自动驾驶样本库中多模态雨天场景融合构建方法  

Construction Method for Multimodal Rainy Scene Fusion in Autonomous Driving Sample Library

作　　者：董兆龙 黄鹤[1,2] 李战一 杨澜 王会峰[2] Dong Zhaoong;Huang He;Li Zhanyi;Yang Lan;Wang Huifeng(School of Electronic and Control Engineering,Chang’an University,Xi’an 710064;Key Laboratory of Intelligent Expressway Information Fusion and Control,Xi’an 710064;School of Information Engineering,Chang’an University,Xi’an 710064)

机构地区：[1]长安大学电子与控制工程学院,西安710064 [2]西安市智慧高速公路信息融合与控制重点实验室,西安710064 [3]长安大学信息工程学院,西安710064

出　　处：《汽车工程》2025年第2期211-221,共11页Automotive Engineering

基　　金：国家自然科学基金面上项目(52472446);国家重点研发计划项目(2021YFB2501200);陕西省留学人员科技活动择优资助项目(2023001);中央高校基本科研业务费资助项目(300102324501)资助。

摘　　要：针对训练无人驾驶感知性能过程中,现有雨天场景样本数据采集难度大、不可控以及样本库数量较少等问题,提出了一种基于多模态融合的雨天交通场景构建算法。首先,分析雨天场景,将其划分为雨线模型和雨滴模型两种模型进行重构;其次,提出一种基于随机多源融合的雨线模型,由多个方向、多个感知密度融合得出雨线效果;然后,提出了一种基于异构映射的雨滴模型,实现对单个雨滴的凸透效果映射,并结合防碰撞设计,避免多雨滴累加在相同区域造成误差;最后,融合两种模型,并利用多种基础形态实现对雨天场景的重构。实验结果表明,构建的雨天场景随着雨量的增加,部分细节信息变丰富,信息熵、平均梯度等指标先增加后减少,而图像质量则持续降低,接近于实际雨天场景。随着雨量的增加,图像干扰信息和细节都明显增强,信息熵、平均梯度等都有所上升,PSNR、SSIM等参数明显降低,图像质量显著下降。For the problems of difficult and uncontrollable data acquisition,as well as limited quantity of available rainy day scene samples in the process of unmanned driving perception performance training,a multimod-al fusion-based algorithm for constructing rainy day traffic scenes is proposed.Firstly,the rainy day scenes are ana-lyzed and categorized into two models of rain line models and raindrop models for reconstruction.Secondly,a sto-chastic multisource fusion-based rain line model is proposed,which integrates rain effect from multiple directions and densities.Next,a heterogeneous mapping-based raindrop model is proposed to achieve realistic convex transpar-ency mapping for individual raindrops,coupled with collision prevention design to mitigate cumulative errors of mul-tiple raindrops in the same area.Finally,the two models are integrated to realize reconstruction of rainy day scenes by using various foundational forms.The experimental results show that as rainfall intensity increases,detailed infor-mation in the constructed scenes becomes richer initially,with metrics such as entropy and average gradient show-ing an initial increase followed by a decrease,while image quality continuously decreases,approaching realistic rainy day conditions.With higher rainfall intensity,both interference and detail in the images notably increase,with higher entropy and average gradient,as well as decreased PSNR and SSIM parameters,indicating significant image quality degradation.

关 键 词：雨天场景样本 雨线模型 雨滴模型 异构映射 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]