By DRONELIFE Features Editor Jim Magill
Landmines, which kill or injure as many as 100,000 people in nations internationally yearly, represent a worldwide health crisis.
Experts on the organization behind the international Minesweepers estimate that currently there are 110 million land mines in the bottom in about 60 countries. Locating and removing mines by traditional methods involving humans equipped with metal detectors and an enormous dose of courage, is dangerous, expensive and highly inefficient.
A start-up drone and artificial intelligence (AI) company, using off-the-shelf drones and machine learning algorithms is striving to rise to the challenge of introducing a technology-based solution to the worldwide landmine crisis.
“We’re desirous to share the work that we’re doing and the outcomes of what we’re doing and make a big impact on the planet,” Dan Erdberg, CEO of Secure Pro Group, said in an interview. Secure Pro’s subsidiary, Secure Pro AI, is currently conducting a drone-enabled demining pilot program in war-torn Ukraine.
Using off-the-shelf small aerial vehicles and its propriety technology, SpotlightAi, initial results have proven to be promising, locating 60 or more mines in considered one of its initial field tests within the Ukrainian countryside, said Jasper Baur, Secure Pro AI’s co-founder and lead scientist.
SpotlightAi harnesses machine-learning models to process massive amounts of sub-centimeter-level captured by commercially available drones. Powered by the Amazon Web Services cloud, the platform is capable of fast processes drone-collected images, using “an intensive proprietary dataset of tons of of 1000’s of labeled images of over 150 various forms of landmines and unexploded ordnance,” based on a recent company press release.
The forms of UXO that may be identified by the system range from small, anti-personnel devices often known as butterfly mines – devices that when trigged can fly upwards and explode, killing or maiming any unlucky farmer or child who happens to return into contact with them – to American-supplied unexploded cluster munitions.
The SpotlightAi technology immediately detects, labels and assigns a GPS tag to any surface mines and other explosive remnants of war and generates detailed reports that provide actionable intelligence to the suitable government entities and non-governmental organizations engaged in demining operations.
Secure Pro officials made a presentation on the event of on SpotlightAi at a recent meeting of the Geneva International Centre for Humanitarian Demining. The celebrated group acknowledged that the technology represented a breakthrough in the harmful and import business of detecting landmines, Baur said.
“At once, nobody’s using any sort of AI for analyzing their drone imagery,” he said. “The good thing about SpotlightAi is that it provides the evaluation almost immediately,”
So as to develop the machine-learning model, Secure Pro AI’s team labeled greater than 100,000 different items and made images showing the items from different viewpoints to show the software the best way to distinguish a landmine or other piece of unexploded ordinance from other objects present in real-world environments. “It creates this general idea of what a grenade is, what a rock is, what an anti-tank mine is,” Baur said. With these models in its electronic mind, the software uploads imagery captured with a drone, applies that learned information to discover all potential hazards on a map.
The system is built to be used with any business off-the-shelf aerial vehicles. The SpotlightAi team has employed the system with drones from a wide range of providers, including DJI and Parrot. One among the chief advantages of the Highlight Ai system is that it’s compatible with essentially any drone equipped with a visible-light camera with 12-megapixal or greater resolution, Erdberg said.
Ukraine
In war-torn Ukraine, Secure Pro teams have been working for the past several months with the nation’s Ministry of Defense and The HALO Trust, a non-governmental organization dedicated to international demining efforts, to prove the efficacy of the SpotlightAi system. The scope of the issue in that country is large. Experts estimate that enormous sections of the country, equal in area to the state of Florida, are seeded with hidden unexploded ordinance, prone to pose a deadly danger for a very long time, even after the hostilities eventually end.
Experts estimate that it could take as much as 800 years to completely clear the country of unexploded ordinance using traditional methods.
“The World Bank has allocated over a billion and a half dollars for demining in Ukraine,” Erdberg said. “There’s lots of activity without delay going into how will we tackle this problem efficiently and effectively. They usually’re latest technologies.”
Bauer, in his fourth 12 months of a PhD program at Columbia University, has had a longtime interest within the nascent field of landmine detection as a future profession path, although his primary field of doctoral research involves volcanos.
“I studied demining first,” he said. “After which, since my background was in geology, I went into graduate school in volcanology because there’s no program for landmine detection. It’s just very unusual.”
Because it turned out, the study of volcanos proved to be useful in developing his anti-landmine system, as each mines and volcanos represent potential explosive hazards that endangered humans. “I developed lots of skills that I used doing studying volcanology that I exploit day-after-day for detecting mines and doing the mining work,” he said.
His early fundamental research proved the feasibility of using drones equipped with visual and thermal imagery detect equipment to detect foreign objects lying on the surface of the bottom. The challenge then was the best way to scale up the drone-based mine-detection model right into a system that could possibly be duplicated on a big scale.
“How is that this something that may really reach thousands and thousands of individuals and be a useful skill set? That’s where the machine learning is available in,” Baur said. With friend and colleague, Gabriel Steinberg, Baur cofounded Secure Pro AI to develop a machine learning model that may automate the detections of landmines and other unexploded ordinance.
Secure Pro Group
Secure Pro AI is considered one of three affiliated firms within the Secure Pro Group, the opposite two being SafeProUSA and Airborne Response. SafeProUSA builds body armor and equipment utilized in explosive ordnance disposal and mine-clearing. Airborne Response is a Florida-based drone services provider that gives critical mission services for purchasers who don’t need to assemble their very own fleet of drones.
Erdberg said the three firms work in tandem to supply an entire end-to-end solution to the vital job of coping with unexploded ordinance. “We are able to provide you the drone services, we are able to provide you the AI and ML, after which we are able to provide you the ballistic protection it’s good to eventually go and produce the human into the loop to scrub the minefield,” he said.
Read more: