Fast Dual-Feature Extraction Based on Tightly Coupled Lightweight Network for Visual Place Recognition
Visual place recognition (VPR) is a task that aims to predict the location of an image based on the existing images. Because image data can often be massive, extracting features efficiently is critical. To solve the problems of model redundancy and poor time efficiency in feature extraction, this st...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10313262/ |
| _version_ | 1797545244813688832 |
|---|---|
| author | Xiaofei Hu Yang Zhou Liang Lyu Chaozhen Lan Qunshan Shi Mingbo Hou |
| author_facet | Xiaofei Hu Yang Zhou Liang Lyu Chaozhen Lan Qunshan Shi Mingbo Hou |
| author_sort | Xiaofei Hu |
| collection | DOAJ |
| description | Visual place recognition (VPR) is a task that aims to predict the location of an image based on the existing images. Because image data can often be massive, extracting features efficiently is critical. To solve the problems of model redundancy and poor time efficiency in feature extraction, this study proposes a fast dual-feature extraction method based on a tightly coupled lightweight network. The tightly coupled network extracts local and global features in a unified model which has a lightweight backbone. Learned step size quantization is then performed to reduce the computational overhead in the inference stage. Additionally, an efficient channel attention module ensures feature representation ability. Efficiency and performance experiments on different hardware platforms showed that the proposed algorithm incurred significant runtime savings for feature extraction, and the inference was 2.9–4.0 times faster than that in the general model. The experimental results confirmed that the proposed method can significantly improve VPR efficiency while ensuring accuracy. |
| first_indexed | 2024-03-10T14:12:45Z |
| format | Article |
| id | doaj.art-7cf07a1847f24d1c8465ec422e029b80 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-10T14:12:45Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7cf07a1847f24d1c8465ec422e029b802023-11-21T00:01:23ZengIEEEIEEE Access2169-35362023-01-011112785512786510.1109/ACCESS.2023.333137110313262Fast Dual-Feature Extraction Based on Tightly Coupled Lightweight Network for Visual Place RecognitionXiaofei Hu0Yang Zhou1https://orcid.org/0000-0001-6667-3353Liang Lyu2https://orcid.org/0000-0003-1168-210XChaozhen Lan3https://orcid.org/0000-0002-6860-3882Qunshan Shi4Mingbo Hou5Institute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaInstitute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaVisual place recognition (VPR) is a task that aims to predict the location of an image based on the existing images. Because image data can often be massive, extracting features efficiently is critical. To solve the problems of model redundancy and poor time efficiency in feature extraction, this study proposes a fast dual-feature extraction method based on a tightly coupled lightweight network. The tightly coupled network extracts local and global features in a unified model which has a lightweight backbone. Learned step size quantization is then performed to reduce the computational overhead in the inference stage. Additionally, an efficient channel attention module ensures feature representation ability. Efficiency and performance experiments on different hardware platforms showed that the proposed algorithm incurred significant runtime savings for feature extraction, and the inference was 2.9–4.0 times faster than that in the general model. The experimental results confirmed that the proposed method can significantly improve VPR efficiency while ensuring accuracy.https://ieeexplore.ieee.org/document/10313262/Visual place recognitiondual-feature extractiontightly coupledlearned step size quantization |
| spellingShingle | Xiaofei Hu Yang Zhou Liang Lyu Chaozhen Lan Qunshan Shi Mingbo Hou Fast Dual-Feature Extraction Based on Tightly Coupled Lightweight Network for Visual Place Recognition IEEE Access Visual place recognition dual-feature extraction tightly coupled learned step size quantization |
| title | Fast Dual-Feature Extraction Based on Tightly Coupled Lightweight Network for Visual Place Recognition |
| title_full | Fast Dual-Feature Extraction Based on Tightly Coupled Lightweight Network for Visual Place Recognition |
| title_fullStr | Fast Dual-Feature Extraction Based on Tightly Coupled Lightweight Network for Visual Place Recognition |
| title_full_unstemmed | Fast Dual-Feature Extraction Based on Tightly Coupled Lightweight Network for Visual Place Recognition |
| title_short | Fast Dual-Feature Extraction Based on Tightly Coupled Lightweight Network for Visual Place Recognition |
| title_sort | fast dual feature extraction based on tightly coupled lightweight network for visual place recognition |
| topic | Visual place recognition dual-feature extraction tightly coupled learned step size quantization |
| url | https://ieeexplore.ieee.org/document/10313262/ |
| work_keys_str_mv | AT xiaofeihu fastdualfeatureextractionbasedontightlycoupledlightweightnetworkforvisualplacerecognition AT yangzhou fastdualfeatureextractionbasedontightlycoupledlightweightnetworkforvisualplacerecognition AT lianglyu fastdualfeatureextractionbasedontightlycoupledlightweightnetworkforvisualplacerecognition AT chaozhenlan fastdualfeatureextractionbasedontightlycoupledlightweightnetworkforvisualplacerecognition AT qunshanshi fastdualfeatureextractionbasedontightlycoupledlightweightnetworkforvisualplacerecognition AT mingbohou fastdualfeatureextractionbasedontightlycoupledlightweightnetworkforvisualplacerecognition |