M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

• Published in: arXiv.org
• Main Authors: Brazil, Garrick, Liu, Xiaoming
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 11.08.2019
• Subjects: Algorithms; Critical components; Design parameters; Image detection; Lidar; Object recognition; Parameter estimation; Performance enhancement; Scene analysis

Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas monocular image-only methods experience drastically reduced perfor...