Dr. Bharath Ramesh, Research Scientist at  NUS, Singapore gave a talk on Towards Autonomous Unmanned Aerial Systems: Object Recognition and Tracking using Event Cameras on Low-power Devices on 5 February.

Computer vision has found broad applications in Unmanned Aerial Vehicles (UAVs)  such as vision-based navigation, object detection, identification and tracking. Nowadays, there has been a growing interest in inexpensive small UAVs for military and civil applications. In particular, area surveillance and higher-level vision tasks have drawn most of the attention with a focus on low-power sensing capabilities. Dr. Bharath’s talk reviewed the fundamentals and properties of object recognition by leveraging exciting technologies including silicon retina sensors and low-power processing devices. The second part of his talk focused on the development of a novel algorithm to tackle the problem of object tracking with a moving event camera and gave a unified view of the main approaches for event-based sensing on low-power FPGA devices under closed-loop control. Lastly, he discussed open problems to build bio-inspired embedded sensory systems for autonomous navigation of aerial vehicles and remote sensing applications.

Dr. Bharath’s main research interests include pattern recognition and computer vision. At present, his research is specifically focussed on event-based cameras for autonomous  sensing and navigation. This includes tracking and recognition with an array of sensors, most importantly event-based cameras, to be processed efficiently on low-power devices to yield accurate results at real-time. In the past, he has mostly worked on object recognition and related areas such as scene understanding, face recognition, and object detection.

Dr. Bharath received the B.E. degree in electrical & electronics engineering from Anna University of India in 2009; M.Sc and Ph.D degrees in electrical engineering from National University of Singapore in 2011 and 2015 respectively, working at the Control and Simulation Laboratory on Image Classification using Invariant Features.