深度卷积网络支持下的遥感影像井盖部件检测

doi:10.13474/j.cnki.11-2246.2019.0256

测绘通报 ›› 2019, Vol. 0 ›› Issue (8): 78-81,87.doi: 10.13474/j.cnki.11-2246.2019.0256

深度卷积网络支持下的遥感影像井盖部件检测

杨梦圆¹, 刘伟^1,2, 尹鹏程³, 谢梦¹

1. 江苏师范大学地理测绘与城乡规划学院, 江苏徐州 221116;
2. 资源与环境信息系统国家重点实验室, 北京 100101;
3. 徐州市国土资源局, 江苏徐州 221006

收稿日期:2018-12-24 出版日期:2019-08-25 发布日期:2019-09-06
通讯作者: 刘伟。E-mail:grid_gis@126.com E-mail:grid_gis@126.com
作者简介:杨梦圆(1995-),女,硕士生,研究方向为遥感图像处理与目标识别。E-mail:ymy2018@126.com
基金资助:
国家自然科学基金（41601405）；江苏省国土资源科技项目（2018054）；徐州市国土资源科技项目（XZGTKJ2018001）；江苏省研究生科研与实践创新计划项目（KYCX18_2163）

Manhole cover object detection in remote sensing imagery with deep convolutional neural networks

YANG Mengyuan¹, LIU Wei^1,2, YIN Pengcheng³, XIE Meng¹

1. School of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou 221116, China;
2. State Key Laboratory of Resources and Environmental Information System, Beijing 100101, China;
3. Bureau of Land and Resources of Xuzhou, Xuzhou 221006, China

Received:2018-12-24 Online:2019-08-25 Published:2019-09-06

摘要/Abstract

摘要： 数字城市管理发展中城市部件调查是一项重要的任务，但是城市井盖部件信息获取存在人工调绘效率低、精度难以保证等缺陷，影响城市井盖部件的及时更新。因此本文利用深度卷积神经网络模型，通过小卷积核、尾部裁剪和保持输入大小等改进边缘检测网络（HED）并增加两层卷积运算提取目标，提出HED-C网络模型，实现了端到端的井盖部件目标检测。试验结果表明，利用HED-C模型井盖部件召回率可达96.58%，查准率可达97.93%，相较Faster R-CNN、YOLO和SSD网络模型，综合性能有了较大提高。

关键词: 井盖, 遥感图像, 目标检测, 深度卷积网络, 端到端

Abstract: Urban component survey is an important task in the development of digital city management. However, the manhole cover information acquisition still has shortcomings such as low efficiency of manual surveying and high leakage rate. To address these problems, this paper proposes an effective method for detecting manhole cover objects in remote sensing images. We redesign the feature extractor by adopting VGG (visual geometry group) and HED (holistically-nested edge detection) side-output module, which can increase the variety of receptive field size. Then, the detection is performed by a multi-level convolution matching network for object detection based on fused feature maps, which combines several feature maps that enables small and densely packed manhole cover objects to produce stronger response. The results show that the proposed method is more accurate than existing methods for detecting manhole cover in remote sensing images.

Key words: manhole cover, remote sensing images, object detection, deep convolutional neural networks, end to end

中图分类号:

P237

杨梦圆, 刘伟, 尹鹏程, 谢梦. 深度卷积网络支持下的遥感影像井盖部件检测[J]. 测绘通报, 2019, 0(8): 78-81,87.

YANG Mengyuan, LIU Wei, YIN Pengcheng, XIE Meng. Manhole cover object detection in remote sensing imagery with deep convolutional neural networks[J]. 测绘通报, 2019, 0(8): 78-81,87.

参考文献

[1] 王涛, 郑志宏, 张敏. 泉州市数字化城市管理部件普查方法研究[J]. 测绘通报, 2013(S1):246-248.
[2] 李淑清, 高远, 范咪娜. 一种高效的城市部件普查方法[J]. 测绘工程, 2016, 25(11):76-80.
[3] 宋杨, 曾凡洋, 高志国. 车载全景摄影测量在城市部件普查中的应用[J]. 测绘科学, 2016, 41(11):40-43.
[4] 李席锋, 汤竞煌, 李辉. 移动测量技术在数字城市部件普查中的应用[J]. 国土资源导刊, 2017, 14(1):53-57.
[5] 余建伟, 林伟恩. 中海达高精度移动测量系统在城市部件普查中的应用[J]. 测绘通报, 2016(8):147-148.
[6] LEFEVRE S, WEBER J, SHEEREN D. Automatic building extraction in VHR images using advanced morphological operators[C]//Urban Remote Sensing Joint Event. Paris:IEEE, 2007.
[7] TRINDER J C, WANG Y. Knowledge-based road interpretation in aerial images[J]. International Archives of Photogrammetry and Remote Sensing, 1998(32):635-640.
[8] BLASCHKE T, HAY G J, KELLY M, et al. Geographic object-based image analysis-towards a new paradigm[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 87(100):180-191.
[9] CHENG G, HAN J, GUO L, et al. Object detection in remote sensing imagery using a discriminatively trained mixture model[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 85(9):32-43.
[10] CHENG G, HAN J, ZHOU P, et al. Multi-class geospatial object detection and geographic image classification based on collection of part detectors[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 98(1):119-132.
[11] CHENG G, HAN J, ZHOU P, et al. Scalable multi-class geospatial object detection in high-spatial-resolution remote sensing images[C]//Proceedings of the Geoscience and Remote Sensing Symposium.Quebec:IEEE, 2014:2479-2482.
[12] ZHAO Y Q, YANG J. Hyperspectral image denoising via sparse representation and low-rank constraint[J].IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1):296-308.
[13] GRABNER H, NGUYEN T T, GRUBER B, et al. On-line boosting-based car detection from aerial images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2008, 63(3):382-396.
[14] HUANG X, ZHANG L. Road centreline extraction from high-resolution imagery based on multiscale structural features and support vector machines[J]. International Journal of Remote Sensing, 2009, 30(8):1977-1987.
[15] ZHANG W, SUN X, FU K, et al. Object detection in high-resolution remote sensing images using rotation invariant parts based model[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(1):74-78.
[16] ZHANG W, SUN X, WANG H, et al. A generic discriminative part-based model for geospatial object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 99(1):30-44.
[17] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[18] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the Computer Vision and Pattern Recongnition.Columbus:IEEE, 2014:580-587.
[19] GIRSHICK R. Fast R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision.Santiago:IEEE, 2015.
[20] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137-1149.
[21] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real-time object detection[C]//Proceedings of the Computer Vision and Pattern Recognition.Las Vegas:IEEE, 2016:779-788.
[22] LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot multibox detector[C]//Proceedings of the European Conference on Computer Vision.Amsterdam:Springer International Publishing, 2016:21-37.
[23] XIE S, TU Z. Holistically-nested edge detection[J]. International Journal of Computer Vision, 2015, 125(1-3):3-18.

深度卷积网络支持下的遥感影像井盖部件检测

Manhole cover object detection in remote sensing imagery with deep convolutional neural networks

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

本文评价

[1]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[2]	文奴, 郭仁忠, 贺彪, 万远. YOLO v4框架下Multi-Patch多帧增量式交通视频目标检测[J]. 测绘通报, 2022, 0(5): 38-44.
[3]	段晨阳, 冯建中, 全斌, 白林燕, 王盼盼. 利用深度学习进行GF-6影像枣园检测识别[J]. 测绘通报, 2022, 0(3): 54-59.
[4]	程瑞, 高建, 邢强, 孙中昶. 一种优化的Faster R-CNN小目标检测方法[J]. 测绘通报, 2021, 0(9): 21-27.
[5]	梁哲恒, 邓鹏, 姜福泉, 盛森, 魏汝兰, 谢刚生. 基于卷积神经网络的无人机影像违章建筑检测应用[J]. 测绘通报, 2021, 0(4): 111-115.
[6]	马京振, 陈换新, 朱新铭, 张付兵. 利用Faster R-CNN进行立交桥自动识别与定位[J]. 测绘通报, 2021, 0(3): 28-32,86.
[7]	张玉, 贾遂民. 噪声调节主成分变换下的遥感图像薄云去除[J]. 测绘通报, 2021, 0(3): 33-37.
[8]	侯翘楚, 李必军, 蔡毅. 高分辨率遥感影像的车道级高精地图要素提取[J]. 测绘通报, 2021, 0(3): 38-43.
[9]	赖正文, 夏小云. 像素级和对象级高分辨率遥感图像变化检测分析[J]. 测绘通报, 2021, 0(2): 59-63.
[10]	孙玉梅, 刘昱豪, 边占新, 孙亮, 陈敬周. 深度学习PaddlePaddle框架支持下的遥感智能视觉平台研究与实现[J]. 测绘通报, 2021, 0(11): 65-69,75.
[11]	马林飞, 倪欢, 周子涵. 基于注意力机制的高分遥感图像采石场识别[J]. 测绘通报, 2021, 0(11): 96-100.
[12]	沈雨, 仇宇轩, 于正浩. 分部加权的行道树检测网络构建[J]. 测绘通报, 2020, 0(2): 77-81,101.
[13]	谢福鼎, 赫佳妮, 郑宏亮. 半监督离散势理论在遥感影像变化检测中的应用[J]. 测绘通报, 2019, 0(8): 54-58.
[14]	谢梦, 刘伟, 杨梦圆, 柴琪, 吉莉. 深度卷积神经网络支持下的遥感影像飞机检测[J]. 测绘通报, 2019, 0(6): 19-23.
[15]	袁玉珠. 改进分数阶达尔文粒子群的多Renyi熵图像分割算法[J]. 测绘通报, 2019, 0(6): 34-40.