Battlefield Image Dehazing Based on Global Compensation Attention Mechanism

doi:10.12382/bgxb.2022.0786

Abstract

Abstract:

In modern war, images and other carriers are widely used to obtain information. However, the images obtained in foggy environment not only affect scene rendering, but also mask important features. In order to improve the use value of fog-degraded images in modern warfare, a battlefield image dehazing method based on the global compensation attention mechanism is proposed. A global compensation module is constructed to ensure the integrity of output image, and channel down sampling is added to restore the clear image. The dense residual module is used to learn the nonlinear mapping between degraded image and clear image. In addition, an attention mechanism is added to improve the flexible processing capability of the network. The network can fully learn the feature information by increasing the number of channels of the input image. The experimental results show that the proposed method achieves excellent results in both subjective and objective evaluation compared with classical or novel image dehazing methods. The proposed method fully combines the attention mechanism with the global compensation module to effectively alleviate the problem of battlefield image degradation. At the same time, it pays attention to feature enhancement to enable the complete presentation of information and ultimately achieve better performance.

Key words: battlefield image dehazing, global compensation, attention mechanism, dense residual module

CLC Number:

TP391.4

LIN Sen, WANG Jingang, GAO Hongwei. Battlefield Image Dehazing Based on Global Compensation Attention Mechanism[J]. Acta Armamentarii, 2024, 45(4): 1344-1353.

Figures/Tables 15

References 34

[1]	蒋超, 崔玉伟, 王辉. 基于图像的无人机战场态势感知技术综述[J]. 测控技术, 2021, 40(12):14-19.
	JIANG C, CUI Y W, WANG H. Review on battlefield situational awareness of uav based on image technology[J]. Measurement & Control Technology, 2021, 40(12): 14-19. (in Chinese)
[2]	秦朝轩, 顾晓辉. 基于双边分解与L_1暗通道的战场图像增强算法[J]. 控制与决策, 2021, 36(5): 1165-1172.
	QIN Z X, GU X H. A battlefield image enhancement algorithm based on bilateral decomposition and L1 dark channel prior[J]. Control and Decision, 2021, 36(5): 1165-1172. (in Chinese)
[3]	HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353. doi: 10.1109/TPAMI.2010.168 pmid: 20820075
[4]	李春明, 姜雨彤, 宋海平, 等. 基于光学厚度代理模型的雾浓度估计及图像去雾[J]. 兵工学报, 2019, 40(7):1425-1433. doi: 10.3969/j.issn.1000-1093.2019.07.012
	LI C M, JIANG Y T, SONG H P, et al. Research on optical depth surrogate model based method for estimating fog density and removing fog effect from images[J]. Acta Armamentarii, 2019, 40(7):1425-1433. (in Chinese)
[5]	ZHU Q S, MAI J M, SHAO L. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE transactions on image processing, 2015, 24(11): 3522-3533. doi: 10.1109/TIP.2015.2446191 pmid: 26099141
[6]	SHIN J, KIM M, PAIK J, et al. Radiance-reflectance combined optimization and structure-guided-norm for single image dehazing[J]. IEEE Transactions on Multimedia, 2019, 22(1): 30-44.
[7]	LIU X N, LI H, ZHU C. Joint contrast enhancement and exposure fusion for real-world image dehazing[J]. IEEE Transactions on Multimedia, 2022, 24: 3934-3946.
[8]	AGRAWAL S C, JALAL A S. A comprehensive review on analysis and implementation of recent image dehazing methods[J]. Archives of Computational Methods in Engineering, 2022, 29: 4799-4850.
[9]	CAI B L, XU X M, 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. doi: 10.1109/TIP.2016.2598681 pmid: 28873058
[10]	YU H, LI X P, FAN C E, et al. MsDA: multi-scale domain adaptation dehazing network[J]. Applied Intelligence, 2022, 53:2147-2160.
[11]	LI F S, DI X G, ZHAO C D, et al. FA-GAN: a feature attention GAN with fusion discriminator for non-homogeneous dehazing[J]. Signal, Image and Video Processing, 2022, 16(5): 1243-1251.
[12]	ZHOU Y, CHEN Z H, LI P, et al. FSAD-net: feedback spatial attention dehazing network[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 34(10): 7719-7733.
[13]	ZHAO S Y, ZHANG L, SHEN Y, et al. RefineDNet: a weakly supervised refinement framework for single image dehazing[J]. IEEE Transactions on Image Processing, 2021, 30: 3391-3404.
[14]	姜雨彤, 宋海平, 王光辉. 基于质量评价最优的无人机航拍图像去雾方法[J]. 兵工学报, 2022, 43(1):148-158. doi: 10.3969/j.issn.1000-1093.2022.01.016
	JIANG Y T, SONG H P, WANG G H. Image dehazing based on the optimum of uavaerial image quality evaluation[J]. 2022, 43(1):148-158. (in Chinese)
[15]	ZHANG X Q, WANG T, WANG J X, et al. Pyramid channel-based feature attention network for image dehazing[J]. Computer Vision and Image Understanding, 2020, 197: 103003.
[16]	XU H Y, LI Y N. A deep neural network for coarse-to-fine image dehazing with interleaved residual connections and semi-supervised training[J]. IEICE Transactions on Information and Systems, 2022, 105(5): 1125-1129.
[17]	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE conference on computer vision and pattern recognition. Las Vegas, NV, US:IEEE, 2016: 770-778.
[18]	HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of 2017 IEEE conference on computer vision and pattern recognition.Honolulu, HI, US:IEEE, 2017: 4700-4708.
[19]	ZHANG Y L, TIAN Y P, KONG Y, et al. Residual dense network for image super-resolution[C]// Proceedings of 2018 IEEE conference on computer vision and pattern recognition.Salt Lake City, UT, US:IEEE, 2018: 2472-2481.
[20]	QIN X, WANG Z L, BAI Y C, et al. FFA-Net: feature fusion attention network for single image dehazing[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. New York, NY, US:AAAI, 2020, 34(7): 11908-11915.
[21]	DURAND L B, RUIZ L J, PEREZ B G, et al. Color, lightness, chroma, hue, and translucency adjustment potential of resin composites using CIEDE2000 color difference formula[J]. Journal of Esthetic and Restorative Dentistry, 2021, 33(6): 836-843. doi: 10.1111/jerd.12689 pmid: 33283966
[22]	李静, 刘哲, 黄文准. 基于快速非局部均值和超分辨率重建的图像降噪算法[J]. 兵工学报, 2021, 42(8):1716-1727.
	LI J, LIU Z, HUANG W Z. An image deniosing algorithm based on fast non-local mean and super-resolution reconstruction[J]. Acta Armamentarii, 2021, 42(8):1716-1727. (in Chinese) doi: 10.3969/j.issn.1000-1093.2021.08.016
[23]	BAKUROV I, BUZZELLI M, SCHETTINI R, et al. Structural similarity index (SSIM) revisited: a data-driven approach[J]. Expert Systems with Applications, 2022, 189: 116087.
[24]	WANG Y Z, YAN X F, GUAN D H, et al. Cycle-SNSPGAN: towards real-world image dehazing via cycle spectral normalized soft likelihood estimation patch GAN[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11):20368-20382.
[25]	顾德英, 罗聿伦, 李文超. 基于改进YOLOv5算法的复杂场景交通目标检测[J]. 东北大学学报(自然科学版), 2022, 43(8):1073-1079. doi: 10.12068/j.issn.1005-3026.2022.08.002
	GU D Y, LUO Y L, LI W C. Traffic target detection in complex scenes based on improved YOLOv5 algorithm[J]. Journal of Northeastern University(Natural Science), 2022, 43(8):1073-1079. (in Chinese)
[26]	LI P C. Quantum implementation of the classical Canny edge detector[J]. Multimedia Tools and Applications, 2022, 81(8): 11665-11694.
[27]	BANSAL M, KUMAR M, KUMAR M. 2D object recognition: a comparative analysis of SIFT, SURF and ORB feature descriptors[J]. Multimedia Tools and Applications, 2021, 80(12): 18839-18857.
[28]	LI B Y, REN W Q, FU D P, et al. Benchmarking single-image dehazing and beyond[J]. IEEE Transactions on Image Processing, 2018, 28(1): 492-505.
[29]	CHEN X, HUANG Y F. Memory-oriented unpaired learning for single remote sensing image dehazing[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 3511705.
[30]	ANCUTI C O, ANCUTI C, TIMOFTE R, et al. O-haze: a dehazing benchmark with real hazy and haze-free outdoor images[C]// Proceedings of 2018 IEEE conference on computer vision and pattern recognition workshops. Salt Lake City, UT, US:IEEE, 2018: 754-762.
[31]	刘琼, 严由嵘, 张旭, 等. 基于动态小波亚像素配准的战场遥感识别仿真[J]. 计算机仿真, 2015, 32(9):1-4.
	LIU Q, YAN Y R, CAO L L. Simulation of battlefield remote sensing identification based on dynamic wavelet sub-pixel registration[J]. Computer Simulation, 2015, 32(9):1-4. (in Chinese)
[32]	李辉, 王凯. 未来城市作战装备保障问题研究[J]. 舰船电子工程, 2022, 42(3):162-165.
	LI H, WANG K. Research on future urban combat equipment support[J]. Ship Electronic Engineering Magazine Agency, 2022, 42(3):162-165. (in Chinese)
[33]	SARA U, AKTER M, UDDIN M S. Image quality assessment through FSIM, SSIM, MSE and PSNR-a comparative study[J]. Journal of Computer and Communications, 2019, 7(3): 8-18.
[34]	XU X G, WANG R X, FU C W, et al. SNR-aware low-light image enhancement[C]// Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 17714-17724.

卷积层	结构	输入通道数	输出通道数	输出大小
Conv1_1	3×3	64	64	246×246
Conv1_2	3×3	128	128	246×246
Conv1_3	3×3	256	256	246×246
Conv1_4	3×3	512	64	246×246
Conv2	1×1	64	64	1×1
Conv3_1	3×3	64	1	246×246
Conv3_2	3×3	1	1	246×246
Conv3_3	3×3	1	64	246×246

卷积层	结构	输入通道数	输出通道数	输出大小
Conv1_1	3×3	64	64	246×246
Conv1_2	3×3	128	128	246×246
Conv1_3	3×3	256	256	246×246
Conv1_4	3×3	512	64	246×246
Conv2	1×1	64	64	1×1
Conv3_1	3×3	64	1	246×246
Conv3_2	3×3	1	1	246×246
Conv3_3	3×3	1	64	246×246

方法	CIEDE2000↓
DCP方法	18.11
CEEF方法	21.59
DehazeNet方法	21.41
RefineDNet方法	17.69
本文方法	17.12

方法	CIEDE2000↓
DCP方法	18.11
CEEF方法	21.59
DehazeNet方法	21.41
RefineDNet方法	17.69
本文方法	17.12

方法	SSIM↑			PSNR↑			MSE↓			SNR↑
方法	outdoor	indoor	synthetic	outdoor	indoor	synthetic	outdoor	indoor	synthetic	outdoor	indoor	synthetic
DCP方法	0.61	0.54	0.77	11.65	12.95	16.65	1708.67	3350.46	1668.58	9.81	5.97	9.98
CEEF方法	0.62	0.52	0.76	14.41	12.80	16.72	1661.07	3475.57	1556.13	9.33	6.90	9.96
DehazeNet方法	0.88	0.53	0.88	22.93	12.86	23.95	416.86	3455.18	300.03	17.53	5.86	18.81
RefineDNet方法	0.92	0.58	0.86	20.93	12.76	20.67	686.45	3507.52	640.92	14.42	6.86	15.53
本文方法	0.90	0.59	0.88	25.15	15.45	25.77	265.84	2974.61	209.19	19.75	7.56	20.90