All-day perception for intelligent vehicles: switching perception algorithms based on WBCNet

作     者：Hongbin XIE Haiyan ZHAO Chengcheng XU Hong CHEN 

作者机构：College of Communication Engineering Jilin University College of Electronic and Information Engineering Tongji University 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2024年第67卷第11期

页      面：269-284页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 082304[工学-载运工具运用工程] 080204[工学-车辆工程] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 0823[工学-交通运输工程] 

基　　金：supported by National Nature Science Foundation of China (Grant No. 52472430) Jilin Province Science and Technology Plan Program (Grant No. 20230201123GX) 

摘      要：A weather-and brightness-based classification network(WBCNet) is proposed for driving scene classification to address the decreased accuracy in perception caused by weather and environment *** facilitate its applicability in vehicles and minimize computational demands on vehicle chips, WBCNet has been designed with special modules, including attention mechanisms and dilated convolutions. Dilated convolutions combined with residual connections empower WBCNet to concurrently handle information at various scales. This aids in simplifying the training and optimization of deep networks, consequently enhancing the model s performance and mitigating the risk of overfitting. The outstanding feature association capability originating from the fusion of channel attention and spatial attention enables WBCNet to focus more on the sky, lanes, and other traffic information features within the image. This design enables WBCNet to use only images as input, making it highly suitable for engineering applications. The output of WBCNet provides the basis for the downstream perception model selection algorithm, allowing it to choose the appropriate perception model for different scenes accurately. A dataset with complex scenes based on Carla is constructed for comparison to verify WBCNet s performance. Finally, a real-world driving dataset is used to validate the effectiveness and real-time performance of WBCNet.