The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.02 - Apr.-June (2014 vol.21)
pp: 32-41
Tao Guan , HuaZhong University of Science and Technology
Yunfeng He , HuaZhong University of Science and Technology
Liya Duan , HuaZhong University of Science and Technology
Jianzhong Yang , HuaZhong University of Science and Technology
Juan Gao , HuaZhong University of Science and Technology
Junqing Yu , HuaZhong University of Science and Technology
ABSTRACT
Existing mobile visual location recognition (MVLR) applications typically rely on bag-of-features (BOF) representation, which shows superior performance in retrieval accuracy. However, although the BOF framework is promising, it is not compact enough for on-device MVLR. The authors have made two contributions to the design of a BOF-based on-device MVLR system. First, to generate BOF descriptors, they propose a memory-efficient approximate nearest-neighbor search algorithm by combining residual vector quantization (RVQ) and tree-structured RVQ (TSRVQ). Second, they implemented a GPS-based and heading-aware RankBoost algorithm to reduce the dimensionality of the BOF descriptors. The authors evaluate the effectiveness of the proposed algorithms on an HTC mobile phone. Their work applies to on-device MVLR in city-scale workspaces.
INDEX TERMS
Data visualization, Mobile communication, Vocabulary, Quantization (signal), Image recognition, Algorithm design and analysis,RankBoost, multimedia, mobile visual location recognition, on-device, bag-of-features
CITATION
Tao Guan, Yunfeng He, Liya Duan, Jianzhong Yang, Juan Gao, Junqing Yu, "Efficient BOF Generation and Compression for On-Device Mobile Visual Location Recognition", IEEE MultiMedia, vol.21, no. 2, pp. 32-41, Apr.-June 2014, doi:10.1109/MMUL.2013.31
34 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool