文献类型：期刊文献

英文题名：Toward Collaborative Multimodal Information Perception: A Hierarchical Feature Alignment Network and Acoustic-Optical Dataset for Underwater Object Detection

作者：Chen, Jing[1];Xie, Junjie[2];Liu, Mingxin[2];Wang, Hao[3];Lin, Cong[2]

机构：[1]Guangdong Ocean Univ, Coll Math & Comp, Zhanjiang 524088, Peoples R China;[2]Guangdong Ocean Univ, Coll Elect & Informat Engn, Zhanjiang 524088, Peoples R China;[3]Xian Univ Elect Sci & Technol, Coll Network & Informat Secur, Xian 710000, Peoples R China

年份：2026

卷号：19

起止页码：17916

外文期刊名：IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING

收录：SCI-EXPANDED(收录号：WOS:001788934400034)、、EI(收录号：20262120770388)、WOS

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62171143 and Grant 62172352, in part by the Natural Science Foundation of Guangdong Province under Grant 2025A1515011356 and Grant 2026A1515011448, in part by Innovation Team Project of Universities in Guangdong Province under Grant 2023KCXTD016, in part by Innovation Team Project of Guangdong Ocean University under Grant JDTD2024003, and in part by the Key Research Project of General Universities in Guangdong Province under Grant 2025ZDZX1007.

语种：英文

外文关键词：Signal detection; Object detection; Modeling; Modules (abstract algebra); Grounding; Optical imaging; Sonar; Tires; Distance measurement; Convolution; Acoustic-optical coordination; feature alignment; multimodal fusion; object detection; remotely operated vehicle (ROV)

外文摘要：In the realm of Earth observation, underwater target detection serves as a critical component for characterizing aquatic environments. However, existing acoustic-optical collaborative methods face persistent challenges, including the high calibration difficulty across different modalities and unsatisfactory feature alignment. A core difficulty lies in enabling the network to adaptively capture intrinsic dependencies and achieve efficient fusion of multimodal information during the learning process. To address this, this article proposes an object detection method with adaptive cross-modal feature alignment. Specifically, the method establishes automatic alignment relationships between sonar and optical images through fine-grained and instance-level feature fusion. Furthermore, a novel fusion strategy is designed to enable efficient acoustic-optical information fusion via same-layer feature learning. Finally, to mitigate the issues of scarcity and low quality of multimodal underwater datasets, a data acquisition platform is constructed, and a strictly spatiotemporally synchronized sonar-optical dataset is built. Extensive experimental results demonstrate that the proposed method simultaneously enhances detection performance on both sonar and optical images. On the created dataset, the proposed method achieves mAP@0.5 scores of 86.9% and 94.4% for acoustic-optical collaborative detection, thereby outperforming mainstream approaches. In addition, the robustness and generalization of the proposed method are verified in other multimodal object detection scenarios.