摘要
海量图像检索算法的核心问题是如何对特征进行有效的编码以及快速的检索.局部集聚向量描述(Vector of locally aggregated descriptors,VLAD)算法因其精确的编码方式以及较低的特征维度,取得了良好的检索性能.然而VLAD算法在编码过程中并没有考虑到局部特征的角度信息,VLAD编码向量维度依然较高,无法支持实时的海量图像检索.本文提出一种在VLAD编码框架中融合重力信息的角度编码方法以及适用于海量图像的角度乘积量化快速检索方法.在特征编码阶段,利用前端移动设备采集的重力信息实现融合特征角度的特征编码方法.在最近邻检索阶段将角度分区与乘积量化子分区相结合,采用改进的角度乘积量化进行快速近似最近邻检索.另外本文提出的基于角度编码的图像检索算法可适用于主流的词袋模型及其变种算法等框架.在GPS及重力信息标注的北京地标建筑(Beijing landmark)数据库、Holidays数据库以及SUN397数据库中进行测试,实验结果表明本文算法能够充分利用匹配特征在描述符以及几何空间的相似性,相比传统的VLAD以及协变局部集聚向量描述符(Covariant vector of locally aggregated descriptors,CVLAD)算法精度有明显提升.
Large scale image retrieval has focused on effective feature coding and efficient searching. Vector of locally aggregated descriptors（VLAD） has achieved great retrieval performance as with its exact coding method and relatively low dimension. However, orientation information of features is ignored in coding step and feature dimension is not suitable for large scale image retrieval. In this paper, a gravity-aware oriented coding and oriented product quantization method based on traditional VLAD framework is proposed, which is efficient and effective. In feature coding step, gravity sensors built-in the mobile devices can be used for feature coding as with orientation information. In vector indexing step,oriented product quantization which combines orientation bins and product quantization bins is used for approximate nearest neighborhood search. Our method can be adapted to any popular retrieval frameworks, including bag-of-words and its variants. Experimental results on collected GPS and gravity-tagged Beijing landmark dataset, Holidays dataset and SUN397 dataset demonstrate that the approach can make full use of the similarity of matching pairs in descriptor space as well as in geometric space and improve the mobile visual search accuracy a lot when compared with VLAD and CVLAD.
作者
张运超
陈靖
王涌天
ZHANG Yun-Chao CHEN Jing WANG Yong-Tian(School of Computer Science and Technology, Beijing Insti- tute of Technology, Beijing 100081 School of Optics and Electronics, Beijing Institute of Technology, Beijing 100081)
出处
《自动化学报》
EI
CSCD
北大核心
2016年第10期1501-1511,共11页
Acta Automatica Sinica
基金
国家高技术研究发展计划(863计划)(2013AA013802)
国家自然科学基金(61271375)资助~~
关键词
海量图像检索
重力信息
角度编码
角度乘积量化
Large scale image retrieval
gravity information
oriented coding
oriented product quantization
