基于SqueezeNet的轻量级图像融合方法

doi:10.11772/j.issn.1001-9081.2019081378

计算机应用 ›› 2020, Vol. 40 ›› Issue (3): 837-841.DOI: 10.11772/j.issn.1001-9081.2019081378

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于SqueezeNet的轻量级图像融合方法

王继霄, 李阳, 王家宝, 苗壮, 张洋硕

陆军工程大学指挥控制工程学院, 南京 210007

收稿日期:2019-08-08 修回日期:2019-10-30 出版日期:2020-03-10 发布日期:2019-11-18
通讯作者: 苗壮
作者简介:王继霄(1992-),男,云南曲靖人,硕士研究生,主要研究方向:机器视觉、机器学习;李阳(1984-),男,河北廊坊人,讲师,博士,主要研究方向:机器视觉、机器学习;王家宝(1985-),男,安徽肥西人,讲师,博士,主要研究方向:模式识别、图像检索;苗壮(1976-),男,辽宁辽阳人,副教授,博士,主要研究方向:人工智能;张洋硕(1995-),男,河南三门峡人,硕士研究生,主要研究方向:计算机视觉、目标检测。

Light-weight image fusion method based on SqueezeNet

WANG Jixiao, LI Yang, WANG Jiabao, MIAO Zhuang, ZHANG Yangshuo

College of Command and Control Engineering, Army Engineering University, Nanjing Jiangsu 210007, China

Received:2019-08-08 Revised:2019-10-30 Online:2020-03-10 Published:2019-11-18
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61806220).

摘要/Abstract

摘要： 现有深度红外和可见光图像融合模型网络参数多，计算过程需要耗费大量计算资源和内存，难以满足移动和嵌入式设备上的部署要求。针对上述问题，提出了一种基于SqueezeNet的轻量级图像融合方法，该方法利用轻量级网络SqueezeNet提取红外和可见光图像特征，并通过该网络提取的特征获得权重图并进行加权融合，进而获得最后的融合图像。通过与ResNet50方法进行比较发现，该方法在保持融合图像质量相近的情况下，模型大小和网络参数量分别被压缩为ResNet50方法的1/21和1/204，运行速度加快了4倍。实验结果表明，该方法不仅降低了融合模型的大小，加快了图像融合速度，同时得到了比其他传统融合方法更好的融合效果。

关键词: 图像融合, 深度学习, 轻量级, SqueezeNet

Abstract: The existing deep learning based infrared and visible image fusion methods have too many parameters and require large amounts of computing resources and memory. These methods cannot meet the deployment demand of resource constrained edge devices such as cell phones and embedded devices. In order to address these problems, a light-weight image fusion method based on SqueezeNet was proposed. SqueezeNet was used to extract image features, then the weight map was obtained by these features, and the weighted fusion was performed, finally the fused image was generated. By comparing with the ResNet50 method, it is found that the proposed method compresses the model size and network parameter amount to 1/21 and 1/204 respectively, and improves the running speed to 5 times while maintaining the quality of fused images. The experimental results demonstrate that the proposed method has better fusion effect compared to existing traditional methods as well as reduces the size of fusion model and accelerates the fusion speed.

Key words: image fusion, deep learning, light-weight, SqueezeNet

中图分类号:

TP391.4

王继霄, 李阳, 王家宝, 苗壮, 张洋硕. 基于SqueezeNet的轻量级图像融合方法[J]. 计算机应用, 2020, 40(3): 837-841.

WANG Jixiao, LI Yang, WANG Jiabao, MIAO Zhuang, ZHANG Yangshuo. Light-weight image fusion method based on SqueezeNet[J]. Journal of Computer Applications, 2020, 40(3): 837-841.

参考文献

[1] LI H,WU X,KITTLER J. Infrared and visible image fusion using a deep learning framework[C]//Proceedings of the 24th International Conference on Pattern Recognition. Piscataway:IEEE,2018:2705-2710.
[2] LIU Y,CHEN X,WARD R K,et al. Image fusion with convolutional sparse representation[J]. IEEE Signal Processing Letters, 2016,23(12):1882-1886.
[3] LI H,WU X. DenseFuse:a fusion approach to infrared and visible images[J]. IEEE Transactions on Image Processing,2019,28(5):2614-2623.
[4] LI H,WU X,DURRANI T S. Infrared and visible image fusion with ResNet and zero-phase component analysis[EB/OL].[2019-4-13]. https://arxiv.org/pdf/1806.07119.pdf.
[5] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards realtime object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[6] SANDLER M,HOWARD A,ZHU M,et al. MobileNetV2:inverted residuals and linear bottlenecks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:4510-4520.
[7] ZHANG X,ZHOU X,LIN M,et al. ShuffleNet:an extremely efficient convolutional neural network for mobile devices[EB/OL].[2019-02-15]. https://arxiv.org/pdf/1707.01083.pdf.
[8] IANDOLA F N,HAN S,MOSKEWICZ M W,et al. SqueezeNet:AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size[EB/OL].[2018-11-13]. https://arxiv.org/pdf/1602.07360.pdf.
[9] KUMAR B K S. Image fusion based on pixel significance using cross bilateral filter[J]. Signal,Image and Video Processing, 2015,9(5):1193-1204.
[10] KUMAR B K S. Multifocus and multispectral image fusion based on pixel significance using discrete cosine harmonic wavelet transform[J]. Signal,Image and Video Processing,2013,7(6):1125-1143.
[11] ZHANG Q,FU Y,LI H,et al. Dictionary learning method for joint sparse representation-based image fusion[J]. Optical Engineering,2013,52(5):No. 057006.
[12] LIU C,QI Y,DING W. Infrared and visible image fusion method based on saliency detection in sparse domain[J]. Infrared Physics and Technology,2017,83:94-102.
[13] MA J,ZHOU Z,WANG B,et al. Infrared and visible image fusion based on visual saliency map and weighted least square optimization[J]. Infrared Physics and Technology,2017,82:8-17.
[14] MA J,CHEN C,LI C,et al. Infrared and visible image fusion via gradient transfer and total variation minimization[J]. Information Fusion,2016,31:100-109.
[15] LIU Y,CHEN X,PENG H,et al. Multi-focus image fusion with a deep convolutional neural network[J]. Information Fusion,2017, 36:191-207.
[16] KRIZHEVSKY A,SUTSKEVER I,HINTON G. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. New York:Curran Associates Inc.,2012:1097-1105.
[17] SAINATH T N,KINGSBURY B,SAON G,et al. Deep convolutional neural networks for large-scale speech tasks[J]. Neural Networks,2015,64:39-48.
[18] TOET A. TNO image fusion dataset[EB/OL].[2018-12-10]. https://figshare.com/articles/TN Image Fusion Dataset/1008029.
[19] HAGHIGHAT M,RAZIAN M A. Fast-FMI:non-reference image fusion metric[C]//Proceedings of the IEEE 8th International Conference on Application of Information and Communication Technologies. Piscataway:IEEE,2014:1-3.
[20] PRABHAKAR K R,SRIKAR V S,BABU R V. DeepFuse:a deep unsupervised approach for exposure fusion with extreme exposure image pairs[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE,2017:4724-4732.

基于SqueezeNet的轻量级图像融合方法

Light-weight image fusion method based on SqueezeNet

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

[1]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[3]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[4]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[5]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[8]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[9]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[10]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[11]	李亚芳, 梁烨, 冯韦玮, 祖宝开, 康玉健. 基于社区优化的深度网络嵌入方法[J]. 计算机应用, 2021, 41(7): 1956-1963.
[12]	张林发, 张榆锋, 王琨, 李支尧. 基于直觉模糊集和亮度增强的医学图像融合[J]. 计算机应用, 2021, 41(7): 2082-2091.
[13]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[14]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[15]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.