首页> 外文会议>International FLINS conference >Safety helmet recognition based on deep convolution neural networks
【24h】

Safety helmet recognition based on deep convolution neural networks

机译:基于深度卷积神经网络的安全帽识别

获取原文

摘要

This paper introduces deep learning for safety helmet recognition. First, a pedestrian detection algorithm based on HOG+SVM is discussed. Then, a safety helmet recognition method based on deep convolution neural networks is presented. Simulation results show that compared with a traditional neural network method, the proposed method improves the automatic recognition accuracy of helmets and shows better adaptability to the environment.
机译:本文介绍了用于安全帽识别的深度学习。首先,讨论了基于HOG + SVM的行人检测算法。然后,提出了一种基于深度卷积神经网络的安全帽识别方法。仿真结果表明,与传统的神经网络方法相比,该方法提高了头盔的自动识别精度,对环境具有更好的适应性。

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