| TAO Sili(陶思丽),QIN Danyang,YANG Jiaqiang,BIE Haoze.[J].高技术通讯(英文),2025,31(3):300~308 |
|
| Research on indoor visual localization based on semantic segmentation and adaptive weighting |
| |
| DOI：10. 3772 / j. issn. 1006-6748. 2025. 03. 010 |
| 中文关键词: |
| 英文关键词: indoor localization, image retrieval, semantic segmentation, adaptive weight |
| 基金项目: |
| Author Name | Affiliation | | TAO Sili(陶思丽) | (College of Electronic Engineering,Heilongjiang University,Harbin 150080,P.R.China)
(National Mobile Communications Research Laboratory,Southeast University,Nanjing 210096,P.R.China) | | QIN Danyang | | | YANG Jiaqiang | | | BIE Haoze | |
|
| Hits: 19 |
| Download times: 22 |
| 中文摘要: |
| |
| 英文摘要: |
| Indoor visual localization relies heavily on image retrieval to ascertain location information.However, the widespread presence and high consistency of floor patterns across different images often lead to the extraction of numerous repetitive features, thereby reducing the accuracy of image retrieval. This article proposes an indoor visual localization method based on semantic segmentation and adaptive weight fusion to address the issue of ground texture interference with retrieval results.During the positioning process, an indoor semantic segmentation model is established. Semantic segmentation technology is applied to accurately delineate the ground portion of the images. Feature extraction is performed on both the original database and the ground-segmented database. The vector of locally aggregated descriptors (VLAD) algorithm is then used to convert image features into a fixed-length feature representation, which improves the efficiency of image retrieval. Simultaneously, a method for adaptive weight optimization in similarity calculation is proposed, using adaptive weights to compute similarity for different regional features, thereby improving the accuracy of image retrieval. The experimental results indicate that this method significantly reduces ground interference and effectively utilizes ground information, thereby improving the accuracy of image retrieval. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
