Method for Real-time Object Detection Based on Lidar Sensor and Camera Using CNN

摘要

A camera and lidar sensor-based real-time object detection method and apparatus using CNN are presented. Camera and lidar sensor-based real-time object detection method using CNN proposed in the present invention is based on PCD (Point Cloud Data) including reflectance and distance information and image data, and object detection learning for a plurality of YOLOs based on CNN Performing each, predicting a bounding box and a reliability score for an object in each object detection model learned based on PCD and image data, and converting the coordinates of the bounding box to the object to fuse the object detection results. And determining a final bounding box through a weighted average based on the confidence score for