作战辅助系统中基于深度学习的投影图像颜色补偿方法

doi:10.3969/j.issn.1000-1093.2021.11.015

兵工学报 ›› 2021, Vol. 42 ›› Issue (11): 2418-2423.doi: 10.3969/j.issn.1000-1093.2021.11.015

作战辅助系统中基于深度学习的投影图像颜色补偿方法

张凤^1，2，张超¹，杨华民¹，王发斌^1，2

（1.长春理工大学计算机科学技术学院，吉林长春 130022； 2.吉林师范大学计算机学院，吉林四平 136000）

上线日期:2021-12-27
通讯作者: 张超（1985—），男，讲师，博士 E-mail:zhangchao@cust.edu.cn
作者简介:张凤（1983—），女，博士研究生。E-mail: zhangfeng@jlnu.edu.cn
基金资助:
国家自然科学基金青年科学基金项目（61702051）

Deep Learning-based Color Compensation Method for Projected Images in Combat Assistant System

ZHANG Feng^1，2， ZHANG Chao¹， YANG Huamin¹， WANG Fabin^1，2

(1.College of Computer Science and Technology，Changchun University of Science and Technology，Changchun 130022，Jilin，China；2.College of Computer，Jilin Normal University，Siping 136000，Jilin，China)

Online:2021-12-27

摘要/Abstract

摘要： 为了在复杂环境下实现显示系统的快速布置，提高现代战争中野外指挥系统建立的机动性，提出一种基于深度学习的投影图像颜色补偿方法，实现大规模数据在任意复杂颜色平面的可视化显示。该方法利用端到端的深度学习网络，基于一个模型和一个目标函数，规避了深度学习中多模块固有的缺陷；通过增加CompenNet网络层数，增加训练模型中图像特征的提取数量；采用改进的损失函数SSIM+Smooth L1计算图像相似度，增强损失函数的鲁棒性和稳定性，同时加快网络的收敛速度。实验结果显示，改进的CompenNet网络在相同24个数据集上训练迭代1 000次后，生成的图像峰值信噪比平均值提高5.54%，结构相似性平均值提高0.14%，均方根误差平均值降低0.14%，人眼主观感知投影效果也表现得更好。

关键词: 投影图像, 颜色补偿, 深度学习, 作战辅助系统

Abstract: A deep learning-based color compensation method for projected images is proposed to realize the visual display of large-scale data in arbitrary complex color plane.The proposed method is aimed to realize the rapid deployment of display system in complex environment and improve the mobility of field command system in modern war. The method is used to avoid the inherent defects of multiple modules in deep learning based on an end-to-end deep learning network，a model and an objective function. The number of image features extracted from the training model is increased by deepening the layers of CompenNet. The improved loss function SSIM+Smooth L1 is used to calculate image similarity，which enhances the robustness and stability of the loss function while speeding up the convergence of the network. The experimental results show that the PSNR and SSIM average values of the images generated by the improved CompenNet after 1 000 training iterations on the same 24 data sets are increased by 5.54% and 0.14%, respectively，the RMSE average value is decreased by 0.14%, and the subjective perception projection effect of human eyes is also better.

Key words: projectedimage, colorcompensation, deeplearning, combatassistantsystem

中图分类号:

TP391.41

张凤, 张超, 杨华民, 王发斌. 作战辅助系统中基于深度学习的投影图像颜色补偿方法[J]. 兵工学报, 2021, 42(11): 2418-2423.

ZHANG Feng, ZHANG Chao, YANG Huamin, WANG Fabin. Deep Learning-based Color Compensation Method for Projected Images in Combat Assistant System[J]. Acta Armamentarii, 2021, 42(11): 2418-2423.

参考文献

［1］ GRUNDHFER A.Practical non-linear photometric projector compensation[C]∥Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Portland，OR，US:IEEE，2013:924-929.
[2］ HUANG T H，WANG T C，CHEN H H.Radiometric compensation of images projected on non-white surfaces by exploiting chromatic adaptation and perceptual anchoring[J].IEEE Transactions on Image Processing，2016，26(1):147-159.
[3］ COSTA P，GALDRAN A，MEYER M I，et al.End-to-end adversarial retinal image synthesis[J].IEEE Transactions on Medical Imaging，2018，37(3):781-791.
[4］ TAN J X，GAO Y F,LIANG Z R，et al.3D-GLCM CNN:A 3-dimensional gray-level co-occurrence matrix-based CNN model for polyp classification via CT colonography[J].IEEE Transactions on Medical Imaging，2020，39(6):2013-2024.
[5］ LI Y S，ZHANG Y J，HUANG X，et al.Learning source-invariant deep hashing convolutional neural networks for cross-source remote sensing image retrieval[J].IEEE Transactions on Geoscience and Remote Sensing，2018，56(11):6521-6536.
[6］ EL MALLAHI M，ZOUHRI A，QJIDAA H.Radial meixner moment invariants for 2D and 3D image recognition[J].Pattern Recognition and Image Analysis，2018，28(2):207-216.
[7］李响，苏娟，杨龙.基于改进YOLOv3的合成孔径雷达图像中建筑物检测算法[J].兵工学报，2020，41(7):1347-1359.
LI X，SU J，YANG L.A SAR building detection algorithm based on improved YOLOv3[J].Acta Armamentarii，2020，41(7):1347-1359.(in Chinese)
[8］梁杰，李磊，任君，等.基于深度学习的红外图像遮挡干扰检测方法[J].兵工学报，2019，40(7):1401-1410.
LIANG J，LI L，REN J，et al.Infrared image occlusion interference detection method based on deep learning[J].Acta Armamentarii，2019，40(7):1401-1410.(in Chinese)
[9］余跃，王宏伦.基于深度学习的高超声速飞行器再入预测校正容错制导[J].兵工学报，2020，41(4):656-669.
YU Y，WANG H L.Deep learning-based reentry predictor-corrector fault-tolerant guidance for hypersonic vehicles[J]. Acta Armamentarii，2020，41(4):656-669.(in Chinese)
[10］温豪，孟召宗，高楠，等.多光通道条纹投影系统误差测量与补偿[J].光子学报，2020，49(7):712004.
WEN H，MENG Z Z，GAO N，et al.Error measurement and compensation of multi-light channel stripe projection system[J].Acta Photonica Sinica，2020，49(7):712004.(in Chinese)
[11］ ISOLA P，ZHU J Y，ZHOU T H，et al.Image-to-image translation with conditional adversarial networks[C]∥Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu, HI，US:IEEE Computer Society Press，2017.
[12］杜振龙，沈海洋，宋国美，等.基于改进CycleGAN的图像风格迁移[J].光学精密工程，2019，27(8):1836-1844.
DU Z L，SHEN H Y，SONG G M，et al.Image style transfer based on improved CycleGAN[J].Optical Precision Engineering，2019，27(8):1836-1844. (in Chinese)
[13］ HUANG B Y，LING H B.End-to-end projector photometric compensation[C]∥Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach，CA，US：IEEE，2019.
[14］ GIRSHICK R.Fast R-CNN[C]∥Proceedings of 2015 IEEE International Conferenceon Computer Vision.Santiago，Chile：IEEE，2015.
[15］ KINGMA D P，BA J L.Adam: amethod for stochastic optimization[C]∥Proceedings of the 3rd International Conference on Learning Representations.San Diego，CA，US:the Computational and Biological Learning Society，2015.
[16］ HE K M，ZHANG X Y，REN S Q，et al.Delving deep into rectifiers: surpassing human-level performance on ImageNet classification[C]∥Proceedings of 2015 IEEE International Conference on Computer Vision.Santiago，Chile:IEEE，2015.

[1]	李良福，陈卫东，高强，许开銮，刘轩，何曦，钱钧. 基于深度学习的光电系统智能目标识别[J]. 兵工学报, 2022, 43(S1): 162-168.
[2]	李锦青，刘泽飞，满振龙. 基于生成对抗网络的密钥生成方法及其在微光图像加密中的应用[J]. 兵工学报, 2022, 43(2): 337-344.
[3]	普运伟，刘涛涛，郭江，吴海潇. 基于卷积神经网络和模糊函数主脊坐标变换的雷达辐射源信号识别[J]. 兵工学报, 2021, 42(8): 1680-1689.
[4]	朱敏，许爱强，许晴，李睿峰. 基于改进多层核超限学习机的模拟电路故障诊断[J]. 兵工学报, 2021, 42(2): 356-369.
[5]	薛灵芝, 曾向阳, 杨爽. 基于生成对抗网络的水声目标识别算法[J]. 兵工学报, 2021, 42(11): 2444-2452.
[6]	余跃，王宏伦. 基于深度学习的高超声速飞行器再入预测校正容错制导[J]. 兵工学报, 2020, 41(4): 656-669.
[7]	闫孟达，杨任农，左家亮，胡东愿，岳龙飞，赵雨. 基于深度学习的空空导弹多类攻击区实时解算[J]. 兵工学报, 2020, 41(12): 2466-2477.
[8]	梁杰，任君，李磊，齐航，周红丽. 基于典型几何形状精确回归的机场跑道检测方法[J]. 兵工学报, 2020, 41(10): 2045-2054.
[9]	余永维，彭西，杜柳青，陈天皓. 基于深度学习框架的装配机器人零件实时检测方法[J]. 兵工学报, 2020, 41(10): 2122-2130.

作战辅助系统中基于深度学习的投影图像颜色补偿方法

Deep Learning-based Color Compensation Method for Projected Images in Combat Assistant System

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价