智能系统学报2023，Vol.18Issue(6)：1197-1204,8.DOI:10.11992/tis.202210039
基于注意力机制的SOLOA船舶实例分割算法
SOLOA ship instance segmentation algorithm based on attention
摘要
Abstract
At present,the instance segmentation of visible ship images remains a highly challenging task.Most instance segmentation algorithms cannot effectively segment ship images in complex scenes due to the intricate and variable nature of ship images.A segmenting objects by locations based on attention(SOLOA)algorithm for ship instance seg-mentation,which utilizes the spatial attention mechanism to maximize the instance information in the classification fea-tures,is proposed in this paper.Here,the interrelationships between the image instances are modeled and fused with seg-mentation features.Training and testing results of the newly constructed ship image dataset show that the improved net-work model can effectively enhance the instance information in the network features and reduce the background inter-ferences.The accuracy of ship instance segmentation by the SOLOA algorithm is higher than that of other algorithms;hence,the proposed algorithm can be effectively adapted to meet the demands of ship segmentation in complex scenes.关键词
船舶目标/实例分割/复杂海上场景/深度学习/卷积神经网络/注意力机制/单阶段实例分割/可见光图像Key words
ship object/instance segmentation/complex scene/deep learning/convolution neural network/attention/one-stage instance segmentation/visible light image分类
信息技术与安全科学引用本文复制引用
孙雨鑫,苏丽,陈禹升,苑守正,孟浩..基于注意力机制的SOLOA船舶实例分割算法[J].智能系统学报,2023,18(6):1197-1204,8.基金项目
国家重点研发计划项目(2019YFE0105400) （2019YFE0105400）
船舶态势智能感知系统研制项目(MC-201920-X01) （MC-201920-X01）
中央高校基本科研业务费专项资金-博士研究生创新基金项目(3072022GIP0403). （3072022GIP0403）
