基于弱语义注意力的遥感图像可解释目标检测

doi:10.12263/DZXB.20200554

电子学报 ›› 2021, Vol. 49 ›› Issue (4): 679-689.DOI: 10.12263/DZXB.20200554

基于弱语义注意力的遥感图像可解释目标检测

周勇^1,2, 陈思霖^1,2, 赵佳琦^1,2,3, 张迪^1,2, 王瀚正^1,2

1. 中国矿业大学计算机科学与技术学院, 江苏徐州 221116;
2. 矿山数字化教育部工程研究中心, 江苏徐州 221116;
3. 灾害智能防控与应急救援创新研究中心, 江苏徐州 221116

收稿日期:2020-06-10 修回日期:2020-12-11 出版日期:2021-04-25 发布日期:2021-04-25
作者简介:周勇男,1974年9月出生于江苏省徐州市,中国矿业大学计算机科学与技术学院教授.主要研究方向为数据挖掘、机器学习和人工智能.E-mail:yzhou@cumt.edu.cn;陈思霖 男,1998年4月出生于吉林省吉林市,中国矿业大学计算机科学与技术学院硕士研究生.主要研究方向为计算机视觉、图像处理、目标检测.E-mail:silin.chen@cumt.edu.cn
基金资助:
国家自然科学基金（No.61806206）；江苏省自然科学基金（No.BK20180639，No.BK20201346）；江苏省六大高峰人才项目（No.2015-DZXX-010）

Weakly Semantic Based Attention Network for Interpretable Object Detection in Remote Sensing Imagery

ZHOU Yong^1,2, CHEN Si-lin^1,2, ZHAO Jia-qi^1,2,3, ZHANG Di^1,2, WANG Han-zheng^1,2

1. School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China;
2. Ministry of Education Engineering Research Center of Mine Digitization, Xuzhou, Jiangsu 221116, China;
3. Innovation Research Center of Disaster Intelligent Prevention and Emergency Rescue, Xuzhou, Jiangsu 221116, China

Received:2020-06-10 Revised:2020-12-11 Online:2021-04-25 Published:2021-04-25

摘要/Abstract

摘要： 近些年来随着遥感技术的快速发展，遥感图像目标检测成为了当前的研究热点.针对遥感图像背景复杂以及现有目标检测模型缺乏可解释性等问题，本文提出了一种基于弱语义注意力的遥感图像可解释目标检测方法.具体地，首先通过多层级特征金字塔来解决遥感图像中目标尺度变化范围大的问题.其次，利用检测框的角度回归来解决遥感图像目标定向的问题.然后，基于弱语义分割网络产生强化目标特征的注意力权重值，抑制背景噪声.最终用网络剖析的分析方法，获取模型中卷积核对应的可解释性语义概念.实验结果表明，本文提出的算法在遥感图像目标检测的准确性以及对背景噪声抑制上有较好的表现，并且通过可解释性算法在一定程度上使本文提出的模型易于理解.

关键词: 目标检测, 遥感图像, 注意力网络, 弱语义, 深度学习可解释性

Abstract: In recent years,the object detection in remote sensing imagery has been a hot research spot with the development of remote sensing technique.To deal with the complex background in the imagery and the detection model’s interpretability,we propose a weakly semantic based attention network for interpretable object detection model in remote sensing imagery.Firstly,a feature pyramid network is devised for the variation of object scales.Next,an angle is added to the regression to better locate the object.Thirdly,we add a weakly semantic segmentation network to enhance feature and filter the noisy information in the background.Finally,the model is dissected by the proposed method to get the interpretable semantic concepts of convolutional kernel.Experiments validated that the model has a good performance in the aspect of suppressing the background noise and make our model easy to comprehend.

Key words: object detection, remote sensing imagery, attention network, weakly semantic, deep learning interpretability

中图分类号:

TP753

周勇, 陈思霖, 赵佳琦, 张迪, 王瀚正. 基于弱语义注意力的遥感图像可解释目标检测[J]. 电子学报, 2021, 49(4): 679-689.

ZHOU Yong, CHEN Si-lin, ZHAO Jia-qi, ZHANG Di, WANG Han-zheng. Weakly Semantic Based Attention Network for Interpretable Object Detection in Remote Sensing Imagery[J]. Acta Electronica Sinica, 2021, 49(4): 679-689.

参考文献

[1] Zhang Q,Zhu S C.Visual interpretability for deep learning:a survey[J].Frontiers of Information Technology & Electronic Engineering,2018,19(1):27-39.
[2] Lin T Y,Goyal P,Girshick R,et al.Focal loss for dense object detection[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2017.2980-2988.
[3] Xia G S,Bai X,Ding J,et al.DOTA:A large-scale dataset for object detection in aerial images[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Los Alamitos:IEEE Computer Society Press,2018.3974-3983.
[4] Bau D,Zhou B,Khosla A,et al.Network dissection:Quantifying interpretability of deep visual representations[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Los Alamitos:IEEE Computer Society Press,2017.6541-6549.
[5] 张顺,龚怡宏,王进军.深度卷积神经网络的发展及其在计算机视觉领域的应用[J].计算机学报,2019,42(3):453-482. Zhang S,Gong Y H,Wang J J.The development of deep convolution neural network and its applications on computer vision[J].Chinese Journal of Computers,2019,42(3):453-482.(in Chinese)
[6] Girshick R,Donahue J,Darrell T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Los Alamitos:IEEE Computer Society Press,2014.580-587.
[7] Girshick R.Fast r-cnn[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2015.1440-1448.
[8] Ren S,He K,Girshick R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[A].Advances in Neural Information Processing Systems[C].Cambridge:MIT Press,2015.91-99.
[9] He K,Gkioxari G,Dollár P,et al.Mask r-cnn[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2017.2961-2969.
[10] Cai Z,Vasconcelos N.Cascade r-cnn:Delving into high quality object detection[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2018.6154-6162.
[11] Liu W,Anguelov D,Erhan D,et al.SSD:Single shot multibox detector[A].European Conference on Computer Vision[C].Cham:Springer,2016.21-37.
[12] Redmon J,Divvala S,Girshick R,et al.You only look once:Unified,real-time object detection[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2016.779-788.
[13] Redmon J,Farhadi A.YOLO9000:better,faster,stronger[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2017.7263-7271.
[14] Redmon J,Farhadi A.Yolov3:An incremental improvement[J].ArXiv Preprint,2018,arXiv:1804.02767.
[15] Samek W,Wiegand T,Müller K R.Explainable artificial intelligence:Understanding,visualizing and interpreting deep learning models[J].ArXiv Preprint,2017,arXiv:1708.08296.
[16] Zeiler M D,Fergus R.Visualizing and understanding convolutional networks[A].European Conference on Computer Vision[C].Cham:Springer,2014.818-833.
[17] Zhou B,Khosla A,Lapedriza A,et al.Object detectors emerge in deep scene cnns[J].ArXiv Preprint,2014,arXiv:1412.6856.
[18] Goyal Y,Mohapatra A,Parikh D,et al.Towards transparent AI systems:Interpreting visual question answering models[J].ArXiv Preprint,2016,arXiv:1608.08974.
[19] 张峰,钟宝江.基于兴趣目标的图像检索[J].电子学报,2018,46(8):1915-1923. Zhang F,Zhong B J.Image retrieval based on interested objects[J].Acta Electronica Sinica,2018,46(8):1915-1923.(in Chinese)
[20] Lin T Y,Dollár P,Girshick R,et al.Feature pyramid networks for object detection[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2017.2117-2125.
[21] He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Los Alamitos:IEEE Computer Society Press,2016.770-778.
[22] 李宝奇,贺昱曜,何灵蛟,等.基于全卷积神经网络的非对称并行语义分割模型[J].电子学报,2019,47(5):1058-1064. Li B Q,He Y Y,He L J,et al.Asymmetric parallel semantic segmentation model based on full convolutional neural network[J].Acta Electronica Sinica,2019,47(5):1058-1064.(in Chinese)
[23] Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2015.3431-3440.
[24] Ma J,Shao W,Ye H,et al.Arbitrary-oriented scene text detection via rotation proposals[J].IEEE Transactions on Multimedia,2018,20(11):3111-3122.
[25] 黄德根,张云霞,林红梅,邹丽,刘壮.基于规则推理网络的分类模型[J].软件学报,2020,31(4):1063-1078. Huang D G,Zhang Y X,Lin H M,Zou L,Liu Z.Rule inference network model for classification[J].Journal of Software,2020,31(4):1063-1078.(in Chinese)
[26] Zhou B,Zhao H,Puig X,et al.Scene parsing through ade20k dataset[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2017.633-641.
[27] Bell S,Bala K,Snavely N.Intrinsic images in the wild[J].ACM Transactions on Graphics,2014,33(4):1-12.
[28] Mottaghi R,Chen X,Liu X,et al.The role of context for object detection and semantic segmentation in the wild[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2014.891-898.
[29] Chen X,Mottaghi R,Liu X,et al.Detect what you can:Detecting and representing objects using holistic models and body parts[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2014.1971-1978.
[30] Cimpoi M,Maji S,Kokkinos I,et al.Describing textures in the wild[A].Proceedings of the IEEE International Conference on Computer Vision[C].Los Alamitos:IEEE Computer Society Press,2014.3606-3613.
[31] Dai J,Li Y,He K,et al.R-fcn:Object detection via region-based fully convolutional networks[A].Advances in Neural Information Processing Systems[C].Cambridge:MIT Press,2016.379-387.
[32] Lin Y,Feng P,Guan J.IENET:Interacting embranchment one stage anchor free detector for orientation aerial object detection[J].ArXiv Preprint,2019,arXiv:1912.00969.
[33] Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[A].Advances in Neural Information Processing Systems[C].Nevada:Lake Tahoe,2012.1097-1105.

基于弱语义注意力的遥感图像可解释目标检测

Weakly Semantic Based Attention Network for Interpretable Object Detection in Remote Sensing Imagery

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]	杨曦, 张鑫, 郭浩远, 王楠楠, 高新波. 基于不变特征的多源遥感图像舰船目标检测算法[J]. 电子学报, 2022, 50(4): 887-899.
[2]	严莉, 张凯, 徐浩, 韩圣亚, 刘珅岐, 史玉良. 基于图注意力机制和Transformer的异常检测[J]. 电子学报, 2022, 50(4): 900-908.
[3]	肖进胜, 张舒豪, 陈云华, 王元方, 杨力衡. 双向特征融合与特征选择的遥感影像目标检测[J]. 电子学报, 2022, 50(2): 267-272.
[4]	骈纬国, 吴映波, 陈蒙, 蔡俊鹏. 一种基于时空动态图注意力网络的共享出行需求预测方法[J]. 电子学报, 2022, 50(2): 432-439.
[5]	罗会兰, 袁璞, 童康. 基于深度学习的显著性目标检测方法综述[J]. 电子学报, 2021, 49(7): 1417-1427.
[6]	程旭, 宋晨, 史金钢, 周琳, 张毅锋, 郑钰辉. 基于深度学习的通用目标检测研究综述[J]. 电子学报, 2021, 49(7): 1428-1438.
[7]	李志欣, 凌锋, 张灿龙, 马慧芳. 融合两级相似度的跨媒体图像文本检索[J]. 电子学报, 2021, 49(2): 268-274.
[8]	王洪雁, 张海坤, 罗宇华, 汪祖民. 复杂动态背景下基于群稀疏的运动目标检测方法[J]. 电子学报, 2021, 49(12): 2330-2338.
[9]	罗大鹏, 杜国庆, 曾志鹏, 魏龙生, 高常鑫, 陈应, 肖菲, 罗琛. 基于少量样本学习的多目标检测跟踪方法[J]. 电子学报, 2021, 49(1): 183-191.
[10]	李琳, 唐守廉. 基于多层注意力表示的音乐推荐模型[J]. 电子学报, 2020, 48(9): 1672-1679.
[11]	李维刚, 叶欣, 赵云涛, 王文波. 基于改进YOLOv3算法的带钢表面缺陷检测[J]. 电子学报, 2020, 48(7): 1284-1292.
[12]	秦福强, 王丽芳. 基于变分的多尺度遥感图像融合算法[J]. 电子学报, 2020, 48(6): 1084-1090.
[13]	罗会兰, 陈鸿坤. 基于深度学习的目标检测研究综述[J]. 电子学报, 2020, 48(6): 1230-1239.
[14]	刘颖, 刘红燕, 范九伦, 公衍超, 李莹华, 王富平, 卢津. 基于深度学习的小目标检测研究与应用综述[J]. 电子学报, 2020, 48(3): 590-601.
[15]	孟祥伟. 量化秩非参数CFAR检测器在杂波边缘中的性能分析[J]. 电子学报, 2020, 48(2): 384-389.