基于Word Embedding的遥感影像检测分割

doi:10.3969/j.issn.0372-2112.2020.01.009

电子学报 ›› 2020, Vol. 48 ›› Issue (1): 75-83.DOI: 10.3969/j.issn.0372-2112.2020.01.009

基于Word Embedding的遥感影像检测分割

尤洪峰¹, 田生伟², 禹龙³, 吕亚龙¹

1. 新疆大学信息科学与工程学院, 乌鲁木齐 830046;
2. 新疆大学软件学院, 乌鲁木齐 830046;
3. 新疆大学网络中心, 乌鲁木齐 830046

收稿日期:2018-12-04 修回日期:2019-06-05 出版日期:2020-01-25
- 通讯作者:
- 田生伟
- 作者简介:
- 尤洪峰 男,1991年6月生,江苏省南通人.现为新疆大学硕士研究生,主要研究方向为人工智能和图像处理.E-mail:1053109177@qq.com;禹龙女,1974年10月出生,新疆乌鲁木齐人.教授、博士生导师.现为网络与信息技术中心网络部主任,主要研究方向为人工智能、网络空间安全、自然语言处理.
- 基金资助:
- 新疆维吾尔自治区自然科学基金 (No.2016D01C050）; 新疆自治区科技人才培养 (No.QN2016YX0051）

Remote Sensing Image Detection and Segmentation Based on Word Embedding

YOU Hong-feng¹, TIAN Sheng-wei², YU Long³, Lü Ya-long¹

1. School of Information Science and Engineering, Xinjiang University, Urumqi, Xinjiang 830046, China;
2. Software College, Xinjiang University, Urumqi, Xinjiang 830046, China;
3. Network Center, Xinjiang University, Urumqi, Xinjiang 830046, China

Received:2018-12-04 Revised:2019-06-05 Online:2020-01-25 Published:2020-01-25
- Corresponding author:
- TIAN Sheng-wei
- Supported by:
- Natural Science Foundation of Xinjiang Uygur Autonomous Region, China (No.2016D01C050); Science and Technology Talent Cultivation Project of Xinjiang Uygur Autonomous Region, China (No.QN2016YX0051)

摘要/Abstract

摘要： 遥感影像检测分割技术通常需提取影像特征并通过深度学习算法挖掘影像的深层特征来实现.然而传统特征（如颜色特征、纹理特征、空间关系特征等）不能充分描述影像语义信息，而单一结构或串联算法无法充分挖掘影像的深层特征和上下文语义信息.针对上述问题，本文通过词嵌入将空间关系特征映射成实数密集向量，与颜色、纹理特征的结合.其次，本文构建基于注意力机制下图卷积网络和独立循环神经网络的遥感影像检测分割并联算法（Attention Graph Convolution Networks and Independently Recurrent Neural Network，ATGIR）.该算法首先通过注意力机制对结合后的特征进行概率权重分配；然后利用图卷积网络（GCNs）算法对高权重的特征进一步挖掘并生成方向标签，同时使用独立循环神经网络（IndRNN）算法挖掘影像特征中的上下文信息，最后用Sigmoid分类器完成影像检测分割任务.以胡杨林遥感影像检测分割任务为例，我们验证了提出的特征提取方法和ATGIR算法能有效提升胡杨林检测分割任务的性能.

关键词: 注意力机制, 图卷积网络, 独立循环神经网络, 并联算法, 词嵌入

Abstract: Remote sensing image detection and segmentation technology usually needs to extract image features and mine the deep features of images through deep learning algorithm. However, traditional imaging features (e.g., color, texture, spatial relationship) cannot fully reflect the semantic information of the images,while single/sequential algorithm cannot fully exploit the deep features and the contextual semantic information of the images. Aiming at the above challenges, in this paper, the spatial relation features are mapped into real dense vectors by word embedding, which are combined with color and texture features. Further, we propose a new parallel algorithm referred to as attention graph convolution networks and independently recurrent neural network (ATGIR) based on graph convolution network and independent recurrent neural network under attention mechanism for remote sensing image detection and segmentation. Our algorithm first assigns probabilistic weights to the combined features based on attention mechanism; then extracts deep features based on the features with high weights to generate labels with directions by using graph convolution network (GCNs) algorithms, extracts contextual semantic information of the images by using the independently recurrent neural network (IndRNN) algorithm; finally, our algorithm realizes image detection and segmentation by using Sigmoid.For remote sensing image detection and segmentation of populous euphratica forest as an instance, we prove that our feature extraction method and proposed ATGIR algorithm can effectively improve the detection and segmentation tasks.

Key words: attention mechanism, GCNs, IndRNN, parallel algorithm, word embedding

中图分类号:

TP391

尤洪峰, 田生伟, 禹龙, 等. 基于Word Embedding的遥感影像检测分割[J]. 电子学报, 2020, 48(1): 75-83.

YOU Hong-feng, TIAN Sheng-wei, YU Long, et al. Remote Sensing Image Detection and Segmentation Based on Word Embedding[J]. Acta Electronica Sinica, 2020, 48(1): 75-83.

参考文献

[1] WEI H,ZHANG H,GAO G.Representing word image spotting on historical document images[A].IEEE International Conference on Multimedia and Expo[C].US:IEEE,2017.1368-1373.
[2] TANG P,WANG H,KWONG S.Deep sequential fusion LSTM network for image description[J].Neurocomputing,2018,312:54-164.
[3] URICCHIO T,BALLAN L,SEIDENARI L,et al.Automatic image annotation via label transfer in the semantic space[J].Pattern Recognition,2017,71:144-157.
[4] MARCHEGGIANI D,TITOV I.Encoding sentences with graph convolutional networks for semantic role labeling[A].Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing[C]. US:ACL,2017.1506-1515.
[5] LI S,LI W,COOK C,et al.Independently recurrent neural network (indrnn):Building a longer and deeper RNN[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].US:IEEE,2018.5457-5466.
[6] 慕彩红,霍利利,刘逸,等.基于小波融合和PCA-核模糊聚类的遥感图像变化检测[J].电子学报,2014,43(7):1375-1381. MU Cai-hong,HUO Li-li,LIU Yi,et al.Change detection for remote sensing images based on wavelet fusion and PCA-kernel fuzzy clustering[J].Acta Electronica Sinica,2014,43(7):1375-1381.(in Chinese)
[7] 宋婉莹,李明,张鹏,等.基于加权合成核与三重Markov场的极化SAR图像分类方法[J].电子学报,2015,44(3):520-526. SONG Wan-ying,LI Ming,ZHANG Peng,et al.A classification method of PolSAR image based on weighted composite kernel and triplet Markov field[J].Acta Electronica Sinica,2015,44(3):520-526.(in Chinese)
[8] 李玉,袁永华,赵雪梅.可变类谱聚类遥感影像分割[J].电子学报,2018,46(12):3021-3028. LI Yu,YUAN Yong-hua,ZHAO Xue-mei.Spectral clustering of variable class for remote sensing image segmentation[J].Acta Electronica Sinica,2018,46(12):3021-3028.(in Chinese)
[9] XU Y,DU B,ZHANG L,et al.A band grouping based LSTM algorithm for hyperspectral image classification[A].Chinese Conference on Computer Vision[C].China:CCF,2017.421-432.
[10] HAN D,LIU Q,FAN W.A new image classification method using CNN transfer learning and web data augmentation[J].Expert Systems with Applications,2018,95:43-56.
[11] LIM H,RHYU S,LEE K.Chord Generation from Symbolic Melody Using BLSTM Networks[OL].https://arxiv.org/abs/1712.01011v1,2017.
[12] CLICHE M.BB_twtr at SemEval-2017 Task 4:Twitter sentiment analysis with CNNs and LSTMs[A].Proceedings of the 11th International Workshop on Semantic Evaluation[C].US:SemEval,2017.573-580.
[13] ROZENTAL A,FLEISCHER D.AMOBEE at SemEval-2018 Task 1:GRU neural network with a CNN attention mechanism for sentiment classification[A].Proceedings of the 12th International Workshop on Semantic Evaluation[C].US:SemEval,2018.218-225.
[14] MIWA M,BANSAL M.End-to-end relation extraction using LSTMs on sequences and tree structures[A].Association for Computational Linguistics[C].US:ACL,2016.1105-1116.
[15] KIM A Y,HA J G,CHOI H,et al.Automated text analysis based on skip-gram model for food evaluation in predicting consumer acceptance[A].Computational Intelligence and Neuroscience[C].US:Hindawi,2018.ID9293437.
[16] ALEXANDER ARIZA.Empirical line model for the atmospheric correction of Sentinel-2A MSI images in the caribbean islands journal[J].European Journal of Remote Sensing,2018,51(1):765-776.
[17] MA X,HOVY E.End-to-end sequence labeling via bi-directional LSTM-CNNS-CRF[A].Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics[C].US:ACL,2016.64-74.

基于Word Embedding的遥感影像检测分割

Remote Sensing Image Detection and Segmentation Based on Word Embedding

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	隗昊, 唐焕玲, 周爱, 张益嘉, 陈飞, 鲁明羽. 基于双路分段注意力神经张量网络的临床文本关系抽取[J]. 电子学报, 2023, 51(3): 658-665.
[2]	吴翼腾, 刘伟, 于溆乔. 基于参数差异假设的图卷积网络对抗性攻击[J]. 电子学报, 2023, 51(2): 330-341.
[3]	何滢婕, 刘月峰, 边浩东, 郭威, 张小燕. 基于Informer的电池荷电状态估算及其稀疏优化方法[J]. 电子学报, 2023, 51(1): 50-56.
[4]	王硕, 王坚, 王亚男, 宋亚飞. 一种基于特征融合的恶意代码快速检测方法[J]. 电子学报, 2023, 51(1): 57-66.
[5]	刘群, 谭洪胜, 张优敏, 王国胤. 基于元路径的动态异质网络表示学习[J]. 电子学报, 2022, 50(8): 1830-1839.
[6]	张志昌, 于沛霖, 庞雅丽, 朱林, 曾扬扬. SMGN：用于对话状态跟踪的状态记忆图网络[J]. 电子学报, 2022, 50(8): 1851-1858.
[7]	赵俊男, 佘青山, 孟明, 陈云. 基于多流空间注意力图卷积SRU网络的骨架动作识别[J]. 电子学报, 2022, 50(7): 1579-1585.
[8]	王延达, 陈炜通, 皮德常, 岳琳. 一种自适应记忆神经网络多跳读取与覆盖度机制结合的药物推荐模型[J]. 电子学报, 2022, 50(4): 943-953.
[9]	张凌明, 赵悦, 李鹏程, 刘洋, 高陈强. 基于局部注意力机制的三维牙齿模型分割网络[J]. 电子学报, 2022, 50(3): 681-690.
[10]	伍邦谷, 张苏林, 石红, 朱鹏飞, 王旗龙, 胡清华. 基于多分支结构的不确定性局部通道注意力机制[J]. 电子学报, 2022, 50(2): 374-382.
[11]	周登文, 李文斌, 李金新, 黄志勇. 一种轻量级的多尺度通道注意图像超分辨率重建网络[J]. 电子学报, 2022, 50(10): 2336-2346.
[12]	王波, 黄冕, 刘利军, 黄青松, 单文琦. 基于多层聚焦Inception-V3卷积网络的细粒度图像分类[J]. 电子学报, 2022, 50(1): 72-78.
[13]	赵琰, 赵凌君, 匡纲要. 基于注意力机制特征融合网络的SAR图像飞机目标快速检测[J]. 电子学报, 2021, 49(9): 1665-1674.
[14]	周东明, 张灿龙, 李志欣, 王智文. 基于多层级视觉融合的图像描述模型[J]. 电子学报, 2021, 49(7): 1286-1290.
[15]	黄名选. 关联模式挖掘与词向量学习融合的伪相关反馈查询扩展[J]. 电子学报, 2021, 49(7): 1305-1313.