Limits...
On-device mobile visual location recognition by using panoramic images and compressed sensing based visual descriptors.

Guan T, Fan Y, Duan L, Yu J - PLoS ONE (2014)

Bottom Line: Secondly, to search high dimensional visual descriptors directly on mobile devices, we propose an effective bilinear compressed sensing based encoding method.While being fast and accurate enough for on-device implementation, our algorithm can also reduce the memory usage of projection matrix significantly.Experimental results prove the effectiveness of the proposed methods for on-device MVLR applications.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Technology, Huazhong University of Science & Technology, Wuhan, People's Republic of China.

ABSTRACT
Mobile Visual Location Recognition (MVLR) has attracted a lot of researchers' attention in the past few years. Existing MVLR applications commonly use Query-by-Example (QBE) based image retrieval principle to fulfill the location recognition task. However, the QBE framework is not reliable enough due to the variations in the capture conditions and viewpoint changes between the query image and the database images. To solve the above problem, we make following contributions to the design of a panorama based on-device MVLR system. Firstly, we design a heading (from digital compass) aware BOF (Bag-of-features) model to generate the descriptors of panoramic images. Our approach fully considers the characteristics of the panoramic images and can facilitate the panorama based on-device MVLR to a large degree. Secondly, to search high dimensional visual descriptors directly on mobile devices, we propose an effective bilinear compressed sensing based encoding method. While being fast and accurate enough for on-device implementation, our algorithm can also reduce the memory usage of projection matrix significantly. Thirdly, we also release a panoramas database as well as a set of test panoramic quires which can be used as a new benchmark to facilitate further research in the area. Experimental results prove the effectiveness of the proposed methods for on-device MVLR applications.

Show MeSH

Related in: MedlinePlus

Performance of heading-aware BOF under different vocabulary size.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4043852&req=5

pone-0098806-g007: Performance of heading-aware BOF under different vocabulary size.

Mentions: Our method generates database and query descriptors separately by part. To verify the effectiveness of our method (HBOF), we propose a method for comparison (HBOF-CMP). The method generates database descriptors separately by part, while query does not. Meanwhile, generate traditional -dimensional BOF for query. For database, select the descriptors of the corresponding parts and add them to a -dimensional BOF. Figure 7 shows the comparison of the methods under different vocabulary size. The panoramas are diving into 12 parts. The baseline method is traditional BOF method. The performance of BOF is very poor because of lots of disturbed areas. The HBOF and HBOF-CMP methods improve the performance greatly by filtering out most of disturbed areas. Moreover, HBOF outperforms HBOF-CMP because HBOF can retain partial spatial information of database and query panorama.


On-device mobile visual location recognition by using panoramic images and compressed sensing based visual descriptors.

Guan T, Fan Y, Duan L, Yu J - PLoS ONE (2014)

Performance of heading-aware BOF under different vocabulary size.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4043852&req=5

pone-0098806-g007: Performance of heading-aware BOF under different vocabulary size.
Mentions: Our method generates database and query descriptors separately by part. To verify the effectiveness of our method (HBOF), we propose a method for comparison (HBOF-CMP). The method generates database descriptors separately by part, while query does not. Meanwhile, generate traditional -dimensional BOF for query. For database, select the descriptors of the corresponding parts and add them to a -dimensional BOF. Figure 7 shows the comparison of the methods under different vocabulary size. The panoramas are diving into 12 parts. The baseline method is traditional BOF method. The performance of BOF is very poor because of lots of disturbed areas. The HBOF and HBOF-CMP methods improve the performance greatly by filtering out most of disturbed areas. Moreover, HBOF outperforms HBOF-CMP because HBOF can retain partial spatial information of database and query panorama.

Bottom Line: Secondly, to search high dimensional visual descriptors directly on mobile devices, we propose an effective bilinear compressed sensing based encoding method.While being fast and accurate enough for on-device implementation, our algorithm can also reduce the memory usage of projection matrix significantly.Experimental results prove the effectiveness of the proposed methods for on-device MVLR applications.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Technology, Huazhong University of Science & Technology, Wuhan, People's Republic of China.

ABSTRACT
Mobile Visual Location Recognition (MVLR) has attracted a lot of researchers' attention in the past few years. Existing MVLR applications commonly use Query-by-Example (QBE) based image retrieval principle to fulfill the location recognition task. However, the QBE framework is not reliable enough due to the variations in the capture conditions and viewpoint changes between the query image and the database images. To solve the above problem, we make following contributions to the design of a panorama based on-device MVLR system. Firstly, we design a heading (from digital compass) aware BOF (Bag-of-features) model to generate the descriptors of panoramic images. Our approach fully considers the characteristics of the panoramic images and can facilitate the panorama based on-device MVLR to a large degree. Secondly, to search high dimensional visual descriptors directly on mobile devices, we propose an effective bilinear compressed sensing based encoding method. While being fast and accurate enough for on-device implementation, our algorithm can also reduce the memory usage of projection matrix significantly. Thirdly, we also release a panoramas database as well as a set of test panoramic quires which can be used as a new benchmark to facilitate further research in the area. Experimental results prove the effectiveness of the proposed methods for on-device MVLR applications.

Show MeSH
Related in: MedlinePlus