邢志勇,肖儿良.多网络联合的红外与可见光图像融合算法研究[J].包装工程,2019,40(23):251-257.
XING Zhi-yong,XIAO Er-liang.Multi-network Joint Infrared and Visible Image Fusion Algorithm[J].Packaging Engineering,2019,40(23):251-257. |
| 多网络联合的红外与可见光图像融合算法研究 |
| Multi-network Joint Infrared and Visible Image Fusion Algorithm |
| 投稿时间：2019-06-14 修订日期：2019-12-10 |
| DOI：10.19554/j.cnki.1001-3563.2019.23.037 |
| 中文关键词: 图像融合 密集残差网络 生成对抗网络（GAN） 融合策略 |
| 英文关键词: image fusion dense residual network generative adversarial networks (GAN) fusion strategy |
| 基金项目: |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 针对红外与可见光图像在融合过程中，融合图像失真以及可见光图像信息融合不足的问题，提出一种联合多网络结构的红外与可见光图像融合算法。方法 首先采用基于密集残差连接的编码器对输入的红外与可见光图像进行特征提取，然后利用融合策略对得到的特征图进行融合，最后将融合后的特征图送入基于GAN网络的解码器中。结果 通过与可见光图像对抗优化训练，使得融合后的图像保留了更多可见光图像的细节、背景信息，增强了图像的视觉效果。结论 实验表明，与现有的融合算法相比，该算法达到了更好的实验效果，在主观感知和客观评价上都具有更好的表现力。 |
| 英文摘要: |
| The work aims to propose a multi-network joint infrared and visible image fusion algorithm, for the purpose of solving the problem of fusion image distortion and insufficient fusion of visible light image information in the fusion process of infrared and visible light images. Firstly, the inputted infrared and visible images were extracted by the encoder based on dense residual connection. Then, the fusion strategy was used to fuse the obtained feature map. Finally, the fused feature map was sent to the decoder based on GAN network. By optimizing the adversarial training with the visible light image, the fused image retained more details and background information of the visible image, and enhanced the visual effect of the image. Experiments show that, compared with the existing fusion algorithm, the proposed algorithm achieves better experimental results and has better expressiveness in subjective perception and objective evaluation. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
渝公网安备 50010702501716号