Image Retrieval Method Based on Visual Map Pre-Sampling Construction in Indoor Positioning
In visual indoor positioning systems, the method of constructing a visual map by point-by-point sampling is widely used due to its characteristics of clear static images and simple coordinate calculation. However, too small a sampling interval will cause image redundancy, while too large a sampling...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/12/4/169 |
| _version_ | 1827744949342306304 |
|---|---|
| author | Jianan Bai Danyang Qin Ping Zheng Lin Ma |
| author_facet | Jianan Bai Danyang Qin Ping Zheng Lin Ma |
| author_sort | Jianan Bai |
| collection | DOAJ |
| description | In visual indoor positioning systems, the method of constructing a visual map by point-by-point sampling is widely used due to its characteristics of clear static images and simple coordinate calculation. However, too small a sampling interval will cause image redundancy, while too large a sampling interval will lead to the absence of any scene images, which will result in worse positioning efficiency and inferior positioning accuracy. As a result, this paper proposed a visual map construction method based on pre-sampled image features matching, according to the epipolar geometry of adjacent position images, to determine the optimal sampling spacing within the constraints and effectively control the database size while ensuring the integrity of the image information. In addition, in order to realize the rapid retrieval of the visual map and reduce the positioning error caused by the time overhead, an image retrieval method based on deep hashing was also designed in this paper. This method used a convolutional neural network to extract image features to construct the semantic similarity structure to guide the generation of hash code. Based on the log-cosh function, this paper proposed a loss function whose function curve was smooth and not affected by outliers, and then integrated it into the deep network to optimize parameters, for fast and accurate image retrieval. Experiments on the FLICKR25K dataset and the visual map proved that the method proposed in this paper could achieve sub-second image retrieval with guaranteed accuracy, thereby demonstrating its promising performance. |
| first_indexed | 2024-03-11T04:58:08Z |
| format | Article |
| id | doaj.art-73134cc9b75a45a0b84ef03923afcfbc |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-11T04:58:08Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-73134cc9b75a45a0b84ef03923afcfbc2023-11-17T19:31:33ZengMDPI AGISPRS International Journal of Geo-Information2220-99642023-04-0112416910.3390/ijgi12040169Image Retrieval Method Based on Visual Map Pre-Sampling Construction in Indoor PositioningJianan Bai0Danyang Qin1Ping Zheng2Lin Ma3Department of Electronic Engineering, Heilongjiang University, Harbin 150080, ChinaDepartment of Electronic Engineering, Heilongjiang University, Harbin 150080, ChinaDepartment of Electronic Engineering, Heilongjiang University, Harbin 150080, ChinaDepartment of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150080, ChinaIn visual indoor positioning systems, the method of constructing a visual map by point-by-point sampling is widely used due to its characteristics of clear static images and simple coordinate calculation. However, too small a sampling interval will cause image redundancy, while too large a sampling interval will lead to the absence of any scene images, which will result in worse positioning efficiency and inferior positioning accuracy. As a result, this paper proposed a visual map construction method based on pre-sampled image features matching, according to the epipolar geometry of adjacent position images, to determine the optimal sampling spacing within the constraints and effectively control the database size while ensuring the integrity of the image information. In addition, in order to realize the rapid retrieval of the visual map and reduce the positioning error caused by the time overhead, an image retrieval method based on deep hashing was also designed in this paper. This method used a convolutional neural network to extract image features to construct the semantic similarity structure to guide the generation of hash code. Based on the log-cosh function, this paper proposed a loss function whose function curve was smooth and not affected by outliers, and then integrated it into the deep network to optimize parameters, for fast and accurate image retrieval. Experiments on the FLICKR25K dataset and the visual map proved that the method proposed in this paper could achieve sub-second image retrieval with guaranteed accuracy, thereby demonstrating its promising performance.https://www.mdpi.com/2220-9964/12/4/169indoor positioningbinary codessemanticsimage retrieval |
| spellingShingle | Jianan Bai Danyang Qin Ping Zheng Lin Ma Image Retrieval Method Based on Visual Map Pre-Sampling Construction in Indoor Positioning ISPRS International Journal of Geo-Information indoor positioning binary codes semantics image retrieval |
| title | Image Retrieval Method Based on Visual Map Pre-Sampling Construction in Indoor Positioning |
| title_full | Image Retrieval Method Based on Visual Map Pre-Sampling Construction in Indoor Positioning |
| title_fullStr | Image Retrieval Method Based on Visual Map Pre-Sampling Construction in Indoor Positioning |
| title_full_unstemmed | Image Retrieval Method Based on Visual Map Pre-Sampling Construction in Indoor Positioning |
| title_short | Image Retrieval Method Based on Visual Map Pre-Sampling Construction in Indoor Positioning |
| title_sort | image retrieval method based on visual map pre sampling construction in indoor positioning |
| topic | indoor positioning binary codes semantics image retrieval |
| url | https://www.mdpi.com/2220-9964/12/4/169 |
| work_keys_str_mv | AT jiananbai imageretrievalmethodbasedonvisualmappresamplingconstructioninindoorpositioning AT danyangqin imageretrievalmethodbasedonvisualmappresamplingconstructioninindoorpositioning AT pingzheng imageretrievalmethodbasedonvisualmappresamplingconstructioninindoorpositioning AT linma imageretrievalmethodbasedonvisualmappresamplingconstructioninindoorpositioning |