首页> 外文会议>AAAI Symposium on Qualitative Representations for Robots >Towards a Similarity between Qualitative Image Descriptions for Comparing Real Scenes
【24h】

Towards a Similarity between Qualitative Image Descriptions for Comparing Real Scenes

机译:朝着比较真实场景的定性图像描述之间的相似性

获取原文

摘要

In this paper, qualitative descriptors of shape, color, topology and location are applied to describe images of real scenes. Then, an approach for obtaining a similarity measure between two qualitative image descriptions (SimQID) is presented. As a proof-of-concept, this approach is tested on real digital images taken by a robot camera at the corridors of TI building at Universitat Jaume I. The results obtained are analyzed and a discussion is provided.
机译:在本文中,应用了形状,颜色,拓扑和地点的定性描述符来描述真实场景的图像。然后,呈现了一种用于获得两个定性图像描述(SIMQID)之间获得相似性度量的方法。作为概念验证,该方法在TI大楼的TI大楼的走廊拍摄的真实数字图像上进行测试,在Wearsitat Jaume I.分析所获得的结果并提供讨论。

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