首页> 外文会议>International Conference on Computer Vision, Image and Deep Learning >Research on Camera Calibration Technology Based on Deep Neural Network in Mine Environment
【24h】

Research on Camera Calibration Technology Based on Deep Neural Network in Mine Environment

机译:基于矿井环境深神经网络的摄像机校准技术研究

获取原文

摘要

achieve the calibration accuracy of the Kinect camera in a complex mine environment, the calibration process was simplified. In this paper, a camera calibration method based on a deep neural network is proposed, which can achieve flexible and high-precision calibration in-plane regions under a complex environment. Without data feature extraction or classification, the deep neural network can be trained quickly and effectively by optimizing network structure, super parameters, and training algorithm. Experimental results show that compared with the Zhang Zhengyou calibration method and shallow neural network calibration method, this method can achieve higher calibration accuracy in a wide range and multi angle shooting.
机译:在复杂的矿井环境中实现了Kinect摄像机的校准精度,简化了校准过程。本文提出了一种基于深神经网络的摄像机校准方法,可以在复杂环境下实现灵活和高精度的校准面内区域。如果没有数据特征提取或分类,通过优化网络结构,超级参数和训练算法,可以快速有效地培训深神经网络。实验结果表明,与张正友校准方法相比和浅神经网络校准方法,这种方法可以在宽范围内实现更高的校准精度和多角度拍摄。

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