首页> 外文会议>SPIE Defense + Security Conference >Augmented reality data generation for training deep learning neural network
【24h】

Augmented reality data generation for training deep learning neural network

机译:增强现实数据生成深度学习神经网络

获取原文

摘要

One of the major challenges in deep learning is retrieving sufficiently large labeled training datasets, which can become expensive and time consuming to collect. A unique approach to training segmentation is to use Deep Neural Network (DNN) models with a minimal amount of initial labeled training samples. The procedure involves creating synthetic data and using image registration to calculate affine transformations to apply to the synthetic data. The method takes a small dataset and generates a high-quality augmented reality synthetic dataset with strong variance while maintaining consistency with real cases. Results illustrate segmentation improvements in various target features and increased average target confidence.
机译:深度学习中的主要挑战之一是检索足够大的标记训练数据集,这可能变得昂贵且耗时地收集。训练分割的独特方法是使用具有最小数量的初始标记的训练样本的深神经网络(DNN)模型。该过程涉及创建合成数据并使用图像配准以计算仿射转换以应用于合成数据。该方法采用小型数据集,并生成具有强大方差的高质量增强现实合成数据集,同时保持与实际情况的一致性。结果说明了各种目标特征的分割改进,增加了平均目标置信度。

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