Adaptive Feature Fusion Based Cooperative 3D Object Detection for Autonomous Driving

Wang，Junyong1; Zeng，Yuan2; Gong，Yi3

10.1109/ICTC55111.2022.9778731

2022

3rd Information Communication Technologies Conference (ICTC)

978-1-6654-9509-7

2022 3rd Information Communication Technologies Conference, ICTC 2022

103-107

6-8 May 2022

Nanjing, China

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

In this paper, we focus on the collaborative 3D object detection problem in autonomous vehicle systems in which autonomous vehicles can improve their detection accuracy by aggregating the information received from spatially diverse sensors through wireless links. We propose a novel adaptive feature fusion based cooperative 3D object detection framework, which consists of feature transformation networks and an improved region proposal network. The framework learns to fuse features from different views to improve object detection accuracy on the autonomous vehicle. To evaluate the proposed method, we build a new synthetic dataset created in two driving scenarios (a Roundabout and a T-junction). Experiment analysis and results demonstrate that the proposed adaptive feature fusion approach performs better than two baseline approaches in terms of detection accuracy.

3D object detection. adaptive feature fusion autonomous driving cooperative perception

第一

英语

CPCI-S ; EI

Computer Science

Computer Science, Information Systems

WOS:000838718100018

20222412232601

Autonomous vehicles ; Feature extraction ; Object detection

Highway Transportation:432 ; Data Processing and Image Processing:723.2 ; Robot Applications:731.6

2-s2.0-85131823301

Scopus

1.Southern University of Science And Technology (SUSTech),Department of Electrical And Electronic Engineering,Shenzhen,China
2.Academy For Advanced Interdisciplinary Studies SUSTech,Shenzhen,China
3.SUSTech,Department of Electrical And Electronic Engineering,Shenzhen,China

Wang，Junyong,Zeng，Yuan,Gong，Yi. Adaptive Feature Fusion Based Cooperative 3D Object Detection for Autonomous Driving[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2022:103-107.