首页> 外国专利> Deep learning training method and system using infrared image

Deep learning training method and system using infrared image

机译:使用红外图像的深度学习训练方法和系统

摘要

In the deep learning learning method using an infrared image, the step of designating a threshold value for all pixel values based on all pixel values of an infrared image in which an object and a background are displayed, exceeding the threshold value among all pixel values to distinguish between the object and the background Generating a pre-processed image obtained by adjusting pixel values to a first pixel value, and adjusting pixel values below a threshold to a second pixel value different from the first pixel value, combining the pre-processed image and the infrared image to generate training data The step and training data may be used as input data to train a deep learning model.
机译:在使用红外图像的深度学习学习方法中,基于显示对象和背景的红外图像的所有像素值来指定所有像素值的阈值的步骤,超过所有像素值之间的阈值区分通过将像素值调整为第一像素值而获得的预处理图像,以及将低于阈值的像素值调整到与第一像素值不同的第二像素值,组合预处理图像和用于生成训练数据的红外图像可以用作培训深度学习模型的输入数据。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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