The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
돌출 선박 탐지는 해상 운송 및 항해의 안전을 보장하는 데 중요한 역할을 합니다. 그러나 파도, 특수한 날씨, 해상 조도의 영향으로 인해 기존의 돌출 방법으로는 복잡한 해양 환경에서 효과적인 선박 탐지를 달성할 수 없습니다. 이러한 문제를 해결하기 위해 본 논문에서는 Attention Nested U-Structure(A)를 기반으로 한 새로운 돌출 방법을 제안했다.U2그물). 먼저, U자형 구조의 단점을 보완하기 위해 PPM(Pyramid Pooling Module)과 GGP(Global Guidance Path)를 설계하여 특징 정보 복원을 안내합니다. 그런 다음 대상 특성을 더욱 구체화하기 위해 중첩된 U자형 구조에 주의 모듈을 추가합니다. 궁극적으로 FAM(Feature Aggregation Module)을 통해 다단계 기능과 전역 컨텍스트 기능이 통합되어 대상을 찾는 기능이 향상됩니다. 실험 결과는 제안된 방법이 F-측정에서 최대 36.75%의 개선을 가질 수 있음을 보여줍니다(F평균) 다른 최신 방법과 비교됩니다.
Weina ZHOU
Shanghai Maritime University
Ying ZHOU
Shanghai Maritime University
Xiaoyang ZENG
Fudan University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Weina ZHOU, Ying ZHOU, Xiaoyang ZENG, "An Attention Nested U-Structure Suitable for Salient Ship Detection in Complex Maritime Environment" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 6, pp. 1164-1171, June 2022, doi: 10.1587/transinf.2021EDP7181.
Abstract: Salient ship detection plays an important role in ensuring the safety of maritime transportation and navigation. However, due to the influence of waves, special weather, and illumination on the sea, existing saliency methods are still unable to achieve effective ship detection in a complex marine environment. To solve the problem, this paper proposed a novel saliency method based on an attention nested U-Structure (AU2Net). First, to make up for the shortcomings of the U-shaped structure, the pyramid pooling module (PPM) and global guidance paths (GGPs) are designed to guide the restoration of feature information. Then, the attention modules are added to the nested U-shaped structure to further refine the target characteristics. Ultimately, multi-level features and global context features are integrated through the feature aggregation module (FAM) to improve the ability to locate targets. Experiment results demonstrate that the proposed method could have at most 36.75% improvement in F-measure (Favg) compared to the other state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7181/_p
부
@ARTICLE{e105-d_6_1164,
author={Weina ZHOU, Ying ZHOU, Xiaoyang ZENG, },
journal={IEICE TRANSACTIONS on Information},
title={An Attention Nested U-Structure Suitable for Salient Ship Detection in Complex Maritime Environment},
year={2022},
volume={E105-D},
number={6},
pages={1164-1171},
abstract={Salient ship detection plays an important role in ensuring the safety of maritime transportation and navigation. However, due to the influence of waves, special weather, and illumination on the sea, existing saliency methods are still unable to achieve effective ship detection in a complex marine environment. To solve the problem, this paper proposed a novel saliency method based on an attention nested U-Structure (AU2Net). First, to make up for the shortcomings of the U-shaped structure, the pyramid pooling module (PPM) and global guidance paths (GGPs) are designed to guide the restoration of feature information. Then, the attention modules are added to the nested U-shaped structure to further refine the target characteristics. Ultimately, multi-level features and global context features are integrated through the feature aggregation module (FAM) to improve the ability to locate targets. Experiment results demonstrate that the proposed method could have at most 36.75% improvement in F-measure (Favg) compared to the other state-of-the-art methods.},
keywords={},
doi={10.1587/transinf.2021EDP7181},
ISSN={1745-1361},
month={June},}
부
TY - JOUR
TI - An Attention Nested U-Structure Suitable for Salient Ship Detection in Complex Maritime Environment
T2 - IEICE TRANSACTIONS on Information
SP - 1164
EP - 1171
AU - Weina ZHOU
AU - Ying ZHOU
AU - Xiaoyang ZENG
PY - 2022
DO - 10.1587/transinf.2021EDP7181
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2022
AB - Salient ship detection plays an important role in ensuring the safety of maritime transportation and navigation. However, due to the influence of waves, special weather, and illumination on the sea, existing saliency methods are still unable to achieve effective ship detection in a complex marine environment. To solve the problem, this paper proposed a novel saliency method based on an attention nested U-Structure (AU2Net). First, to make up for the shortcomings of the U-shaped structure, the pyramid pooling module (PPM) and global guidance paths (GGPs) are designed to guide the restoration of feature information. Then, the attention modules are added to the nested U-shaped structure to further refine the target characteristics. Ultimately, multi-level features and global context features are integrated through the feature aggregation module (FAM) to improve the ability to locate targets. Experiment results demonstrate that the proposed method could have at most 36.75% improvement in F-measure (Favg) compared to the other state-of-the-art methods.
ER -