Query Adaptive Similarity Measure for RGB-D Object Recognition

Yanhua Cheng, Rui Cai, Chi Zhang, Zhiwei Li, Xin Zhao, Kaiqi Huang, Y. Rui
{"title":"Query Adaptive Similarity Measure for RGB-D Object Recognition","authors":"Yanhua Cheng, Rui Cai, Chi Zhang, Zhiwei Li, Xin Zhao, Kaiqi Huang, Y. Rui","doi":"10.1109/ICCV.2015.25","DOIUrl":null,"url":null,"abstract":"This paper studies the problem of improving the top-1 accuracy of RGB-D object recognition. Despite of the impressive top-5 accuracies achieved by existing methods, their top-1 accuracies are not very satisfactory. The reasons are in two-fold: (1) existing similarity measures are sensitive to object pose and scale changes, as well as intra-class variations, and (2) effectively fusing RGB and depth cues is still an open problem. To address these problems, this paper first proposes a new similarity measure based on dense matching, through which objects in comparison are warped and aligned, to better tolerate variations. Towards RGB and depth fusion, we argue that a constant and golden weight doesn't exist. The two modalities have varying contributions when comparing objects from different categories. To capture such a dynamic characteristic, a group of matchers equipped with various fusion weights is constructed, to explore the responses of dense matching under different fusion configurations. All the response scores are finally merged following a learning-to-combination way, which provides quite good generalization ability in practice. The proposed approach win the best results on several public benchmarks, e.g., achieves 92.7% top-1 test accuracy on the Washington RGB-D object dataset, with a 5.1% improvement over the state-of-the-art.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"12 1","pages":"145-153"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE International Conference on Computer Vision (ICCV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2015.25","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12

Abstract

This paper studies the problem of improving the top-1 accuracy of RGB-D object recognition. Despite of the impressive top-5 accuracies achieved by existing methods, their top-1 accuracies are not very satisfactory. The reasons are in two-fold: (1) existing similarity measures are sensitive to object pose and scale changes, as well as intra-class variations, and (2) effectively fusing RGB and depth cues is still an open problem. To address these problems, this paper first proposes a new similarity measure based on dense matching, through which objects in comparison are warped and aligned, to better tolerate variations. Towards RGB and depth fusion, we argue that a constant and golden weight doesn't exist. The two modalities have varying contributions when comparing objects from different categories. To capture such a dynamic characteristic, a group of matchers equipped with various fusion weights is constructed, to explore the responses of dense matching under different fusion configurations. All the response scores are finally merged following a learning-to-combination way, which provides quite good generalization ability in practice. The proposed approach win the best results on several public benchmarks, e.g., achieves 92.7% top-1 test accuracy on the Washington RGB-D object dataset, with a 5.1% improvement over the state-of-the-art.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
RGB-D对象识别的查询自适应相似度度量
本文研究了提高RGB-D目标识别的top-1精度的问题。尽管现有方法取得了令人印象深刻的前5名精度,但它们的前1名精度并不十分令人满意。原因有两方面:(1)现有的相似性度量对物体姿态和尺度变化以及类内变化敏感;(2)有效融合RGB和深度线索仍然是一个悬而未决的问题。为了解决这些问题,本文首先提出了一种基于密集匹配的相似性度量方法,通过对比较对象进行扭曲和对齐,以更好地容忍变化。对于RGB和深度融合,我们认为不存在恒定的黄金权重。当比较来自不同类别的对象时,这两种模式有不同的贡献。为了捕捉这一动态特性,构建了一组配备不同融合权值的匹配器,探索不同融合配置下密集匹配的响应。所有的回答分数最终按照学习到组合的方式进行合并,在实践中具有很好的泛化能力。所提出的方法在几个公共基准测试中获得了最佳结果,例如,在华盛顿RGB-D对象数据集上达到了92.7%的top-1测试精度,比最先进的方法提高了5.1%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Listening with Your Eyes: Towards a Practical Visual Speech Recognition System Using Deep Boltzmann Machines Self-Calibration of Optical Lenses Single Image Pop-Up from Discriminatively Learned Parts Multi-task Recurrent Neural Network for Immediacy Prediction Low-Rank Tensor Approximation with Laplacian Scale Mixture Modeling for Multiframe Image Denoising
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1