...
首页> 外文期刊>Infrared physics and technology >A rapid and accurate infrared image super-resolution method based on zoom mechanism
【24h】

A rapid and accurate infrared image super-resolution method based on zoom mechanism

机译:基于缩放机制的快速准确的红外图像超分辨率方法

获取原文
获取原文并翻译 | 示例
           

摘要

Highlights?An effective infrared image super resolution method is proposed.?We design a novel network architecture and introduce the zoom mechanism.?The proposed method owns a rapid running speed and can process videos in real-time.?We apply the method from natural images to infrared images by transfer learning.AbstractIn view that the existing methods for infrared image super-resolution could not have good performance both in speed and accuracy simultaneously, with the advantage of deep learning method, this paper presents a rapid and accurate infrared image super-resolution method based on zoom mechanism. In the meantime, we design a novel network architecture. First, we take low-resolution images as network inputs directly, and employ a convolution layer to extract and represent features. Then we introduce the combination of a deconvolution layer and a pooling layer into the network, what we name as zoom mechan
机译:<![cdata [ 亮点 提出了有效的红外图像超分辨率方法。 我们设计一个新颖的网络架构并介绍缩放机制。 所提出的方法拥有快速运行速度,可以实时处理视频。 < CE:标签>? 我们将方法从自然图像应用到红外图像转移学习。 抽象 鉴于现有的红外图像超分辨率的方法同时不能具有良好的性能,同时具有良好的精度,具有深度学习方法的优势,这纸张介绍了基于缩放机制的快速准确的红外图像超分辨率方法。与此同时,我们设计一种新颖的网络架构。首先,我们将低分辨率图像直接拍摄,并使用卷积层来提取和表示功能。然后我们将解卷积层和汇集层的组合介绍到网络中,我们名称为ZOOM机

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号