基于天空区域分割与边缘优化的图像去雾算法

兰州理工大学学报 ›› 2025, Vol. 51 ›› Issue (1): 92-99.

• 自动化技术与计算机技术 • 上一篇下一篇

基于天空区域分割与边缘优化的图像去雾算法

赵小强^*1,2,3, 周康毅¹

1.兰州理工大学电气工程与信息工程学院, 甘肃兰州 730050;
2.兰州理工大学甘肃省工业过程先进控制重点实验室, 甘肃兰州 730050;
3.兰州理工大学国家级电气与控制工程实验室教学中心, 甘肃兰州 730050

收稿日期:2022-07-01 出版日期:2025-02-28 发布日期:2025-03-03
通讯作者: 赵小强(1969-),男,陕西岐山人,博士,教授,博导.Email:xqzhao@lut.edu.cn
基金资助:
国家自然科学基金(62263021),甘肃省高校产业支撑计划项目(2023CYZC-24),甘肃省科技计划资助项目(21JR7RA206)

Image dehazing algorithm based on sky regionsegmentation and edge optimization

ZHAO Xiao-qiang^1,2,3, ZHOU Kang-yi¹

1. College of Electrical Engineering and Information Engineering,Lanzhou University of Technology, Lanzhou 730050, China;
2. Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou University of Technology, Lanzhou 730050, China;
3. National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, China

Received:2022-07-01 Online:2025-02-28 Published:2025-03-03

摘要/Abstract

摘要： 针对暗通道先验算法对天空区域和景深突变区域处理能力不足,复原后的图像存在光晕以及颜色失真等降质问题,提出一种将区域分割与边缘优化相结合的去雾算法.首先,提出一种有效的自适应阈值分割算法,将有雾图像中的天空区域和非天空区域分割开来,在天空区域内对全局大气光值进行求解.其次,对有雾图像天空区域的暗通道和透射率进行分析,求出天空区域透射率权重图,进而求出该区域透射率;对非天空区域提出一种边缘优化算法来改进暗通道,抑制光晕现象的产生.然后,通过引导滤波细化透射率,利用大气散射模型复原出图像.最后,对复原后的图像进行色调映射,使其更加符合人眼视觉特性.实验结果表明,本文算法去雾效果明显,天空区域恢复自然,边缘光晕现象得到有效抑制,复原后的图像在主观视觉和客观指标方面均表现出色.

关键词: 暗通道先验, 天空区域分割, 透射率权重, 边缘优化, 色调映射

Abstract: Aiming at the insufficient processing ability of the traditional dark channel prior algorithm for the sky area and the sudden depth of field area, and the degraded problems such as halo and color distortion in the restored image, a dehazing algorithm that combines area segmentation and edge optimization algorithm is proposed in this paper. Firstly, an efficient adaptive threshold segmentation algorithm is proposed to separate the sky and non-sky regions in foggy images, and the global atmospheric light value is solved in the sky area. Secondly, the dark channel and transmittance of the sky area of the foggy image are analyzed to derive the transmittance weight map, and then the transmittance of the sky area is obtained. For the non-sky area. an edge optimization algorithm is proposed to improve the dark channel and suppress the appearance of the halo phenomenon. Then the transmittance is refined by guided filtering, and the image is restored by using the atmospheric scattering model. Finally, tone mapping is performed on the restored image to make it more consistent with the visual characteristics of human eyes. The experimental results show that the proposed algorithm in this paper significantly improves dehazing effectiveness, restores the natural appearance of the sky region, effectively suppresses edge halos, and delivers superior performance in both subjective vision and objective indicators.

Key words: dark channel prior, division of sky, transmittance weight, edge optimization, tone mapping

中图分类号:

TP391

赵小强, 周康毅. 基于天空区域分割与边缘优化的图像去雾算法[J]. 兰州理工大学学报, 2025, 51(1): 92-99.

ZHAO Xiao-qiang, ZHOU Kang-yi. Image dehazing algorithm based on sky regionsegmentation and edge optimization[J]. Journal of Lanzhou University of Technology, 2025, 51(1): 92-99.

参考文献

[1] 蒋华伟,杨震,张鑫,等.图像去雾算法研究进展[J].吉林大学学报(工学版),2021,51(4):1169-1181.
[2] SEOW M J,ASARI V K.Ratio rule and homomorphic filter for enhancement of digital colour image[J].Neurocomputing,2006,69(7/8/9):954-958.
[3] DIPPEL S,STAHL M,WIEMKER R,et al.Multiscale contrast enhancement for radiographies: Laplacian pyramid versus fast wavelet transform[J].IEEE Transactions on Medical Imaging,2002,21(4):343-353.
[4] JUN W L,RONG Z H U.Image defogging algorithm of single color image based on wavelet transform and histogram equalization[J].Applied Mathematical Sciences,2013,7(79):3913-3921.
[5] LIU J,ZHU J,PEI Y,et al.Adaptive depth map-based retinex for image defogging[C]//2016 International Conference on Audio,Language and Image Processing (ICALIP).Shanghai:IEEE,2016:318-322.
[6] REN W,PAN J,ZHANG H,et al.Single image dehazing via multi-scale convolutional neural networks with holistic edges[J].International Journal of Computer Vision,2020,128(1):240-259.
[7] CAI B,XU X,JIA K,et al.Dehazenet:an end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[8] FATTAL R.Single image dehazing[J].ACM Transactions on Graphics (TOG),2008,27(3):1-9.
[9] TAN R T.Visibility in bad weather from a single image[C]//2008 IEEE Conference on Computer Vision and PatternRecognition.Anchorage:IEEE,2008:1-8.
[10] ZHU Q,MAI J,SHAO L.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):3522-3533.
[11] WANG W,JI T,WU X,et al.Gray projection for single image dehazing[C]//2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC).Nanjing:IEEE,2018:1152-1155.
[12] KUMAR H,GUPTA S,VENKATESH K S.Realtime dehazing using colour uniformity principle[J].IET Image Processing,2019,13(11):1931-1939.
[13] HE K,SUN J,TANG X.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,33(12):2341-2353.
[14] HE K,SUN J,TANG X.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,35(6):1397-1409.
[15] MERZBAN M H,ELBARYOUMI M.Efficient solution of Otsu multilevel image thresholding:a comparative study[J].Expert Systems with Applications,2019,116:299-309.
[16] XING J,YANG P,QINGGE L.Automatic thresholding using a modified valley emphasis[J].IET Image Process,2020,14(3):536-544.
[17] 宋瑞霞,刚睿鹏,王小春.含有大片天空区域图像的去雾算法[J].计算机辅助设计与图形学学报,2019,31(11):1946-1954.
[18] WANG W,YUAN X,WU X,et al.An airlight estimation method for image dehazing based on gray projection[J].Multimedia Tools and Applications,2020,79(37):27185-27203.
[19] 王柯俨,胡妍,王怀,等.结合天空分割和超像素级暗通道的图像去雾算法[J].吉林大学学报(工学版),2019,49(4):1377-1384.
[20] LIU Y,LI H,WANG M.Single image dehazing via large sky region segmentation and multiscale opening dark channel model[J].IEEE Access,2017,5:8890-8903.
[21] DRAGO F,MYSZKOWSKI K,ANNEN T,et al.Adaptive logarithmic mapping for displaying high contrast scenes[J].Computer Graphics Forum:Journal of the European Association for Computer Graphics,2003,22(3):419-426.
[22] MENG G,WANG Y,DUAN J,et al.Efficient image dehazing with boundary constraint and contextual regularization[C]//Proceedings of the IEEE International Conference on Computer Vision.Sydney:IEEE,2013:617-624.
[23] ZHOU H,ZHANG Z,LIU Y,et al.Single image dehazing algorithm based on modified dark channel prior[J].IEICE Transactions on Information and Systems,2021,104(10):1758-1761.
[24] CHEN T,LIU M,GAO T,et al.A fusion-based defogging algorithm[J].Remote Sensing,2022,14(2):425.

基于天空区域分割与边缘优化的图像去雾算法

Image dehazing algorithm based on sky regionsegmentation and edge optimization

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	林玉萍, 刘梦皎, 王明豪, 张栋, 许美凤, 李策. 面向多模态皮肤病语料库的可变形分区注意力黑色素瘤识别方法[J]. 兰州理工大学学报, 2025, 51(5): 92-99.
[2]	谢小正, 杜敏, 张子健, 赵维吉. 基于改进樽海鞘群算法的无人机山区巡航[J]. 兰州理工大学学报, 2025, 51(4): 43-50.
[3]	赵宏, 张陈鹏, 王奡隆, 张扬. 基于细粒度字词特征的中文作者识别模型[J]. 兰州理工大学学报, 2025, 51(3): 99-106.
[4]	郭润兰, 薛凯, 邓文强, 范雅琼, 王虎林. 基于随机游走麻雀搜索算法的多特征结构尺寸熔融沉积成型工艺参数优化[J]. 兰州理工大学学报, 2024, 50(1): 41-47.
[5]	赵小强, 王涛. 基于边缘约束与范数比值的图像盲复原[J]. 兰州理工大学学报, 2024, 50(1): 76-83.
[6]	张乐, 包广斌, 郭琳, 武立. 基于LSTM的智能手机3D手写识别[J]. 兰州理工大学学报, 2024, 50(1): 96-103.
[7]	袁小鹏, 苗思蕊, 马蓉, 冯涛, 方君丽. 基于区块链的社会化考试成绩安全管理系统[J]. 兰州理工大学学报, 2023, 49(4): 88-94.
[8]	王星, 晏榕璟. 深度可分卷积结合多通道注意力的垃圾图像快速分类模型[J]. 兰州理工大学学报, 2023, 49(3): 88-93.
[9]	谢楠, 马振国, 唐兵, 黄煜铭, 张柯琪, 曹丹怡. 继电保护设备剩余寿命预测的智能算法研究[J]. 兰州理工大学学报, 2023, 49(2): 83-87.
[10]	苏昀暄, 涂正, 王绪安, 林川. 一种基于CKKS同态加密与神经网络的安全人脸识别方案[J]. 兰州理工大学学报, 2023, 49(2): 103-109.
[11]	王燕, 赵妮妮, 范林. 基于图神经网络特征交叉的协同过滤算法[J]. 兰州理工大学学报, 2023, 49(1): 94-102.
[12]	赵荣珍, 赵楠. 结合扰动集成RBF的故障识别方法[J]. 兰州理工大学学报, 2022, 48(6): 40-45.
[13]	冯笑, 杨雅婷, 董瑞, 艾孜麦提·艾尼瓦尔, 马博. 基于回译和集成学习的维汉神经机器翻译方法[J]. 兰州理工大学学报, 2022, 48(5): 99-106.
[14]	郭润兰, 史方青, 范雅琼, 何智. 基于卷积神经网络的壁面清洗机器人障碍物检测识别算法[J]. 兰州理工大学学报, 2022, 48(4): 83-89.
[15]	赵小强, 蒋红梅. 基于可调节判别器的领域适应[J]. 兰州理工大学学报, 2022, 48(1): 85-90.