Name
Abstract | ||
|---|---|---|
With the increasing demand for indoor localization service in our daily life, vision-based indoor localization has become a hot topic since image recording and application are very popular in the indoor environment. Based on the epipolar geometry algorithm, more images are required in the database to achieve better localization performance, which would inevitably lead to high time consuming for image retrieval. Therefore, in this paper we propose a vision-based indoor localization method by using the BoVW (Bag of Visual Word)- based image retrieval method, which could achieve less time consuming and good localization performance. The experiment results show that the localization error of the system by utilizing our proposed method could achieve an accuracy of less than 2 meters by a chance of 75%, while the time for localization sharply decreases by 60%. Compared with the traditional localization system, the proposed method could make a balance between the localization accuracy and efficiency in practice. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1007/978-981-10-6571-2_60 | Lecture Notes in Electrical Engineering |
Keywords | DocType | Volume |
Indoor localization,Vision-based,Image retrieval,BoVW algorithm,Epipolar geometry | Conference | 463 |
ISSN | Citations | PageRank |
1876-1100 | 0 | 0.34 |
References | Authors | |
8 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lin Ma | 1 | 7 | 4.24 |
| Lin Ma | 2 | 7 | 4.24 |
| Tong Jia | 3 | 0 | 0.68 |
| Tong Jia | 4 | 0 | 0.68 |
| Xuezhi Tan | 5 | 80 | 14.98 |
| Xuezhi Tan | 6 | 80 | 14.98 |