Hierarchical Visual Place Recognition Based on Semantic-Aggregation
A major challenge in place recognition is to be robust against viewpoint changes and appearance changes caused by self and environmental variations. Humans achieve this by recognizing objects and their relationships in the scene under different conditions. Inspired by this, we propose a hierarchical...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/20/9540 |
| _version_ | 1827680252203106304 |
|---|---|
| author | Baifan Chen Xiaoting Song Hongyu Shen Tao Lu |
| author_facet | Baifan Chen Xiaoting Song Hongyu Shen Tao Lu |
| author_sort | Baifan Chen |
| collection | DOAJ |
| description | A major challenge in place recognition is to be robust against viewpoint changes and appearance changes caused by self and environmental variations. Humans achieve this by recognizing objects and their relationships in the scene under different conditions. Inspired by this, we propose a hierarchical visual place recognition pipeline based on semantic-aggregation and scene understanding for the images. The pipeline contains coarse matching and fine matching. Semantic-aggregation happens in residual aggregation of visual information and semantic information in coarse matching, and semantic association of semantic edges in fine matching. Through the above two processes, we realized a robust coarse-to-fine pipeline of visual place recognition across viewpoint and condition variations. Experimental results on the benchmark datasets show that our method performs better than several state-of-the-art methods, improving the robustness against severe viewpoint changes and appearance changes while maintaining good matching-time performance. Moreover, we prove that it is possible for a computer to realize place recognition based on scene understanding. |
| first_indexed | 2024-03-10T06:45:26Z |
| format | Article |
| id | doaj.art-7e05be88ec5f4e8aadb1046006b6c3af |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T06:45:26Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7e05be88ec5f4e8aadb1046006b6c3af2023-11-22T17:20:18ZengMDPI AGApplied Sciences2076-34172021-10-011120954010.3390/app11209540Hierarchical Visual Place Recognition Based on Semantic-AggregationBaifan Chen0Xiaoting Song1Hongyu Shen2Tao Lu3School of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaHubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, School of Computer Science and Engineering, Wuhan 430205, ChinaA major challenge in place recognition is to be robust against viewpoint changes and appearance changes caused by self and environmental variations. Humans achieve this by recognizing objects and their relationships in the scene under different conditions. Inspired by this, we propose a hierarchical visual place recognition pipeline based on semantic-aggregation and scene understanding for the images. The pipeline contains coarse matching and fine matching. Semantic-aggregation happens in residual aggregation of visual information and semantic information in coarse matching, and semantic association of semantic edges in fine matching. Through the above two processes, we realized a robust coarse-to-fine pipeline of visual place recognition across viewpoint and condition variations. Experimental results on the benchmark datasets show that our method performs better than several state-of-the-art methods, improving the robustness against severe viewpoint changes and appearance changes while maintaining good matching-time performance. Moreover, we prove that it is possible for a computer to realize place recognition based on scene understanding.https://www.mdpi.com/2076-3417/11/20/9540hierarchical place recognitionsemantic aggregationsemantic edges |
| spellingShingle | Baifan Chen Xiaoting Song Hongyu Shen Tao Lu Hierarchical Visual Place Recognition Based on Semantic-Aggregation Applied Sciences hierarchical place recognition semantic aggregation semantic edges |
| title | Hierarchical Visual Place Recognition Based on Semantic-Aggregation |
| title_full | Hierarchical Visual Place Recognition Based on Semantic-Aggregation |
| title_fullStr | Hierarchical Visual Place Recognition Based on Semantic-Aggregation |
| title_full_unstemmed | Hierarchical Visual Place Recognition Based on Semantic-Aggregation |
| title_short | Hierarchical Visual Place Recognition Based on Semantic-Aggregation |
| title_sort | hierarchical visual place recognition based on semantic aggregation |
| topic | hierarchical place recognition semantic aggregation semantic edges |
| url | https://www.mdpi.com/2076-3417/11/20/9540 |
| work_keys_str_mv | AT baifanchen hierarchicalvisualplacerecognitionbasedonsemanticaggregation AT xiaotingsong hierarchicalvisualplacerecognitionbasedonsemanticaggregation AT hongyushen hierarchicalvisualplacerecognitionbasedonsemanticaggregation AT taolu hierarchicalvisualplacerecognitionbasedonsemanticaggregation |