期刊
IEEE ACCESS
卷 9, 期 -, 页码 103627-103636出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3093462
关键词
Feature extraction; Visualization; Databases; Image recognition; Image databases; Crowdsourcing; Smart phones; Crowdsourcing; rich information; deep hash feature; common crucial feature
资金
- Scientific and Technological Project in Henan Province [212102210384]
- Key Scientific Research Project of Colleges and Universities in Henan Province [21A520031]
- Nanyang Institute of Technology through the Interdisciplinary Sciences Project [520019]
- Scientific and Technological Project in Nanyang City [KJGG007]
- Education and Teaching Reform Project [NIT2020JY-077]
Crowdsourcing offers an effective way to build a location recognition image database, with rich information but susceptible to disturbances. To address this, a RCCF detection framework and VHB scheme were proposed, along with deep feature extraction, leading to superior performance compared to other state-of-the-art schemes.
Crowdsourcing provides an effective way to construct a location recognition image database. Comparing with traditional location image database construction, crowdsourced image database has massive advantages, e.g., much richer information for location, with various angles, timestamps, distances and weather information, providing useful potential for high recognition precision. However, when capturing the crowdsourced images, it is inevitable to have various disturbances on these location images, for example, moving vehicles and pedestrians, hindering the realization of potential. To address this challenge, we first propose a Rich Common Crucial Feature (RCCF) detection framework to exclude unimportant visual SURF features from crucial features. To achieve a good balance between the efficiency and accuracy, we further propose an RCCF based Visual Hash Bits (VHB) scheme to encode RCCF features into hash bits to vote for most matching images. Furthermore, deep feature extraction is also utilized with visual search architecture MobileNet. Extensive experiments are conducted on a crowdsourced dataset with 9,064 location images, demonstrating that our scheme outperforms other state-of-the-art schemes.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据