首页> 外文会议>International Conference on Computer Vision Theory and Applications >Learning Visual Odometry with a Convolutional Network
【24h】

Learning Visual Odometry with a Convolutional Network

机译:使用卷积网络学习视觉径管

获取原文

摘要

We present an approach to predicting velocity and direction changes from visual information ("visual odometry") using an end-to-end, deep learning-based architecture. The architecture uses a single type of computational module and learning rule to extract visual motion, depth, and finally odometry information from the raw data. Representations of depth and motion are extracted by detecting synchrony across time and stereo channels using network layers with multiplicative interactions. The extracted representations are turned into information about changes in velocity and direction using a convolutional neural network. Preliminary results show that the architecture is capable of learning the resulting mapping from video to egomotion.
机译:我们使用端到端的深度学习的架构来提出一种预测速度和方向改变的方法,从视觉信息(“视觉内径”)。该架构使用单一类型的计算模块和学习规则来提取来自原始数据的视觉运动,深度和最终的OCOMORY信息。通过使用具有乘法交互的网络层检测时间和立体声通道的同步来提取深度和运动的表示。将提取的表示转化为使用卷积神经网络的速度和方向变化的信息。初步结果表明,该架构能够从视频到象征的结果映射。

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