Accurate Automatic 3D Annotation of Traffic Lights and Signs for Autonomous Driving

TL;DR

This paper presents a new method for automatically generating accurate 3D annotations of traffic lights and signs using only RGB images and GNSS/INS data, aiding autonomous vehicle training without LiDAR.

Contribution

It introduces a novel approach for 3D annotation that is accurate, temporally consistent, and does not require LiDAR, leveraging 2D detections and GNSS/INS data.

Findings

Effective up to 200 meters range

Eliminates need for LiDAR data

Suitable for training real-time autonomous driving models

Abstract

3D detection of traffic management objects, such as traffic lights and road signs, is vital for self-driving cars, particularly for address-to-address navigation where vehicles encounter numerous intersections with these static objects. This paper introduces a novel method for automatically generating accurate and temporally consistent 3D bounding box annotations for traffic lights and signs, effective up to a range of 200 meters. These annotations are suitable for training real-time models used in self-driving cars, which need a large amount of training data. The proposed method relies only on RGB images with 2D bounding boxes of traffic management objects, which can be automatically obtained using an off-the-shelf image-space detector neural network, along with GNSS/INS data, eliminating the need for LiDAR point cloud data.