基于注意力机制的图像去雾方法

针对目前图像去雾方法中存在的输出图像色彩偏暗、场景信息丢失以及去雾不彻底等问题, 提出了一种基于注意力机制的端到端图像去雾方法。首先将通道注意力机制嵌入到Inception网络中, 并由融合后的网络进行浅层特征提取; 然后通过多尺度卷积和残差密集连接块学习深层图像信息, 同时以跳跃连接的方式实现深浅特征融合; 最后经过单一卷积层回归到像素比例系数矩阵, 依据改进后的大气散射模型生成无雾图像; 网络模型在均方差(MSE)的基础上设计了保真度损失函数作为约束。在RESIDE雾天数据集上的实验结果显示, 提出的方法的峰值信噪比(PSNR)、结构相似度(SSIM)、学习感知图像块相似度(LPIPS)和CIEDE2000分别达到32.545,0.970, 0.026和2.711, 表现出良好的效果, 输出图像去雾彻底, 色彩保真度高, 并有效避免了已有方法中的细节信息丢失问题。

Abstract

Aiming at the problems existing in current image dehazing methods, such as dark color of output image, loss of scene information and incomplete dehazing, an end-to-end image dehazing method based on attention mechanism is proposed.Firstly, the channel attention mechanism is embedded into the inception network, and the shallow features are extracted from the fused network.Then, the deep image information is learned by multi-scale convolution and residual dense connection blocks, the depth and shallow feature fusion is realized by skip connection.Finally, it is returned to the pixel scale coefficient matrix through a single convolution layer, and a fog-free image is generated according to the improved atmospheric scattering model.Based on the Mean Square Error (MSE), the fidelity loss function is designed as a constraint in the network model.The experimental results on RESIDE dataset show that the Peak Signal-to-Noise Ratio(PSNR), Structure Similarity (SSIM), Learning Perceptual Image Patch Similarity (LPIPS) and CIEDE2000 of the proposed method reach 32.545, 0.970, 0.026 and 2.711 respectively.The method shows good effect, the output image is dehazed thoroughly and the color fidelity is high;It effectively avoids the loss of detail information in the existing methods.

参考文献

[1] 万隆.基于颜色描述的快速视频去雾算法［J］.电光与控制, 2021, 28(5):36-41.

[2] 张登银,鞠铭烨,钱雯.图像去雾算法研究现状与展望［J］.南京邮电大学学报(自然科学版),2020, 40(5):101-111.

[3] 吴成茂.直方图均衡化的数学模型研究［J］.电子学报,2013,41(3):598-602.

[4] 王万国,王滨海,张晶晶,等.基于直方图规定化的图像去雾算法［J］.计算机技术与发展,2014, 24(9):241-244.

[5] 王智奇,李荣冰,刘建业,等.基于同态滤波和直方图均衡化的图像增强算法［J］.电子测量技术,2020, 43(24):75-80.

[6] 贺欢,吐尔洪江·阿布都克力木,何笑.基于小波变换的彩色图像去雾方法［J］.计算机技术与发展,2020, 30(9):60-64.

[7] 罗浩,仲佳嘉,李祥.基于改进多尺度Retinex的单幅彩色图像增强算法［J］.吉林大学学报(理学版),2019, 57(2):369-374.

[8] 王彦林,张进.改进成像模型的单尺度Retinex彩色图像增强算法［J］.计算机工程与设计,2018, 39(11):3511-3515.

[9] TAN R T.Visibility in bad weather from a single from a single image［C］//Proceedings of IEEE Computer Vision and Pattern Recognition.Anchorage:IEEE, 2008:1956-1963．

[10] FATTAL R.Single image dehazing［J］.ACM Transactions on Graphics, 2008, 27(3):721-708.

[11] HE K M, SUN J, TANG X O.Single image haze removal using dark channel prior［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Miami:IEEE, 2009:1956-1963.

[12] HE K M, SUN J, TANG X O.Guided image filtering［C］//Proceeding of the 11th European Conference on Computer Vision:Part I.Berlin:Springer, 2010:1-14.

[13] MENG G F, WANG Y, DUAN J Y, et al.Efficient image dehazing with boundary constraint and contextual regularization［C］//Proceedings of IEEE International Conference on Computer Vision.Washington:IEEE, 2014:617-624.

[14] CAI B L, XU X M, JIA K, et al.DehazeNet:an end-to-end system for single image haze removal［J］.IEEE Transaction on Image Processing, 2016, 25(11):5187-5198．

[15] REN W Q, LIU S, ZHANG H, et al.Single image dehazing via multi-scale convolutional neural networks［C］//European Conference on Computer Vision.Cham:Springer Verlag, 2016:154-169.

[16] LI B Y, PENG X L, WANG Z Y, et al.AOD-net:all-in-one dehazing network［C］//IEEE International Conference on Computer Vision(ICCV).Venice:IEEE, 2017:4780-4788.

[17] 寇大磊,钱敏,权冀川,等.基于多尺度卷积网络的快速图像去雾算法［J］.计算机工程与应用,2020,56(20):191-198.

[18] NARASIMHAN S G, NAYAR S K.Vision and the atmosphere［J］.International Journal of Computer Vision, 2002, 48(3):233-254.

[19] NARASIMHAN S G, NAYAR S K.Contrast restoration of weather degraded images［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(6):713-724.

葛涛, 张闯, 张海超, 乔丹. 基于注意力机制的图像去雾方法[J]. 电光与控制, 2023, 30(3): 20. GE Tao, ZHANG Chuang, ZHANG Haichao, QIAO Dan. An Image Dehazing Algorithm Based on Attention Mechanism[J]. Electronics Optics & Control, 2023, 30(3): 20.

基于注意力机制的图像去雾方法

关于本站 Cookie 的使用提示

全站搜索

基于注意力机制的图像去雾方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索