[1]孙光民,陈佳阳,李冰,等.双尺度网络高分辨率楼面影像微小缺陷检测[J].哈尔滨工程大学学报,2021,42(2):286-293.[doi:10.11990/jheu.201909096]
 SUN Guangmin,CHEN Jiayang,LI Bing,et al.Detection of small defects on a building wall surface from high-resolution images using dual-scale neural networks[J].Journal of Harbin Engineering University,2021,42(2):286-293.[doi:10.11990/jheu.201909096]
点击复制

双尺度网络高分辨率楼面影像微小缺陷检测(/HTML)
分享到:

《哈尔滨工程大学学报》[ISSN:1006-6977/CN:61-1281/TN]

卷:
42
期数:
2021年2期
页码:
286-293
栏目:
出版日期:
2021-02-05

文章信息/Info

Title:
Detection of small defects on a building wall surface from high-resolution images using dual-scale neural networks
作者:
孙光民1 陈佳阳1 李冰2 李煜1 闫冬1
1. 北京工业大学 信息学部, 北京 100124;
2. 中国烟草总公司 北京市公司, 北京 100020
Author(s):
SUN Guangmin1 CHEN Jiayang1 LI Bing2 LI Yu1 YAN Dong1
1. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China;
2. China National Tobacco Corporation Beijing Corporation, Beijing 100020, China
关键词:
目标检测墙面缺陷高分辨率检测器卷积神经网络多尺度滑窗负反馈技术
分类号:
TP391.4
DOI:
10.11990/jheu.201909096
文献标志码:
A
摘要:
为了便于对建筑外墙瓷砖松动和开裂现象进行定期排查以保证周围居民的人身安全,本文提出了一种通过高分辨率相机拍摄的楼面图像进行微小缺陷自动检测的方法。将原始检测任务划分为大尺度下的非墙体分割任务以及小尺度下的缺陷检测任务;分别针对这些任务训练相应的深度模型并应用其进行处理;将这些多尺度任务的处理结果进行融合,得到微小缺陷的最终检测结果。实验表明:本文算法在精度和效率上都要明显优于单尺度方法。本文算法已在某小区实际部署运行并取得了良好的效果,具有很高的实用价值。

参考文献/References:

[1] GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile:IEEE, 2015:1440-1448.
[2] REN Shaoqing, HE Kaiming, GIRSHICK R B, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6):1137-1149.
[3] HE Kaiming, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy:IEEE, 2017.
[4] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD:single shot MultiBox detector[C]//Proceedings of the 14th European Conference European Conference on Computer Vision. Amsterdam:Springer, 2016:21-37.
[5] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV:IEEE, 2016.
[6] REDMON J, FARHADI A. YoLOv3:an incremental improvement[J]. arXiv:1804.02767, 2018.
[7] REDMON J, FARHADI A. YOLO9000:better, faster, stronger[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI:IEEE:2017:6517-6525, DOI:10.1109/CVPR.2017.690.
[8] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI:IEEE, 2017:936-944, DOI:10.1109/CVPR.2017.106.
[9] VAN ETTEN A. You only look twice:rapid multi-scale object detection in satellite imagery[J]. arXiv:1805.09512, 2018.
[10] 胡昌华, 陈辰, 何川, 等. 基于深度卷积神经网络的SAR图像舰船小目标检测[J]. 中国惯性技术学报, 2019, 27(3):397-405, 414.HU Changhua, CHEN Chen, HE Chuan, et al. SAR detection for small target ship based on deep convolutional neural network[J]. Journal of Chinese inertial technology, 2019, 27(3):397-405, 414.
[11] 于洋, 李世杰, 陈亮, 等. 基于改进YOLO v2的船舶目标检测方法[J]. 计算机科学, 2019, 46(8):332-336.YU Yang, LI Shijie, CHEN Liang, et al. Ship target detection based on improved YOLO v2[J]. Computer science, 2019, 46(8):332-336.
[12] VAN ETTEN A. Satellite imagery multiscale rapid detection with windowed networks[J]. arXiv:1809.09978, 2018.
[13] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2):91-110.
[14] ADAMS R, BISCHOF L. Seeded region growing[J]. IEEE transactions on pattern analysis and machine intelligence, 1994, 16(6):641-647.
[15] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV:IEEE, 2016:770-778, DOI:10.1109/CVPR.2016.90.
[16] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). Venice:IEEE, 2017:2999-3007.
[17] HUANG J, RATHOD V, SUN Chen, et al. Speed/accuracy trade-offs for modern convolutional object detectors[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI:IEEE, 2017.
[18] SHAO Ling, ZHU Fan, LI Xuelong. Transfer learning for visual categorization:a survey[J]. IEEE transactions on neural networks and learning systems, 2015, 26(5):1019-1034.
[19] PAN S J, YANG Qiang. A survey on transfer learning[J]. IEEE transactions on knowledge and data engineering, 2010, 22(10):1345-1359, DOI:10.1109/TKDE.2009.191.
[20] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO:common objects in context[C]//Proceedings of the 13th European Conference European Conference on Computer Vision. Zurich, Switzerland:Springer, 2014.

相似文献/References:

[1]万磊,曾文静,张铁栋,等.近海岸目标快速提取[J].哈尔滨工程大学学报,2012,(09):1158.[doi:10.3969/j.issn.1006-7043.201110043]
 WAN Lei,ZENG Wenjing,ZHANG Tiedong,et al.Fast extraction of offshore targets based on sea line detection[J].Journal of Harbin Engineering University,2012,(2):1158.[doi:10.3969/j.issn.1006-7043.201110043]
[2]赵春晖,李晓慧,朱海峰.空间4邻域稀疏表示的高光谱图像目标检测 [J].哈尔滨工程大学学报,2013,(09):1152.[doi:10.3969/j.issn.1006-7043. 201207005]
[3]赵春晖,靖晓昊,李威.基于StOMP稀疏方法的高光谱图像目标检测[J].哈尔滨工程大学学报,2015,(07):992.[doi:10.3969/j.issn.1006-7043.201404087]
 ZHAO Chunhui,JING Xiaohao,LI Wei.Hyperspectral image target detection algorithm based on StOMP sparse representation[J].Journal of Harbin Engineering University,2015,(2):992.[doi:10.3969/j.issn.1006-7043.201404087]
[4]李子高,李淑秋,闻疏琳.基于无人平台的水下目标自动检测方法[J].哈尔滨工程大学学报,2017,38(01):103.[doi:10.11990/jheu.201601012]
 LI Zigao,LI Shuqiu,WEN Shulin.Automatic detection of an underwater target based on UUV[J].Journal of Harbin Engineering University,2017,38(2):103.[doi:10.11990/jheu.201601012]
[5]时胜国,祝文昭,李赢,等.基于特征值多阈值修正的声矢量圆阵信源数检测[J].哈尔滨工程大学学报,2017,38(01):120.[doi:10.11990/jheu.201511028]
 SHI Shengguo,ZHU Wenzhao,LI Ying,et al.Source number detection based on multi-threshold eigenvalue correction using uniform circular acoustic vector sensor array[J].Journal of Harbin Engineering University,2017,38(2):120.[doi:10.11990/jheu.201511028]
[6]赵春晖,孟美玲,闫奕名.基于字典重构的高光谱图像亚像元目标检测[J].哈尔滨工程大学学报,2018,39(09):1582.[doi:10.11990/jheu.201707008]
 ZHAO Chunhui,MENG Meiling,YAN Yiming.Sub-pixel target detection on hyperspectral image based on dictionary reconstruction[J].Journal of Harbin Engineering University,2018,39(2):1582.[doi:10.11990/jheu.201707008]
[7]韩骁枫,陆建峰,李祥瑞,等.一种基于激光雷达传感器的行人检测方法[J].哈尔滨工程大学学报,2019,40(06):1149.[doi:10.11990/jheu.201803119]
 HAN Xiaofeng,LU Jianfeng,LI Xiangrui,et al.Pedestrian detection method based on LIDAR sensors[J].Journal of Harbin Engineering University,2019,40(2):1149.[doi:10.11990/jheu.201803119]
[8]王言鹏,杨飏,姚远.用于内河船舶目标检测的单次多框检测器算法[J].哈尔滨工程大学学报,2019,40(07):1258.[doi:10.11990/jheu.201805057]
 WANG Yanpeng,YANG Yang,YAO Yuan.Single shot multibox detector for ships detection in inland waterway[J].Journal of Harbin Engineering University,2019,40(2):1258.[doi:10.11990/jheu.201805057]
[9]朱健楠,虞梦苓,杨益新.无人水面艇感知技术发展综述[J].哈尔滨工程大学学报,2020,41(10):1486.[doi:10.11990/jheu.202007111]
 ZHU Jiannan,YU Mengling,YANG Yixin.Overview of development of unmanned-surface-vehicle sensing technology[J].Journal of Harbin Engineering University,2020,41(2):1486.[doi:10.11990/jheu.202007111]

备注/Memo

备注/Memo:
收稿日期:2019-09-26。
基金项目:国家重点研发计划(2018YFF01012300);国家自然科学基金项目(11527801,41706201).
作者简介:孙光民,男,教授,博士生导师;李煜,男,副教授,博士生导师.
通讯作者:李煜,E-mail:yuli@bjut.edu.cn.
更新日期/Last Update: 2021-02-27