[1]孙雨鑫,苏丽,陈禹升,等.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.[doi:10.11992/tis.202210039]
　SUN Yuxin,SU Li,CHEN Yusheng,et al.SOLOA ship instance segmentation algorithm based on attention[J].CAAI Transactions on Intelligent Systems,2023,18(6):1197-1204.[doi:10.11992/tis.202210039]
点击复制

基于注意力机制的SOLOA船舶实例分割算法

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 18 期数: 2023年第6期 页码: 1197-1204 栏目: 学术论文—机器感知与模式识别 出版日期: 2023-11-05
Title:
SOLOA ship instance segmentation algorithm based on attention
作者:
孙雨鑫1, 苏丽1,2, 陈禹升1, 苑守正1, 孟浩1,2
1. 哈尔滨工程大学 智能科学与工程学院, 黑龙江 哈尔滨 150001;
2. 哈尔滨工程大学 船舶装备智能化技术与应用教育部重点实验室, 黑龙江 哈尔滨 150001
Author(s):
SUN Yuxin1, SU Li1,2, CHEN Yusheng1, YUAN Shouzheng1, MENG Hao1,2
1. College of Intelligent Science and Engineering, Harbin Engineering University, Harbin 150001, China;
2. Key Laboratory of Ministry of Education on Intelligent Technology and Application of Marine Equipment, Harbin Engineering University, Harbin 150001, China
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
Keywords:
ship object; instance segmentation; complex scene; deep learning; convolution neural network; attention; one-stage instance segmentation; visible light image
分类号:
TP183
DOI:
10.11992/tis.202210039
摘要:
目前，可见光船舶图像的实例分割仍然是较有挑战性的工作。由于船舶图像场景复杂多变，多数实例分割算法无法对复杂场景下的船舶图像进行有效分割。本文提出了基于注意力机制的依靠位置分割目标（attention based segmenting objects by locations, SOLOA）船舶实例分割算法，针对网络特征图里实例信息不完善、背景干扰较多的问题，使用空间注意力机制来充分利用分类特征中的实例信息，建模图像实例间的相互关系并与分割特征相融合。实验结果表明,在新构建的船舶图像数据集上进行训练和测试，改进的网络模型能有效地增强网络特征中的实例信息、减弱背景的干扰。SOLOA算法的船舶实例分割准确率高于其他算法，可以很好地适应复杂场景下的船舶分割需求。
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 segmentation, which utilizes the spatial attention mechanism to maximize the instance information in the classification features, is proposed in this paper. Here, the interrelationships between the image instances are modeled and fused with segmentation features. Training and testing results of the newly constructed ship image dataset show that the improved network model can effectively enhance the instance information in the network features and reduce the background interferences. 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.
参考文献/References:
[1] HUANG Guoquan, WAN Zining, LIU Xinggao, et al. Ship detection based on squeeze excitation skip-connection path networks for optical remote sensing images[J]. Neurocomputing, 2019, 332: 215–223.
[2] SU Hao, WEI Shunjun, LIU Shan, et al. HQ-ISNet: high-quality instance segmentation for remote sensing imagery[J]. Remote sensing, 2020, 12(6): 989.
[3] WEI Shunjun, ZENG Xiangfeng, QU Qizhe, et al. HRSID: a high-resolution SAR images dataset for ship detection and instance segmentation[J]. IEEE access, 2020, 8: 120234–120254.
[4] 胡欣, 郭庆昌. 基于红外图像的海上船舶分割算法研究[J]. 水雷战与舰船防护, 2009, 17(1): 5–8
HU Xin, GUO Qingchang. Research on ship segmentation algorithm based on IR image[J]. Mine warfare & ship self-defence, 2009, 17(1): 5–8
[5] SUN Yuxin, SU Li, LUO Yongkang, et al. Global mask R-CNN for marine ship instance segmentation[J]. Neurocomputing, 2022, 480: 257–270.
[6] SUN Yuxin, SU Li, LUO Yongkang, et al. IRDCLNet: instance segmentation of ship images based on interference reduction and dynamic contour learning in foggy scenes[J]. IEEE transactions on circuits and systems for video technology, 2022, 32(9): 6029–6043.
[7] HE Kaiming, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2980-2988.
[8] BOLYA D, ZHOU Chong, XIAO Fanyi, et al. YOLACT: real-time instance segmentation[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2020: 9156-9165.
[9] GAO Naiyu, SHAN Yanhu, WANG Yupei, et al. SSAP: single-shot instance segmentation with affinity pyramid[J]. IEEE transactions on circuits and systems for video technology, 2021, 31(2): 661–673.
[10] BOLYA D, ZHOU Chong, XIAO Fanyi, et al. YOLACT++ better real-time instance segmentation[J]. IEEE transactions on pattern analysis and machine intelligence, 2022, 44(2): 1108–1121.
[11] SUN Yuxin, SU Li, CUI Haohao, et al. Ship instance segmentation in foggy scene[C]//2021 40th Chinese Control Conference. Shanghai: IEEE, 2021: 8340-8345.
[12] LIU Shu, QI Lu, QIN Haifang, et al. Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8759-8768.
[13] ZHANG Rufeng, TIAN Zhi, SHEN Chunhua, et al. Mask encoding for single shot instance segmentation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 10223-10232.
[14] CAI Zhaowei, VASCONCELOS N. Cascade R-CNN: high quality object detection and instance segmentation[J]. IEEE transactions on pattern analysis and machine intelligence, 2021, 43(5): 1483–1498.
[15] CHEN L C, HERMANS A, PAPANDREOU G, et al. MaskLab: instance segmentation by refining object detection with semantic and direction features[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4013-4022.
[16] KIRILLOV A, WU Yuxin, HE Kaiming, et al. PointRend: image segmentation As rendering[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 9796-9805.
[17] CHENG Tianheng, WANG Xinggang, HUANG Lichao, et al. Boundary-preserving mask R-CNN[C]//European Conference on Computer Vision. Cham: Springer, 2020: 660-676.
[18] CHEN Kai, PANG Jiangmiao, WANG Jiaqi, et al. Hybrid task cascade for instance segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 4969-4978.
[19] WANG Shaoru, GONG Yongchao, XING Junliang, et al. RDSNet: a new deep architecture for reciprocal object detection and instance segmentation[C]//Proceedings of the AAAI conference on artificial intelligence. Washington, DC: AAAI press 2020, 34(7): 12208-12215.
[20] WANG X, ZHANG R, KONG T, et al. SOLOv2: dynamic and fast instance segmentation[J]. Advances in neural information processing systems, 2020, 33: 17721–17732.
[21] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 936-944.
[22] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence. Piscataway: IEEE, 2016: 640-651.
[23] LIU R, LEHMAN J, MOLINO P, et al. An intriguing failing of convolutional neural networks and the CoordConv solution[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal: ACM, 2018: 9628-9639.
[24] WU Yuxin, HE Kaiming. Group normalization[C]//European Conference on Computer Vision. Cham: Springer, 2018: 3-19.
[25] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE transactions on pattern analysis and machine intelligence, 2020, 42(2): 318–327.
[26] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The pascal visual object classes (VOC) challenge[J]. International journal of computer vision, 2010, 88(2): 303–338.
[27] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//European Conference on Computer Vision. Cham: Springer, 2014: 740-755.
[28] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84–90.
[29] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[30] XIE Enze, SUN Peize, SONG Xiaoge, et al. PolarMask: single shot instance segmentation with polar representation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 12190-12199.
相似文献/References:
[1]苏丽,孙雨鑫,苑守正.基于深度学习的实例分割研究综述[J].智能系统学报,2022,17(1):16.[doi:10.11992/tis.202109043]
　SU Li,SUN Yuxin,YUAN Shouzheng.A survey of instance segmentation research based on deep learning[J].CAAI Transactions on Intelligent Systems,2022,17():16.[doi:10.11992/tis.202109043]

备注/Memo

收稿日期:2022-10-31。
基金项目:国家重点研发计划项目（2019YFE0105400）；船舶态势智能感知系统研制项目（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）.
作者简介:孙雨鑫,博士研究生,主要研究方向为计算机视觉;苏丽,副教授,博士生导师,主要研究方向为环境感知与智能控制、智能船舶、机器视觉检测技术、多传感器信息融合、先进控制理论及应用、智能系统。作为项目负责人和主要研究人员承担了4项国家及省部级科研项目,发表学术和教改论文40篇;陈禹升,硕士研究生,主要研究方向为目标检测
通讯作者:苏丽.E-mail:suli406@hrbeu.edu.cn

更新日期/Last Update: 1900-01-01
Copyright © 《 智能系统学报》 编辑部
地址：（150001）黑龙江省哈尔滨市南岗区南通大街145-1号楼 电话：0451- 82534001、82518134　邮箱：tis@vip.sina.com