首页> 外国专利> Deep learning and image processing based bolt loosening detection method

Deep learning and image processing based bolt loosening detection method

机译:基于深度学习和图像处理的螺栓松动检测方法

摘要

The present invention relates to a method for detecting bolt loosening based on deep learning and image processing, comprising: detecting a bolt image from image data using RCNN; Through the image processing technique from the detected bolt image, the initial loosening of the bolt can be detected more accurately through the configuration including the step of estimating the bolt loosening angle, the bolt image is detected from the image data through the learning algorithm, and the image processing technique is applied. It relates to a deep learning and image processing-based bolt loosening detection method that can correct perspective distortion and estimate the bolt loosening angle.
机译:本发明涉及一种基于深度学习和图像处理来检测螺栓松动的方法,包括:使用RCNN检测来自图像数据的螺栓图像; 通过从检测到的螺栓图像中的图像处理技术,可以通过包括估计螺栓松动角度的步骤的配置更精确地检测螺栓的初始松动,通过学习算法从图像数据中检测到螺栓图像, 应用图像处理技术。 它涉及一种基于深度学习和图像处理的螺栓松开检测方法,可以校正透视变形并估计螺栓松动角度。

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