计算机科学 ›› 2019, Vol. 46 ›› Issue (5): 260-265.doi: 10.11896/j.issn.1002-137X.2019.05.040

• 图形图像与模式识别 • 上一篇    下一篇

迁移学习模式下基于GoogLeNet网络的风电机组视觉检测

徐一鸣, 张娟, 刘成成, 顾菊平, 潘高超   

  1. (南通大学电气工程学院 江苏 南通226019)
  • 发布日期:2019-05-15
  • 作者简介:徐一鸣(1981-),男,博士,副教授,主要研究方向为数字图像处理及先进传感器技术;张 娟(1992-),女,硕士,主要研究方向为数字图像处理及机器视觉应用技术;刘成成(1995-),男,硕士,主要研究方向为数字图像处理及机器视觉应用技术;顾菊平(1971-),女,博士,教授,主要研究方向为微特电机及先进控制,E-mail:gu.jp@ntu.edu.cn(通信作者);潘高超(1994-),男,硕士,主要研究方向为数字图像处理及模式识别。
  • 基金资助:
    国家自然科学基金面上项目(61673226),南通市应用基础研究项目(GY12016018)资助。

Wind Turbine Visual Inspection Based on GoogLeNet Network in Transfer Learning Mode

XU Yi-ming, ZHANG Juan, LIU Cheng-cheng, GU Ju-ping, PAN Gao-chao   

  1. (School of Electrical Engineering,Nantong University,Nantong,Jiangsu 226019,China)
  • Published:2019-05-15

摘要: 针对无人机航拍环境下拍摄角度变换、特征不显著等干扰问题,提出一种改进的GoogLeNet卷积神经网络对风电机组进行识别和定位,无需人工预选取即可自动提取风电机组类别特征。通过GoogLeNet网络构造风电机组深度特征向量,在网络模型训练过程中引入迁移学习的概念,利用风电机组图像训练已预训练的GoogLeNet网络,在加快模型训练速度的同时,能避免分类网络陷入局部最优解。并在Faster RCNN框架下采用区域建议网络和多任务损失函数将候选区域搜索和边框回归融入到网络中,实现航拍图像中风电机组的自动分类和标注,缩短数据处理时间。实验结果表明,通过迁移学习的手段,利用优化的GoogLeNet网络能改善复杂航拍环境下的目标视觉检测准确率,完成风电机组自动定位任务,基于GoogLeNet的风电机组平均准确率达到了96%以上。

关键词: 风电机组, 视觉检测, 深度学习, 卷积神经网络, GoogLeNet模型, 迁移学习

Abstract: Aiming at the interference of shooting angle changes and insignificant features in the drone aerial photography environment,this paper proposed an improved GoogLeNet convolutional neural network to identify and locate the wind turbines,which can automatically extract wind turbine category features without manual pre-selection.The deep feature vectors of wind turbines are constructed through GoogLeNet network.In the network model training process,the concept of transfer learning is introduced and the pre-trained GoogLeNet network is trained by using wind turbine images.The classification network can be prevented from falling into the local optimal solution while speeding up the model training.The region proposal network and the multi-task loss function are used to integrate the candidate region search and border regression into the network in the Faster RCNN framework,so that the wind turbines in the aerial image can be automatically classified and annotated,and the time complexity can be reduced.Experimental results show that the optimized GoogLeNet network can improve the accuracy of target visual detection in the complex aerial photography environment and complete the task of wind turbine automatic positioning by means of transfer learning.The avera-ge accuracy of wind turbines based on GoogLeNet is over 96%.

Key words: Wind turbine, Visual inspection, Deep learning, Convolutional neural network, GoogLeNet model, Transfer learning

中图分类号: 

  • TP391
[1]ZHANG H,WANG K F,WANG F Y.Advances and perspec-tives on applications of deep learning in visual object detection[J].Acta Automatica Sinica,2017,43(8):1289-1305.(in Chinese)张慧,王坤峰,王飞跃.深度学习在目标视觉检测中的应用进展与展望[J].自动化学报,2017,43(8):1289-1305.
[2]WEI Y M.Research on aerial image location based on convolution neural network [J].Ship Electronic Engineering,2017,37(6):33-37.(in Chinese)魏湧明.基于卷积神经网络的航拍图像定位研究[J].舰船电子工程,2017,37(6):33-37.
[3]SUN Z Y,LU C X,SHI Z Z,et al.Research and advances on deep learning [J].Computer Science,2016,43(2):1-8.(in Chinese)孙志远,鲁成祥,史忠植,等.深度学习研究与进展[J].计算机科学,2016,43(2):1-8.
[4]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE Press,2014:580-587.
[5]GIRSHICK R.Fast R-CNN[C]∥Proceedings of IEEE International Conference on Computer Vision.Chile:IEEE Press,2015:1440-1448.
[6]REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:to-wards real-time object detection with region proposal networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[7]SZEGEDY C,LIU W,JIA Y Q,et al.Going deeper with convolutions[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE Press,2015:1-9.
[8]LI Y D,HAO Z B,LEI H.Survey of convolutional neural network [J].Journal of Computer Applications,2016,36(9):2508-2515,2565.(in Chinese)李彦东,郝宗波,雷航.卷积神经网络研究综述[J].计算机应用,2016,36(9):2508-2515,2565.
[9]ZHOU J Y,ZHAO Y M.Application of convolution neural network in image classification and object detection [J].Computer Engineering and Applications,2017,53(13):34-41.(in Chinese)周俊宇,赵艳明.卷积神经网络在图像分类和目标检测应用综述[J].计算机工程与应用,2017,53(13):34-41.
[10]LI X D,YE M,LI T.Review of object detection based on convolutional neural networks [J].Application Research of Compu-ters,2017,34(10):2881-2886,2891.(in Chinese)李旭东,叶茂,李涛.基于卷积神经网络的目标检测研究综述[J].计算机应用研究,2017,34(10):2881-2886,2891.
[11]WANG Z M,CAO H J,FAN L.Method on human activity re-cognition based on convolutional neural networks [J].Computer Science,2016,43(11A):56-58,87.(in Chinese)王忠民,曹洪江,范琳.一种基于卷积神经网络深度学习的人体行为识别方法[J].计算机科学,2016,43(11A):56-58,87.
[12]FENG Y S,WANG Z L.Fine-grained image categorization with segmentation based on top-down attention map [J].Journal of Image and Graphics,2016,21(9):1147-1154.(in Chinese)冯语姗,王子磊.自上而下注意图分割的细粒度图像分类[J].中国图象图形学报,2016,21(9):1147-1154.
[13]DAI C K,LI Y.Aeroplane detection in static aerodrome based on Faster RCNN and multi-part model[J].Journal of Computer Applications,2017,37(S2):85-88.(in Chinese)戴陈卡,李毅.基于Faster RCNN以及多部件结合的机场场面静态飞机检测[J].计算机应用,2017,37(S2):85-88.
[14]PENG G,YANG S Q,HUANG X H,et al.Improved object detection method of micro-operating system based on regioncon-volutional neural network [J].Pattern Recognition and Artificial Intelligence,2018,31(2):142-149.(in Chinese)彭刚,杨诗琪,黄心汉,等.改进的基于区域卷积神经网络的微操作系统目标检测方法[J].模式识别与人工智能,2018,31(2):142-149.
[15]ZHUANG F Z,LUO P,HE Q,et al.Survey on transfer learning research[J].Journal of Software,2015,26(1):26-39.(in Chinese)庄福振,罗平,何清,等.迁移学习研究与进展[J].软件学报,2015,26(1):26-39.
[16]DAI W Y,YANG Q,XUE G R,et al.Boosting for transfer learning[C]∥Proceedings of International Conference on Machine Learning.USA:IEEE Press,2007:193-200.
[17]WU L N,HUANG Y P,ZHENG X.Noval transfer learning algorithm based on bag-of-visual words model[J].ComputerScien-ce,2014,41(12):260-263,274.(in Chinese)吴丽娜,黄雅平,郑翔.基于词带模型的迁移学习算法[J].计算机科学,2014,41(12):260-263,274.
[1] 单美静, 秦龙飞, 张会兵. L-YOLO:适用于车载边缘计算的实时交通标识检测模型[J]. 计算机科学, 2021, 48(1): 89-95.
[2] 何彦辉, 吴桂兴, 吴志强. 基于域适应的X光图像的目标检测[J]. 计算机科学, 2021, 48(1): 175-181.
[3] 李亚男, 胡宇佳, 甘伟, 朱敏. 基于深度学习的miRNA靶位点预测研究综述[J]. 计算机科学, 2021, 48(1): 209-216.
[4] 王瑞平, 贾真, 刘畅, 陈泽威, 李天瑞. 基于DeepFM的深度兴趣因子分解机网络[J]. 计算机科学, 2021, 48(1): 226-232.
[5] 于文家, 丁世飞. 基于自注意力机制的条件生成对抗网络[J]. 计算机科学, 2021, 48(1): 241-246.
[6] 仝鑫, 王斌君, 王润正, 潘孝勤. 面向自然语言处理的深度学习对抗样本综述[J]. 计算机科学, 2021, 48(1): 258-267.
[7] 欧阳鹏, 陆璐, 张凡龙, 邱少健. 基于迁移学习和过采样技术的跨项目克隆代码一致性维护需求预测[J]. 计算机科学, 2020, 47(9): 10-16.
[8] 丁钰, 魏浩, 潘志松, 刘鑫. 网络表示学习算法综述[J]. 计算机科学, 2020, 47(9): 52-59.
[9] 何鑫, 许娟, 金莹莹. 行为关联网络:完整的变化行为建模[J]. 计算机科学, 2020, 47(9): 123-128.
[10] 张佳嘉, 张小洪. 多分支卷积神经网络肺结节分类方法及其可解释性[J]. 计算机科学, 2020, 47(9): 129-134.
[11] 叶亚男, 迟静, 于志平, 战玉丽, 张彩明. 基于改进CycleGan模型和区域分割的表情动画合成[J]. 计算机科学, 2020, 47(9): 142-149.
[12] 朱玲莹, 桑庆兵, 顾婷婷. 基于视差信息的无参考立体图像质量评价[J]. 计算机科学, 2020, 47(9): 150-156.
[13] 邓良, 许庚林, 李梦杰, 陈章进. 基于深度学习与多哈希相似度加权实现快速人脸识别[J]. 计算机科学, 2020, 47(9): 163-168.
[14] 崔彤彤, 王桂玲, 高晶. 基于1DCNN-LSTM的船舶轨迹分类方法[J]. 计算机科学, 2020, 47(9): 175-184.
[15] 刘海潮, 王莉. 基于深度图卷积胶囊网络的图分类模型[J]. 计算机科学, 2020, 47(9): 219-225.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[2] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[3] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[4] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[5] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[6] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[7] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[8] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[9] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .
[10] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .