Multi-Modal 3D Object Detection by Box Matching

doi:10.1109/TITS.2024.3453963

Multi-Modal 3D Object Detection by Box Matching

2024-12-01

1

PRE

AI

DOI：10.1109/TITS.2024.3453963

Original

Original request for help

Save

Abstract

En 中文

Multi-modal 3D object detection has received growing attention as the information from different sensors like LiDAR and cameras are complementary. Most fusion methods for 3D detection rely on an accurate alignment and calibration between 3D point clouds and RGB images. However, such an assumption is not reliable in a real-world self-driving system, as the alignment between different modalities is easily affected by asynchronous sensors and disturbed sensor placement. We propose a novel Fusion network by Box Matching (FBMNet) for multi-modal 3D detection, which provides an alternative way for cross-modal feature alignment by learning the correspondence at the bounding box level to free up the dependency of calibration during inference. With the learned assignments between 3D and 2D object proposals, the fusion for detection can be effectively performed by combining their ROI features. Extensive experiments on the nuScenes dataset demonstrate that our method is much more robust in dealing with challenging cases such as asynchronous sensors, misaligned sensor placement, and degenerated camera images than existing fusion methods. We hope that our could provide an available solution to dealing with these challenging cases for safety in real autonomous driving scenarios.

Keywords:

Three-dimensional displays

Laser radar

Feature extraction

Cameras

Sensors

Proposals

Object detection

Multi-modal

3D object detection

feature alignment

box matching

Multi-Modal 3D Object Detection by Box Matching

Abstract

Journal

Organization