BirdNet: a 3D Object Detection Framework from LiDAR information

TL;DR

BirdNet is a novel LiDAR-based 3D object detection framework that uses a new bird's eye view encoding and CNNs to accurately detect and localize objects for autonomous driving.

Contribution

The paper introduces a new LiDAR data encoding and a CNN-based pipeline for 3D object detection, achieving state-of-the-art results on the KITTI dataset.

Findings

Achieves state-of-the-art detection accuracy on KITTI dataset.

Effective multi-device detection with different LiDAR sensors.

Robust 3D detection in various traffic scenarios.

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.