Healthcare Innovation

Remote Sensing for Healthcare

Non-contact, non-invasive, real-time monitoring of human vitals using a consumer grade camera.

There is a worldwide demand for ubiquitous and low-cost healthcare. 2016 saw a record funding of $8B for digital health/telemedicine. There has been lot of research going on in remote diagnosis and treatment of patients. To track multiple vitals, different sensors are required to be put on the human body, which not only increases the cost of equipment, but also requires skilled workers to analyze these parameters remotely. A cost-saving medical technology plays an important role in reducing healthcare costs.

Our Approach

Our solution is a simple and frugal innovation where we use consumer-grade cameras such as those found on laptops and mobile phones to sense multiple vitals remotely. Thus, one sensor can do the work of multiple sensors, leading to reduced costs, without compromising the efficiency of tracking multiple vitals. In addition, our solution is completely non-contact and non-invasive.

Business Engagements

15 patent families sold to CocoonCam, a US-based baby wellness monitor.
Solution shortlisted by UNICEF for pneumonia diagnosis and monitoring.

Technical Accomplishments

"System and method for extracting a periodic signal from video," Patent Filed.
"Determining when a subject is speaking by analyzing a respiratory signal obtained from a video," Patent Filed.
"Determining respiration rate from a video of subject breathing," Patent Filed.

Scientific Impact

"Estimation of respiratory pattern from video using selective ensemble aggregation," to be published in a forthcoming issue of the IEEE Transactions on Signal Processing.
"Real-time respiration rate measurement from thoracoabdominal movement with a consumer grade camera," published in the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016.
"Respiration monitoring through thoraco-abdominal video with an LSTM," published in the IEEE 16th International Conference on BioInformatics and BioEngineering (BIBE), 2016.