Abstract | ||
---|---|---|
Recently, indoor localization technology has attracted the attention of many scholars and IT industry enterprises. The main problem that exists in the current algorithms is time latency and localization accuracy. We propose a fast image retrieval algorithm for vision-based indoor localization system. The proposed algorithm is based on PCA, Linear Regression and GIST when an image database is built. Gist feature of database image is processed as training data set. Through PCA the key information is extracted, then we fit a model by linear regression. We compare the performance of our algorithm with C-GIST algorithm. It will be also demonstrated that our proposed algorithm takes an average of 31.5 percent less time for image retrieval in coarse matching step, and the accuracy is better than C-GIST. The most prominent contribution is the results of our algorithm can be directly applied to the localization of a region of narrower width, and the latency of the algorithm have no relation to the size of the visual database. |
Year | Venue | Keywords |
---|---|---|
2018 | 2018 IEEE 87TH VEHICULAR TECHNOLOGY CONFERENCE (VTC SPRING) | PCA, GIST, Linear Regression, image retrieval, Visual Localization |
Field | DocType | Citations |
Approximation algorithm,Computer science,Latency (engineering),Visualization,Image retrieval,Algorithm,GiST,Cluster analysis,Principal component analysis,Linear regression | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiliang Yin | 1 | 0 | 1.01 |
Lin Ma | 2 | 912 | 71.35 |
Xuezhi Tan | 3 | 80 | 14.98 |