This week’s SD Times open-source project of the week is an IBM hackathon winning project that uses visual recognition to detect and count SOS icons on the ground from drone streams overhead to help first responders plot rescue actions. 

DroneAid was developed by developer Pedro Cruz after he witnessed Hurricane Maria in Puerto Rico and saw how people in rural areas desperately wrote signs seeking food and water so that planes and helicopters could see their messages. 

“I thought that drones could be the perfect solution for rapidly assessing damages from the air and they could help with capturing images that could then be processed by AI computer vision systems,” Cruz wrote in a blog post that described the steps that were necessary to complete the project.  

After finding that optical character recognition (OCR) technologies would be limited by people’s different handwriting, Cruz realized the best course of action was to use visual recognition to detect SOS icons that have been standardized by the United Nations. 

IBM is committed to applying the solution in its Code and Response initiative, which is a $25 million program that hopes to advance “the creation and deployment of solutions powered by open source technology to tackle the world’s biggest challenges.” The company will also use its cloud annotation tools to make it easy to train AI using IBM Cloud object storage, which analyzes the drones’ recorded video frames to analyze whether one of the images exist. 

“Our team decided to open source DroneAid because I feel it’s important to make this technology available to as many people as possible. The standardized icon approach can be used around the world in many natural disaster scenarios (i.e., hurricanes, tsunamis, earthquakes, and wildfires) and having developers contribute by training the software on an ongoing basis can help increase our efficiency and expand how the symbols can be used together,” Cruz wrote. 

IBM also sponsors other disaster relief projects such as last year’s Call for Code winner Project OWL, a hardware and software solution that simplifies disaster management using AI and blockchain technology.