...
首页> 外文期刊>IEEE Transactions on Robotics >Exploiting Object Similarity for Robotic Visual Recognition
【24h】

Exploiting Object Similarity for Robotic Visual Recognition

机译:利用机器人视觉识别的对象相似性

获取原文
获取原文并翻译 | 示例
           

摘要

In this article, we are interested in robotic visual object classification using a deep convolutional neural network (DCNN) classifier. We show that the correlation coefficient of the automatically learned DCNN features of two object images carries robust information on their similarity, and can be utilized to significantly improve the robot's classification accuracy, without additional training. More specifically, we first probabilistically analyze how the feature correlation carries vital similarity information and build a correlation-based Markov random field (CoMRF) for joint object labeling. Given query and motion budgets, we then propose an optimization framework to plan the robot's query and path based on our CoMRF. This gives the robot a new way to optimally decide which object sites to move close to for better sensing and for which objects to ask a remote human for help with classification, which considerably improves the overall classification. We extensively evaluate our proposed approach on two large datasets (e.g., drone imagery and indoor scenes) and several real-world robotic experiments. The results show that our proposed approach significantly outperforms the benchmarks.
机译:在本文中,我们对使用深卷积神经网络(DCNN)分类器的机器人视觉对象分类感兴趣。我们表明,两个对象图像的自动学习DCNN特征的相关系数携带有关它们的相似性的强大信息,并且可以利用来显着提高机器人的分类精度,而无需额外的训练。更具体地,我们首先概率分析特征相关性如何携带重要的相似性信息并构建基于相关的马尔可夫随机字段(ComRF),用于联合对象标记。给定查询和运动预算,我们提出了一个优化框架,以规划基于我们的COMRF的机器人的查询和路径。这使得机器人成为最佳地决定哪些对象站点移动的新方法,以便更好地感测,并为哪些对象询问远程人类帮助分类,这显着提高了整体分类。我们广泛地评估了我们在两个大型数据集(例如,无人机图像和室内场景)和几个真实世界机器人实验中的提出方法。结果表明,我们的建议方法显着优于基准。

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