The last talk of the Day 2 "Leveraging Computer Vision In Drone Tech" was presented at the Computer Vision conference of the year, CVDC 2020 by Animesh Dutta, who is the Machine Learning Developer at Kesowa. CVDC 2020 is scheduled for 13th and 14th of August, organised by the Association of Data Scientists (ADaSCi), the premier global professional body of data science and machine learning professionals. Dutta kick-started the talk by discussing the ecosystems of drones and how drone tech is evolving quite rapidly by leveraging emerging technologies like artificial intelligence, deep learning, autonomy and unmanned aerial systems. Regarding the ecosystem, Dutta mentioned some of the important components which constitute a drone ecosystem. The speaker then discussed the steps that are required to build a drone by showing an example of a drone that is built in-house by Dutta and his team at Kesowa.

As climate change-driven wildfires continue to wreak havoc around the world, artificial intelligence, satellites, and drones are emerging as a potential solution to this problem. Despite repeated warnings from the scientific community about the gravity of the issue, our greenhouse gas emissions continue to rise year after year, resulting in deadly heatwaves, devastating wildfires, severe droughts, and powerful hurricanes. While these extreme weather events once used to be few and far between, they've become more frequent and lethal in recent years, a direct consequence of climate change. According to Munich Re, one of the world's leading insurance companies, weather and climate events killed more than 4,000 people worldwide and caused around $42 billion in insured losses in 2019. Wildfires in particular have become increasingly destructive in recent years. An average of 67,000 wildfires per year were recorded over the last 10 years in the United States, burning an average of 7 million acres of land, according to the National Interagency Fire Center (NIFC).

NEW DELHI: A team of students at IIT Madras has developed a drone technology that can help in rescue and relief operations, especially after natural disasters. "The solution is beta-ready and can be deployed. It is currently being tested and would reach the commercialisation phase within six months," said Ayush Parasbhai Maniar, student member, UAVs for Disaster Management, Centre for Innovation (CFI) -- Indian Institute of Technology (IIT), Madras. "The iterations to improve every feature would continue. The team's artificial intelligence (AI)-based solution is used in combination with drones that use swarm intelligence to collect data and analyse it in real-time. The project is being executed with data inputs from the National Disaster Response Force (NDRF). The drone, or unmanned aerial vehicle (UAV), will have a software that will be compatible with standard drones available in the market. "Thus, for the physical drone we would be partnering with a drone company," Maniar said. This IIT team has also won. 10 lakh in funding from the Indian Innovation Growth Programme (IIGP 2.0) University Challenge, a programme conducted by the department of science and technology along with global defence manufacturer Lockheed Martin Corporation and Tata Trusts. "This solution is based on innovation based on futuristic disruptive technologies.

Drones took up a lot of floor (and air) space at the Consumer Electronics Show in Las Vegas this year, but one of the most impressive displays of new drone tech came from Qualcomm. The chipmaker showed off the latest iteration of its Snapdragon Flight Drone Platform, which allows for flight control and machine learning in real time onboard a drone. With machine learning, drones can fly autonomously without knowing beforehand what they might encounter. Other drones have artificial intelligence that can do things like follow a moving object or avoid obstacles too, but Qualcomm's tech shows more advanced computing that can actually understand what the drone encountered in mid-air and create a flight path. Qualcomm put together a set at its booth at CES that resembled the inside of a cluttered warehouse, showing how its drone processing and decision-making technology is nimble enough to allow drones to operate indoors and in unpredictable settings without using any GPS.