University College London