Adaptive fusion of LiDAR features for 3D object detection in autonomous driving

In the field of autonomous driving, cooperative perception through vehicle-to-vehicle communication significantly enhances environmental understanding by leveraging multi-sensor data, including LiDAR, cameras, and radar. However, traditional early or late fusion methods face challenges such as high...

Descripción completa

Detalles Bibliográficos
Autores: Wang, Mingrui, Li, Dongjie|||0000-0002-1005-7890, Casas Pla, Josep Ramon|||0000-0003-4639-6904, Ruiz Hidalgo, Javier|||0000-0001-6774-685X
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/443824
Acceso en línea:https://hdl.handle.net/2117/443824
https://dx.doi.org/10.3390/s25133865
Access Level:acceso abierto
Palabra clave:Autonomous driving
Cooperative perception
Data fusion
Object detection
LiDAR system
Sensor fusion
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Teledetecció
Descripción
Sumario:In the field of autonomous driving, cooperative perception through vehicle-to-vehicle communication significantly enhances environmental understanding by leveraging multi-sensor data, including LiDAR, cameras, and radar. However, traditional early or late fusion methods face challenges such as high bandwidth and computational resources, which make it difficult to balance data transmission efficiency with the accuracy of perception of the surrounding environment, especially for the detection of smaller objects such as pedestrians. To address these challenges, this paper proposes a novel cooperative perception framework based on two-stage intermediate-level sensor feature fusion specifically designed for complex traffic scenarios where pedestrians and vehicles coexist. In such scenarios, the model demonstrates superior performance in detecting small objects like pedestrians compared to mainstream perception methods while also improving the cooperative perception accuracy for medium and large objects such as vehicles. Furthermore, to thoroughly validate the reliability of the proposed model, we conducted both qualitative and quantitative experiments on mainstream simulated and real-world datasets. The experimental results demonstrate that our approach outperforms state-of-the-art perception models in terms of mAP, achieving up to a 4.1% improvement in vehicle detection accuracy and a remarkable 29.2% enhancement in pedestrian detection accuracy.