海上舰船目标的智能感知是无人水面艇、无人机视觉系统的最主要任务之一，针对海上舰船目标智能检测识别存在的问题，提出基于编码器-解码器结构的海上舰船目标图像智能分割算法，以像素级分割替代常规的检测方法，为海上无人平台的智能感知提供算法支撑。首先，针对通用的图像分割方法中存在的高层语义特征丰富、空间分辨率降低的问题，提出基于膨胀卷积的多尺度特征融合模块，提高编码器的特征提取能力；然后，针对不同目标像素身份判别的难点，在原有编码-解码结构基础上，增加了一个身份识别辅助网络分支，引导编码器对不同身份目标的特征进行关注，提高特征表示对不同身份目标的表征能力。最后，在所构建的6类舰船目标分割数据集上进行实验验证。结果表明，本文方法在准确率上较通用分割方法能更有效地实现舰船目标分割，验证了本文方法的有效性。
The perception of ship targets is one of the most important tasks of the vision system of USVs (Unmanned Surface Vessels) and UAVs (Unmanned Aerial Vehicles). Aiming at the problems of detection and identification for ship targets, we propose a novel image segmentation algorithm of Marine ship targets based on the encoder-decoder structure. In this algorithm, pixel level segmentation is used to replace the conventional detection method, which provides algorithm support for perception of offshore unmanned platform. Firstly, aiming at the problems of rich high-level semantic features and reduced spatial resolution in general image segmentation methods, a multi-scale feature fusion module based on dilated convolution is proposed to improve the feature extraction capability of the encoder. Then, aiming at the difficulty of the identification of different target pixels, on the basis of the original encoding-decoding structure, an identity recognition auxiliary network branch is added to guide the encoder to pay more attention to the features of different identity targets, and improve the ability of feature representation. Finally, the proposed method is verified by experiments on six kinds of ship target segmentation datasets. The experiment results show that the proposed method is more effective than the general segmentation method in terms of accuracy, which verifies the effectiveness of the proposed method.
2022,44(24): 91-95 收稿日期：2022-06-23
DOI：10.3404/j.issn.1672-7649.2022.24.019
分类号：TP701；TP753
作者简介：吕亚飞(1992-),男,博士研究生,研究方向为多源信息智能融合
参考文献：
[1] KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep onvolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25(2).
[2] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2014.
[3] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016.
[4] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 39(4):640-651
[5] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[J]. Computer Science, 2014(4):357-361
[6] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[J]. 2017.
[7] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[J]. European Conference on Computer Vision, 2018:801-818
[8] KAIMING H, GEORGIA G, PIOTR D, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018:1-1
[9] HAMAGUCHI R, FUJITA A, NEMOTO K, et al. Effective use of dilated convolutions for segmenting small object instances in remote sensing imagery[C]//2018 IEEE Winter Conference on Appliation on Compoter Vision, 2018.
[10] RONNEBERGER O, FISCHER P, BROX T. U-Net:Convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing & Computer-assisted Intervention. 2015.
[11] ZHAO H, SHI J, QI X, et al. Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017:6230-6239.
[12] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:Towards real-time object detection with region proposal networks.[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137-1149
[13] BADR INARAYANAN V, KENDALL A, CIPOLLA R. SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495.
[14] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab:semantic image segmentation with deep convolutional nets, atrous-convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 40(4):834-848
[15] XIONG W, LV Y, CUI Y, et al. A discriminative feature learning approach for remote sensing image retrieval[J]. Remote Sensing, 2019, 11(3):281.
