Adelaide, South Australia and Iraq have taken trials on autonomous drone cameras, which detect signs of life in disaster zones, a step further.
As reported, engineers from the University of South Australia (UniSA) and Middle Technical University (MTU) in Baghdad have designed a computer vision system, which can distinguish survivors from deceased bodies from 4-8 metres away, by using a new technique to monitor vital signs remotely.
As long as the upper torso of a human body is visible, the cameras can pick up the tiny movements in the chest cavity, which indicates a heartbeat and breathing rate.
Unlike previous studies, the system does not rely on skin colour changes or body temperature.
The researchers explained that the breakthrough is a more accurate means of detecting signs of life.
Background of the initiative
The study leaders, UniSA Professor Javaan Chahl and Dr Ali Al-Naji, made global headlines in 2017 when they showed for the first time that a camera on a drone could measure heart and respiratory rates.
Back then, their technique was based on detecting changes in human skin tone and the camera needed to be within three metres of the person.
The technique was also limited to one pose where the subject stood in front of the drone, not lying as it would be in a disaster zone.
Other techniques using thermal cameras can only detect signs of life where there is a contrast between body temperature and the background, making this difficult in warm environments.
Thermal cameras are also unreliable where people are wearing insulated clothing.
This study, based on cardiopulmonary motion, is the first of its type.
It was performed using eight people, four of each gender, and a mannequin, all lying on the ground in different poses.
Videos were taken of the subjects in daylight, up to eight metres away, and in relatively low wind conditions for one minute at a time.
The cameras were able to successfully distinguish between the live bodies and the mannequin.
The technology can be used to monitor for signs of life where time is critical. It may help first responders in the search to find survivors in disaster zones.
This system would be ideal for many situations that include the following:
- Earthquakes and floods
- Nuclear disasters such as Fukushima
- Chemical explosions
- Bio attacks
- Mass shootings
- Combat search and rescue or where a plane has crashed in a remote area
Current ground-based operations for rescuing survivors in disaster zones include using rescue robots and rescue dogs, which are expensive and hampered by restricted access.
Additional testing in adverse weather conditions is still needed for the motion-based system to ensure accurate readings when bodies are partially hidden.