现代信息科技2025，Vol.9Issue(10)：39-44,49,7.DOI:10.19850/j.cnki.2096-4706.2025.10.008
基于改进AOD-Net算法的道路交通去雾方法
Road Traffic Dehazing Method Based on Improved AOD-Net Algorithm
宋宇博 1李紫玄 1李祯1
作者信息
- 1. 兰州交通大学 机电技术研究所,甘肃 兰州 730070
- 折叠
摘要
Abstract
To address the problems of detail information loss and reduction of image clarity after traffic image dehazing,an improved AOD-Net algorithm is proposed.Aiming at the problem of information loss caused by insufficient feature extraction depth,a cascaded convolutional network is designed to more accurately identify and extract fine-grained features in the image.At the same time,in order to solve the problem that the AOD-Net algorithm does not fully consider the feature weight and easily leads to information redundancy,an adaptive weight distribution mechanism is introduced to dynamically adjust according to the importance of different information,so as to avoid the loss of detailed information.In addition,the clarity of the image after dehazing is improved by introducing the Smooth L1 loss function optimization model.The experiment is carried out on the public data set RESIDE.The results show that compared with the baseline model,the Peak Signal-to-Noise Ratio(PSNR)of the improved algorithm is increased by 0.52 dB,the Structural Similarity(SSIM)is increased by 0.0868,and the information entropy is increased by 0.76.The image after dehazing is clearer,which effectively improves the image quality.Compared with other algorithms,this method shows significant advantages in processing traffic scene images.关键词
图像去雾/AOD-Net算法/级联卷积/注意力机制Key words
image dehazing/AOD-Net algorithm/cascaded convolution/Attention Mechanism分类
信息技术与安全科学引用本文复制引用
宋宇博,李紫玄,李祯..基于改进AOD-Net算法的道路交通去雾方法[J].现代信息科技,2025,9(10):39-44,49,7.
