Deepen AI, which develops computer vision tools for autonomous systems, has announced the launch of radar and IMU sensor calibrations.
The company’s Deepen Calibrate system is a web-browser-based tool that supports intrinsic and extrinsic calibrations. Deepen AI claims this cuts the time spent on calibrating multi-sensor data from hours to minutes, enabling accurate localization, mapping, sensor fusion perception and control. Deepen Calibrate supports 10 calibration pairs.
The company has also developed a proprietary loop-based calibration optimizer to identify and fix small errors in multiple sensor calibrations, resulting in highly accurate sensor fusion. This works for multiple sensors forming a closed loop. By adding the optimizer on top of the regular techniques, Deepen AI says it can reduce errors and significantly increase sensor fusion accuracy.
“Our calibration suite is critical to help make the world safer and more productive in line with our mission. With the launch of the radar, IMU and optimization loops we have expanded our offerings to multiple new use cases for robotics, automotive and drones,” said Mohammad Musa, co-founder and CEO of Deepen AI.