BirdNet: A 3D Object Detection Framework from LiDAR Information

TLDR

Understanding driving situations in all traffic conditions is essential for autonomous vehicles, yet most perception research focuses on computer vision despite common use of LiDAR or radar. The study introduces a LiDAR‑based 3D object detection pipeline comprising three stages. The pipeline projects LiDAR points into a novel bird‑eye‑view cell encoding, uses a convolutional neural network to estimate planar location and heading, then post‑processes to produce 3D oriented detections, and is validated across multiple LiDAR sensors. On the KITTI dataset, the framework outperforms comparable methods, achieving state‑of‑the‑art results.

Abstract

Understanding driving situations regardless the conditions of the traffic scene is a cornerstone on the path towards autonomous vehicles; however, despite common sensor setups already include complementary devices such as LiDAR or radar, most of the research on perception systems has traditionally focused on computer vision. We present a LiDAR-based 3D object detection pipeline entailing three stages. First, laser information is projected into a novel cell encoding for bird's eye view projection. Later, both object location on the plane and its heading are estimated through a convolutional neural network originally designed for image processing. Finally, 3D oriented detections are computed in a post-processing phase. Experiments on KITTI dataset show that the proposed framework achieves state-of-the-art results among comparable methods. Further tests with different LiDAR sensors in real scenarios assess the multi-device capabilities of the approach.