隧道场景下行人检测DA-Zero-DCE图像增强算法
A denoising-attention based Zero-DCE for tunnel image enhancement
周桐 1李冬春 2田雨聃3
作者信息
- 1. 重庆师范大学计算机与信息科学学院,重庆 401331;重庆工程职业技术学院大数据与物联网学院,重庆 402260
- 2. 重庆师范大学计算机与信息科学学院,重庆 401331
- 3. 重庆大学 自动化学院,重庆 400044
- 折叠
摘要
隧道图像受拍摄环境影响,存在光照分布不均、局部遮挡、噪点较多等问题,针对现有图像增强算法在优化过程中的过曝与失真,提出一种隧道图像增强算法DA-Zero-DCE(denoising-attention based zero-reference deep curve estimation).首先,基于 Zero-DCE 模型,使用U-Net改进用于曲线估计的主干网络DCE-Net,并且加入坐标注意力机制来提升对图像局部区域的暗光感知能力.其次,在曲线估计主干网络后加入NAF-Net噪声去除模块,有效抑制Zero-DCE在低光照增强后的噪声.此外,为缓解增强图像的失真与过曝现象,将空间一致性损失函数的4邻域计算方式扩展为8邻域计算方式,增强输出结果平滑度.通过LOL数据集的消融实验,DA-Zero-DCE模型比Zero-DCE模型在增强结果上的PSNR(峰值信噪比)提升约10 dB,SSIM(结构相似性)提升约0.1,验证了模型的有效性和可行性.
Abstract
Tunnel images,affected by the shooting environment,suffer from uneven illumination distribution,local occlusion,and many noises.To address the problems of overexposure and distortion in existing image enhancement algorithms,this paper proposes a tunnel image enhancement algorithm called DA-Zero-DCE(Denoising-Attention based Zero-Reference Deep Curve Estimation).First,based on the Zero-DCE model,the U-Net is employed to improve the backbone network DCE-Net for curve estimation,and a coordinate attention mechanism is added to enhance the dark light perception ability of local image areas.Second,the NAF-Net noise removal module is added after the curve estimation backbone network to effectively suppress the noises after low-light enhancement by Zero-DCE.To offset the distortion and overexposure of the enhanced images,the 4-neighborhood calculation method of the spatial consistency loss function is extended to an 8-neighborhood calculation method,enhancing the smoothness of the outputs.Through the ablation experiment on the LOL dataset,the DA-Zero-DCE model,compared to the Zero-DCE model,improves PSNR by 10 dB and SSIM by 0.1,demonstrating its feasibility and effectiveness.
关键词
深度学习/卷积神经网络/计算机视觉/图像增强Key words
deep learning/convolutional neural network/computer vision/tunnel image enhance-ment引用本文复制引用
基金项目
中国高校产学研创新基金项目(2021BCG02002)
重庆市教委科学技术研究计划项目(KJZD-K202303405)
重庆市教委科学技术研究计划项目(KJQN202303423)
重庆英才计划"包干制"项目(cstc2022ycjhbgzxm0108)
出版年
2024
国家科技期刊平台
NSTL
万方数据