Cargando…
Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network
Objective: The shallow underwater environment is complex, with problems of color shift, uneven illumination, blurring, and distortion in the imaging process. These scenes are very unfavorable for the reasoning of the detection network. Additionally, typical object identification algorithms struggle...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9608072/ https://www.ncbi.nlm.nih.gov/pubmed/36298226 http://dx.doi.org/10.3390/s22207875 |
_version_ | 1784818695157055488 |
---|---|
author | Ge, Huilin Dai, Yuewei Zhu, Zhiyu Zang, Xu |
author_facet | Ge, Huilin Dai, Yuewei Zhu, Zhiyu Zang, Xu |
author_sort | Ge, Huilin |
collection | PubMed |
description | Objective: The shallow underwater environment is complex, with problems of color shift, uneven illumination, blurring, and distortion in the imaging process. These scenes are very unfavorable for the reasoning of the detection network. Additionally, typical object identification algorithms struggle to maintain high resilience in underwater environments due to picture domain offset, making underwater object detection problematic. Methods: This paper proposes a single-stage detection method with the double enhancement of anchor boxes and features. The feature context relevance is improved by proposing a composite-connected backbone network. The receptive field enhancement module is introduced to enhance the multi-scale detection capability. Finally, a prediction refinement strategy is proposed, which refines the anchor frame and features through two regressions, solves the problem of feature anchor frame misalignment, and improves the detection performance of the single-stage underwater algorithm. Results: We achieved an effect of 80.2 mAP on the Labeled Fish in the Wild dataset, which saves some computational resources and time while still improving accuracy. On the original basis, UWNet can achieve 2.1 AP accuracy improvement due to the powerful feature extraction function and the critical role of multi-scale functional modules. At an input resolution of 300 × 300, UWNet can provide an accuracy of 32.4 AP. When choosing the number of prediction layers, the accuracy of the four and six prediction layer structures is compared. The experiments show that on the Labeled Fish in the Wild dataset, the six prediction layers are better than the four. Conclusion: The single-stage underwater detection model UWNet proposed in this research has a double anchor frame and feature optimization. By adding three functional modules, the underwater detection of the single-stage detector is enhanced to address the issue that it is simple to miss detection while detecting small underwater targets. |
format | Online Article Text |
id | pubmed-9608072 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96080722022-10-28 Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network Ge, Huilin Dai, Yuewei Zhu, Zhiyu Zang, Xu Sensors (Basel) Article Objective: The shallow underwater environment is complex, with problems of color shift, uneven illumination, blurring, and distortion in the imaging process. These scenes are very unfavorable for the reasoning of the detection network. Additionally, typical object identification algorithms struggle to maintain high resilience in underwater environments due to picture domain offset, making underwater object detection problematic. Methods: This paper proposes a single-stage detection method with the double enhancement of anchor boxes and features. The feature context relevance is improved by proposing a composite-connected backbone network. The receptive field enhancement module is introduced to enhance the multi-scale detection capability. Finally, a prediction refinement strategy is proposed, which refines the anchor frame and features through two regressions, solves the problem of feature anchor frame misalignment, and improves the detection performance of the single-stage underwater algorithm. Results: We achieved an effect of 80.2 mAP on the Labeled Fish in the Wild dataset, which saves some computational resources and time while still improving accuracy. On the original basis, UWNet can achieve 2.1 AP accuracy improvement due to the powerful feature extraction function and the critical role of multi-scale functional modules. At an input resolution of 300 × 300, UWNet can provide an accuracy of 32.4 AP. When choosing the number of prediction layers, the accuracy of the four and six prediction layer structures is compared. The experiments show that on the Labeled Fish in the Wild dataset, the six prediction layers are better than the four. Conclusion: The single-stage underwater detection model UWNet proposed in this research has a double anchor frame and feature optimization. By adding three functional modules, the underwater detection of the single-stage detector is enhanced to address the issue that it is simple to miss detection while detecting small underwater targets. MDPI 2022-10-17 /pmc/articles/PMC9608072/ /pubmed/36298226 http://dx.doi.org/10.3390/s22207875 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Ge, Huilin Dai, Yuewei Zhu, Zhiyu Zang, Xu Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network |
title | Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network |
title_full | Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network |
title_fullStr | Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network |
title_full_unstemmed | Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network |
title_short | Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network |
title_sort | single-stage underwater target detection based on feature anchor frame double optimization network |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9608072/ https://www.ncbi.nlm.nih.gov/pubmed/36298226 http://dx.doi.org/10.3390/s22207875 |
work_keys_str_mv | AT gehuilin singlestageunderwatertargetdetectionbasedonfeatureanchorframedoubleoptimizationnetwork AT daiyuewei singlestageunderwatertargetdetectionbasedonfeatureanchorframedoubleoptimizationnetwork AT zhuzhiyu singlestageunderwatertargetdetectionbasedonfeatureanchorframedoubleoptimizationnetwork AT zangxu singlestageunderwatertargetdetectionbasedonfeatureanchorframedoubleoptimizationnetwork |