...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Foreground Detection for Infrared Videos With Multiscale 3-D Fully Convolutional Network
【24h】

Foreground Detection for Infrared Videos With Multiscale 3-D Fully Convolutional Network

机译：多尺度3-D全卷积网络的红外视频前景检测

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Foreground detection for infrared (IR) videos is an important and fundamental problem in many applications, e.g., IR surveillance, IR object tracking, and so on. Conventional foreground detection algorithms developed for visible videos do not focus on the problems for IR videos, e.g., low contrast, coarse texture, lack of color information, and so on. Recent foreground detection methods based on deep neural network (DNN) demonstrated significant improvement, but mast of them still use only spatial features, which is less obvious in IR images. In this letter, we add deeply learned multiscale temporal features to improve the performance of background subtraction for IR videos. We propose a novel multiscale 3-D fully convolutional network (MFC3-D) to establish a mapping from image sequences to pixelwise classification results and to learn deep and hierarchical multiscale spatial-temporal features of the input images sequence. The experimental results show that the MFC3-D can learn spatial-temporal features effectively and achieved state-ofthe-art results on the test data set, comparing to other DNN-based methods and traditional background subtraction methods.
机译：红外（IR）视频的前景检测是许多应用程序中重要且基本的问题，例如IR监视，IR对象跟踪等。针对可见视频开发的常规前景检测算法不关注IR视频的问题，例如，低对比度，粗糙的纹理，缺乏颜色信息等。最近基于深度神经网络（DNN）的前景检测方法显示出显着的改进，但其中的桅杆仍仅使用空间特征，在红外图像中不太明显。在这封信中，我们添加了深入学习的多尺度时间特征，以提高IR视频背景扣除的性能。我们提出了一种新颖的多尺度3-D全卷积网络（MFC3-D），以建立从图像序列到像素分类结果的映射，并学习输入图像序列的深层次分层多尺度时空特征。实验结果表明，与其他基于DNN的方法和传统的背景扣除方法相比，MFC3-D可以有效地学习时空特征，并在测试数据集上获得了最新的结果。

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