OBJECT RECOGNITION SYSTEM FOR COMBINING EO/IR RADAR LiDAR SENSOR BASED ON DEEP NEURAL NETWORK ALGORITHM

摘要

The present invention relates to an object recognition system, and more specifically, by integrating infrared sensor information, visible image sensor information, lidar information, and radar information through neural network technology to robustly recognize objects despite changes in weather and illuminance. It relates to an EO IR RADAR LiDAR sensor fusion object recognition system based on a deep neural network algorithm. To this end, the present invention includes: a first image fusion unit for generating a fusion image through EO (Electro Optical) and IR (Infrared Radiation) sensor information; a second image fusion unit that fuses LiDAR and RADAR information to generate a point cloud including distance information; and an image re-fusion/detection unit for detecting an object by fusing the fusion image and the point cloud received through the first and second image fusion units.