|
|
论文:2023,Vol:41,Issue(1):144-152 |
|
|
引用本文： |
|
|
王殿伟, 刘旺, 房杰, 许志杰. 受生物视觉启发的无人机航拍低照度图像增强算法[J]. 西北工业大学学报 |
|
|
WANG Dianwei, LIU Wang, FANG Jie, XU Zhijie. Enhancement algorithm of low illumination image for UAV images inspired by biological vision[J]. Journal of Northwestern Polytechnical University |
|
|
|
|
|
|
|
| 受生物视觉启发的无人机航拍低照度图像增强算法 |
|
| 王殿伟1, 刘旺1, 房杰1, 许志杰2 |
|
1. 西安邮电大学 通信与信息工程学院, 陕西 西安 710121;
2. 哈德斯菲尔德大学 计算机与工程学院, Huddersfield HD1 3DH |
| 摘要: |
| 针对无人机航拍低照度图像存在亮度低、噪声大、细节不明显等问题,受人类视觉系统中的双路径模型启发,提出一种双路径模型的无人机航拍低照度图像增强算法。构建了一种基于残差单元的U-Net网络将图像分解为结构通路和细节通路;提出了一种改进的生成对抗网络对结构通路进行增强处理,并添加边缘增强模块来增强图像的边缘信息;在细节通路中采取噪声抑制策略减少噪声对图像的影响;融合2条路径的输出得到增强后的图像。实验结果表明,新算法提高了图像的亮度和细节信息,客观评价指标上优于其他对比算法。此外,还验证了所提算法对低照度条件下目标检测算法的影响,实验结果表明,新算法能够有效提升目标检测算法的性能。 |
| 关键词:
低照度图像增强
无人机航拍图像
生物视觉
生成对抗网络
|
|
| Enhancement algorithm of low illumination image for UAV images inspired by biological vision |
|
| WANG Dianwei1, LIU Wang1, FANG Jie1, XU Zhijie2 |
|
1. School of Telecommunication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an 710121, China;
2. School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK |
| Abstract: |
| To address the issue of low brightness, high noise and obscure details of UAV aerial low-light images, this paper proposes an UAV aerial low-light image enhancement algorithm based on dual-path inspired by the dual-path model in human vision system. Firstly, a U-Net network based on residual element is constructed to decompose UAV aerial low-light image into structural path and detail path. Then, an improved generative adversarial network (GAN) is proposed to enhance the structural path, and edge enhancement module is added to enhance the edge information of the image. Secondly, the noise suppression strategy is adopted in detail path to reduce the influence of noise on image. Finally, the output of the two paths is fused to obtain the enhanced image. The experimental results show that the proposed algorithm visually improves the brightness and detail information of the image, and the objective evaluation index is better than the other comparison algorithms. In addition, this paper also verifies the influence of the proposed algorithm on the target detection algorithm under low illumination conditions, and the experimental results show that the proposed algorithm can effectively improve the performance of the target detection algorithm. |
| Key words:
enhancement of low illumination image
UAV images
biological vision
generative adversarial network
|
|
| 收稿日期: 2022-05-23
修回日期:
|
| DOI: 10.1051/jnwpu/20234110144 |
| 基金项目: 国家自然科学基金青年基金(62201454)、陕西省国际科技合作计划(2023-GHYB-04)和西安邮电大学研究生创新基金(CXJJZL2021021)资助 |
| 通讯作者:
Email： |
| 作者简介: 王殿伟(1978-),西安邮电大学副教授、博士,主要从事图像增强处理、图像与视频内容理解、智能态势感知研究。e-mail:wangdianwei@xupt.edu.cn
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 王殿伟 在本刊中的所有文章 |
| 刘旺 在本刊中的所有文章 |
| 房杰 在本刊中的所有文章 |
| 许志杰 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 刘卫东, 李吉玉, 张文博, 等. 基于Retinex和ADMM优化的水下光照不均匀图像增强算法[J]. 西北工业大学学报, 2021, 39(4):824-830 LIU Weidong, LI Jiyu, ZHANG Wenbo, et al. Underwater image enhancement method with non-uniform illumination based on Retinex and ADMM[J].Journal of Northwestern Polytechnical University,2021,39(4):824-830 (in Chinese)
[2] IBRAHIM H, KONG N S P. Brightness preserving dynamic histogram equalization for image contrast enhancement[J]. IEEE Trans on Consumer Electronics, 2007, 53(4):1752-1758
[3] LAND E H. The Retinex theory of color vision[J]. Scientific American, 1978, 237(6):108-128
[4] CAI B, XU X, GUO K, et al. A joint intrinsic-extrinsic prior model for Retinex[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017
[5] GUO X, LI Y, LING H. LIME:low-light image enhancement via illumination map estimation[J]. IEEE Trans on Image Processing, 2017, 26(2):982-993
[6] WANG R, ZHANG Q, FU C W, et al. Underexposed photo enhancement using deep illumination estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019
[7] ZHANG Y, ZHANG J, GUO X. Kindling the darkness:a practical low-light image enhancer[C]//Proceedings of the 27th ACM International Conference on Multimedia, 2019
[8] GUO C, LI C, GUO J, et al. Zero-reference deep curve estimation for low-light image enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
[9] WANG Y, WAN R, YANG W, et al. Low-light image enhancement with normalizing flow[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2022
[10] MA L, MA T, LIU R, et al. Toward fast, flexible, and robust low-light image enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
[11] WU W, WENG J, ZHANG P, et al. URetinex-Net:Retinex-based deep unfolding network for low-light image enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
[12] JIN Y, YANG W, TAN R T. Unsupervised night image enhancement:when layer decomposition meets light-effects suppression[C]//17th European Conference on Computer Vision, Israel, 2002
[13] YANG K F, ZHANG X S, LI Y J. A biological vision inspired framework for image enhancement in poor visibility conditions[J]. IEEE Trans on Image Processing, 2019, 29:1493-1506
[14] 刘月琴, 赖惠成, 高古学, 等. 基于视觉感受野的夜间彩色图像自适应增强算法[J]. 激光杂志, 2020,41(2):92-97 LIU Yueqin, LAI Huicheng, GAO Guxue, et al. Night color image adaptive enhancement algorithm based on visual receptive field[J]. Laser Journal, 2020, 41(2):92-97 (in Chinese)
[15] ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017
[16] KAPLAN E. The M, P, and K pathways of the primate visual system[J]. The Visual Neurosciences, 2004, 1:481-493
[17] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of Medical Image Computing and Computer-Assisted Intervention, Cham, 2015
[18] 杨振舰, 尚佳美, 张众维, 等.基于残差注意力机制的图像去雾算法[J].西北工业大学学报, 2021, 39(4):901-908 YANG Zhenjian, SHANG Jiamei, ZHANG Zhongwei, et al. A new end-to-end image dehazing algorithm based on residual attention mechanism[J].Journal of Northwestern Polytechnical University, 2021, 39(4):901-908 (in Chinese)
[19] YANG L, ZHANG R Y, LI L, et al. SimAM:a simple, parameter-free attention module for convolutional neural networks[C]//Proceedings of Machine Learning, 2021
[20] RUDIN L I, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms[J]. Physica D:Nonlinear Phenomena, 1992, 60(1/2/3/4):259-268
[21] HAI J, XUAN Z, YANG R, et al. R2RNet:Low-light image enhancement via real-low to real-normal network[J]. Journal of Visual Communication and Image Representation, 2023, 90:103712
[22] LI C, GUO C, LOY C C. Learning to enhance low-light image via zero-reference deep curve estimation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2021, 44(8):4225-4238
[23] ZHANG Y, GUO X, MA J, et al. Beyond brightening low-light images[J]. International Journal of Computer Vision, 2021, 129(4):1013-1037
[24] JIANG Y, GONG X, LIU D, et al. EnlightenGAN:deep light enhancement without paired supervision[J]. IEEE Trans on Image Processing, 2021, 30:2340-2349
[25] LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot multibox detector[C]//Proceedings of Computer Vision, Cham, 2016
[26] ZHU X, SU W, LU L, et al. Deformable DETR:deformable transformers for end-to-end object detection[C]//International Conference on Learning Representations, 2021
[27] LOH Y P, CHAN C S. Getting to know low-light images with the exclusively dark dataset[J]. Computer Vision and Image Understanding, 2019, 178:30-42 |
|
|
|
|
|
|
|
