• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE Sensors Applications Symposium >An RGB/Infra-Red camera fusion approach for Multi-Person Pose Estimation in low light environments
【24h】

An RGB/Infra-Red camera fusion approach for Multi-Person Pose Estimation in low light environments

机译：用于弱光环境下多人位姿估计的RGB /红外相机融合方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Enabling collaborative robots to predict the human pose is a challenging, but important issue to address. Most of the development of human pose estimation (HPE) adopt RGB images as input to estimate anatomical keypoints with Deep Convolutional Neural Networks (DNNs). However, those approaches neglect the challenge of detecting features reliably during night-time or in difficult lighting conditions, leading to safety issues. In response to this limitation, we present in this paper an RGB/Infra-Red camera fusion approach, based on the open-source library OpenPose, and we show how the fusion of keypoints extracted from different images can be used to improve the human pose estimation performance in sparse light environments. Specifically, OpenPose is used to extract body joints from RGB and Infra-Red images and the contribution of each frame is combined by a fusion step. We investigate the potential of a fusion framework based on Deep Neural Networks and we compare it to a linear weighted average method. The proposed approach shows promising performances, with the best result outperforming conventional methods by a factor 1.8x on a custom data set of Infra-Red and RGB images captured in poor light conditions, where it is hard to recognize people even by human inspection.
机译：使协作机器人能够预测人体姿势是一个具有挑战性但要解决的重要问题。人体姿态估计（HPE）的大多数开发都采用RGB图像作为输入，以通过深度卷积神经网络（DNN）估计解剖学关键点。然而，这些方法忽略了在夜间或在困难的照明条件下可靠地检测特征的挑战，从而导致安全问题。针对这种局限性，我们在本文中提出了一种基于开源库OpenPose的RGB /红外照相机融合方法，并且我们展示了如何将从不同图像中提取的关键点融合来改善人体姿势稀疏光环境下的估计性能。具体来说，OpenPose用于从RGB和红外图像中提取人体关节，并通过融合步骤组合每个帧的贡献。我们研究了基于深度神经网络的融合框架的潜力，并将其与线性加权平均法进行了比较。所提出的方法显示出令人鼓舞的性能，在光线较弱的条件下捕获的红外和RGB图像的自定义数据集上，即使通过人工检查也很难认出人，最佳结果的性能要比传统方法高1.8倍。

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