JIN Qianqian,LUO Jian,ZHANG Xiaoqian,et al.Small Target Segmentation Method in Remote Sensing Image based on Improved DeepLabV3p[J].Journal of Chengdu University of Information Technology,2023,38(06):673-680.[doi:10.16836/j.cnki.jcuit.2023.06.009]
基于改进DeepLabV3p的遥感图像中小目标分割方法
- Title:
- Small Target Segmentation Method in Remote Sensing Image based on Improved DeepLabV3p
- 文章编号:
- 2096-1618(2023)06-0673-08
- 关键词:
- DeepLabV3p; 遥感图像; SE注意力机制; ASPP; CRFs全连接条件随机场; 混合损失函数
- Keywords:
- DeepLabV3p; remote sensing images; SE attention mechanism; ASPP; CRFs; mixed loss function
- 分类号:
- TP75
- 文献标志码:
- A
- 摘要:
- 针对背景信息复杂、目标类别不均衡，遥感图像的中小目标在分割时常出现误检、漏检的问题，提出一种基于DeepLabV3p改进的遥感图像中小目标分割方法。采用ResNet101作为DeepLabV3p的骨干网络，提出多级感受野融合的ASPP模块，以获取更多感受野; 添加SE注意力机制，使模型获得更加精准的通道信息; 使用加权的CrossEntropyLoss和LovaszSoftmaxLoss损失函数进行训练，克服数据集目标不均衡的问题; 使用全连接条件随机场对预测结果进行图像后处理，对模型输出进行精细化处理。实验结果表明，使用该方法对DLRSD数据集进行分割，mIOU可达到73.22%，与基础网络相比提高了3.78%，有效提高了遥感图像中小目标的分割精度和准确率。
- Abstract:
- Due to the complexity of background information and the imbalance of target categories, small and medium-sized targets in remote sensing images are often subject to false detection and missing detection in segmentation. In order to solve this problem, an improved segmentation method for small and medium-sized targets of remote sensing images is proposed, which is based on DeepLabV3p. The ASPP module of multi-level receptive field fusion is proposed to obtain more receptive fields. In the decoding part, Adds SE attention mechanism to enable the model to obtain more accurate channel information.The weighted Cross Entropyloss function and LovaszSoftmaxLoss function are used for training. Finally, the CRFs is used for image post-processing of the prediction results, and the model output is refined. The experimental results show that using this method to segment images in DLRSD dataset, the mIOU can reach 73.22%,which is 3.78% higher than that of the basic network, effectively improves the segmentation precision and accuracy of small and medium targets in remote sensing images.
参考文献/References:
[1] 董蕴雅,张倩.基于CNN的高分遥感影像深度语义特征提取研究综述[J].遥感技术与应用,2019,34(1):1-11.
[2] 尹昊.基于卷积神经网络的遥感图像分割方法研究[D].泰安:山东农业大学,2021.
[3] Maggiori E,Tarabalka Y,Charpiat G,et al.Fully convolutional neural networks for remote sensing image classification[C].2016 IEEE international geoscience and remote sensing symposium(IGARSS).IEEE,2016:5071-5074.
[4] Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[C].Proceedings of the IEEE conference on computer vision and pattern recognition.2015:3431-3440.
[5] Li R,Zheng S,Duan C,et al.Multistage attention ResU-Net for semantic segmentation of fine-resolution remote sensing images[J].IEEE Geoscience and Remote Sensing Letters.2021,19:1-5.
[6] Ronneberger O,Fischer P,Brox T.U-net: Convolutional networks for biomedical image segmentation[C].International Conference on Medical image computing and computer-assisted intervention.Springer,Cham,2015:234-241.
[7] Zhao H,Shi J,Qi X,et al.Pyramid scene parsing network[C].Proceedings of the IEEE conference on computer vision and pattern recognition.2017:2881-2890.
[8] Chen L C,Zhu Y,Papandreou G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C].Proceedings of the European conference on computer vision(ECCV).2018:801-818.
[9] 杨蜀秦,王鹏飞,王帅,等.基于多头自注意力DeepLab v3+的无人机遥感影像小麦倒伏检测[J/OL].农业机械学报:1-11[2022-11-09].
[10] 黄聪,杨珺,刘毅,等.基于改进DeepLabV3p的遥感图像分割算法[J/OL].电子测量技术:1-7[2022-11-09].
[11] Hu J,Shen L,Sun G.Squeeze-and-excitation networks[C].Proceedings of the IEEE conference on computer vision and pattern recognition.2018:7132-7141.
[12] Berman M,Triki A R,Blaschko M B.The lovász-softmax loss:A tractable surrogate for the optimization of the intersection-over-union measure in neural networks[C].Proceedings of the IEEE conference on computer vision and pattern recognition.2018:4413-4421.
[13] Chen L C,Papandreou G,Kokkinos I,et al.Semantic image segmentation with deep convolutional nets and fully connected crfs[J].arXiv preprint arXiv:1412.7062,2014.
[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 and machine intelligence.2017,40(4):834-848.
[15] Chen L C,Papandreou G,Schroff F,et al.Rethinking atrous convolution for semantic image segmentation[J].arXiv preprint arXiv:1706.05587,2017.
[16] Lin T Y,Dollár P,Girshick R,et al.Feature pyramid networks for object detection[C].Proceedings of the IEEE conference on computer vision and pattern recognition.2017:2117-2125.
[17] 高宇田,杨阳,赵广帅,等.基于全连接条件随机场的图像语义分割算法研究[J].长春理工大学学报(自然科学版),2021,44(2):60-66.
备注/Memo
收稿日期:2022-11-23
通信作者:罗建.E-mail:luojianz@gmail.com