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

Illustration of heading-aware method for database.(a) The database panorama is partitioned into 6 parts equally. “0–59” represents that the part 1 ranges from 0 to 59 degree. (b) Illustration of heading-aware method for database. Stars, triangles, and circles represent different visual words.
© Copyright Policy
Related In: Results  -  Collection

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

pone-0098806-g004: Illustration of heading-aware method for database.(a) The database panorama is partitioned into 6 parts equally. “0–59” represents that the part 1 ranges from 0 to 59 degree. (b) Illustration of heading-aware method for database. Stars, triangles, and circles represent different visual words.

Mentions: The ideal situation is that we can extract the query corresponding areas only, filtering out the disturbed areas. Based on this idea, we propose to partition the database panoramas equally. As shown in Figure 4, the panorama is partitioned into 6 parts. The first part ranges from 0 to 59 degree, and the last part ranges from 300 to 359 degree. Generate the sub-descriptor for each part separately, and concatenate them to compose the heading-aware visual descriptor.


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)

Illustration of heading-aware method for database.(a) The database panorama is partitioned into 6 parts equally. “0–59” represents that the part 1 ranges from 0 to 59 degree. (b) Illustration of heading-aware method for database. Stars, triangles, and circles represent different visual words.
© Copyright Policy
Related In: Results  -  Collection

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

pone-0098806-g004: Illustration of heading-aware method for database.(a) The database panorama is partitioned into 6 parts equally. “0–59” represents that the part 1 ranges from 0 to 59 degree. (b) Illustration of heading-aware method for database. Stars, triangles, and circles represent different visual words.
Mentions: The ideal situation is that we can extract the query corresponding areas only, filtering out the disturbed areas. Based on this idea, we propose to partition the database panoramas equally. As shown in Figure 4, the panorama is partitioned into 6 parts. The first part ranges from 0 to 59 degree, and the last part ranges from 300 to 359 degree. Generate the sub-descriptor for each part separately, and concatenate them to compose the heading-aware visual descriptor.

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