Adversarial Deep Learning-based Unauthorized Construction Site Recognition Using UAV-assisted Aerial Photography

doi:10.19678/j.issn.1000-3428.0059911

Abstract

Abstract: The detection method of unauthorized construction site is mainly to manually check the UAV-assisted aerial photography, leading to low detection accuracy, poor recognition performance and low work efficiency.This paper combines deep learning and UAV-assisted aerial photography for automatic recognition of unauthorized construction site in the early development stage, and proposes a generative adversarial network named ASTN-Fast RCNN, which combines Spatial Transformer Network(STN) and Fast RCNN.The STN(generator) is used to generate rotated samples that Fast R-CNN(detector) cannot easily recognize.Through such adversary training, the robustness of the detector is improved.The experimental results show that the proposed method can significantly improve the performance of unauthorized construction site recognition.

Key words: unauthorized construction site recognition, UVA-assisted aerial photography, Deep Learning(DL), target recognition, Generative Adversarial Network(GAN), Spatial Transformer Network(STN)

摘要： 对违建场地的检测方法主要是通过人工对无人机航拍视频进行检查，存在检测精度低、识别性能差、工作效率低的问题。提出一种结合空间变换网络与Fast RCNN的生成对抗网络ASTN-Fast RCNN，通过深度学习与无人机航拍视频相结合自动识别检测处在建设初期的违建场地。将空间变换网络作为生成器，生成Fast RCNN目标检测器难以识别的旋转形变样本，并通过目标检测器与生成器的对抗式训练，提高检测器的鲁棒性。实验结果表明，该方法能够有效提高对无人机航拍违建场地的识别性能。

关键词: 违建场地识别, 无人机航拍, 深度学习, 目标识别, 生成对抗网络, 空间变换网络

CLC Number:

TP391

GONG Faming, XU Chenxi, LI Juejin. Adversarial Deep Learning-based Unauthorized Construction Site Recognition Using UAV-assisted Aerial Photography[J]. Computer Engineering, 2022, 48(1): 275-280,287.

宫法明, 徐晨曦, 李厥瑾. 基于对抗深度学习的无人机航拍违建场地识别[J]. 计算机工程, 2022, 48(1): 275-280,287.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0059911

http://www.ecice06.com/EN/Y2022/V48/I1/275

Figures/Tables 9

References

[1] SHRIVASTAVA A, GUPTA A, GIRSHICK R.Training region-based object detectors with online hard example mining[C]//Proceedings of IEEE Conference on Computer Vision & Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:761-769.
[2] 黄蓉, 綦春峰, 赵云华.基于RS和GIS技术的城市违建治理动态监测研究与应用[J].城市勘测, 2019(6):53-57. HUANG R, QI C F, ZHAO Y H.Research and application of dynamic monitoring of urban violation control based on RS and GIS technology[J].Urban Geotechnical Investigation & Surveying, 2019(6):53-57.(in Chinese)
[3] JI Y Z, ZHANG H J, ZHANG Z, et al.CNN-based encoder-decoder networks for salient object detection:a comprehensive review and recent advances[J].Information Sciences, 2021, 546:835-857.
[4] DENG J, DONG W, SOCHER R, et al.ImageNet:a large-scale hierarchical image database[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2009:248-255.
[5] 李想, 汪荣贵, 杨娟, 等.基于示例选择的目标跟踪改进算法[J].计算机工程, 2015, 41(1):150-157. LI X, WANG R G, YANG J, et al.Improved object tracking algorithm based on instance selection[J].Computer Engineering, 2015, 41(1):150-157.(in Chinese)
[6] WANG X L, GUPTA A.Unsupervised learning of visual representations using videos[C]//Proceedings of IEEE International Conference on Computer Vision and Patterm Recognition.Washington D.C., USA:IEEE Press, 2015:2794-2802.
[7] CHENG G L, WANG Y, XU S B.Automatic road detection and centerline extraction via cascaded end-to-end convolutional neural network[J].IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(6):3322-3337.
[8] 强保华, 庞远超, 杨明浩, 等.基于可嵌入式网络结构的图像超分辨率重建方法[J].计算机工程, 2021, 47(5):221-228. QIANG B H, PANG Y C, YANG M H, et al.Image super-resolution reconstruction method based on embeddable network structure[J].Computer Engineering, 2021, 47(5):221-228.(in Chinese)
[9] SAITO M, MATSUMOTO E.Temporal generative adversarial nets with singular value clipping[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2849-2858.
[10] SZEGEDY C, IOFFE S, VANHOUCKE V.Inception-v4, Inception-ResNet and the impact of residual connections on learning[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence.New York, USA:ACM Press, 2017:4278-4284.
[11] XIE S, GIRSHICK R, DOLLAR P.Aggregated residual transformations for deep neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:5987-5995.
[12] BELL S, ZITNICK C L, BALA K.Inside-outside net:detecting objects in context with skip pooling and recurrent neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:2874-2883.
[13] 黄伟, 冯晶晶, 黄遥.基于多通道极深卷积神经网络的图像超分辨率算法[J].计算机工程, 2020, 46(9):242-247, 253. HUANG W, FENG J J, HUANG Y.Super-resolution algorithm for images based on multi-channel extremely deep convolutional neural network[J].Computer Engineering, 2020, 46(9):242-247, 253.(in Chinese)
[14] JIANG M, LENG B, MENG Z J, et al.Spatial-transformed regional quality estimation network for large-variance person re-identification[J].IEEE Access, 2019, 7:118101-118111.
[15] SHRIVASTAVA A, GUPTA A.Contextual priming and feedback for faster R-CNN[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:330-348.
[16] ZHANG P Z, GONG M G, ZHANG H, et al.Unsupervised difference representation learning for detecting multiple types of changes in multitemporal remote sensing images[J].IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(4):2277-2289.
[17] CHADHA A, ANDREOPOULOS Y.Improved techniques for adversarial discriminative domain adaptation[J].IEEE Transactions on Image Processing, 2020, 29:2622-2637.
[18] GAO X J, ZHANG Z, MU T T, et al.Self-attention driven adversarial similarity learning network[J].Pattern Recognition, 2020, 105:107331.
[19] LIU L L, ZHANG H J, ZHAO X F, et al.Collocating clothes with generative adversarial networks cosupervised by categories and attributes:a multidiscriminator framework[J].IEEE Transactions on Neural Networks and Learning Systems, 2019, 31(9):3540-3554.
[20] ZHAO M B, LIU Y, LI X R, et al.An end-to-end framework for clothing collocation based on semantic feature fusion[J].IEEE Multimedia, 2020, 27(4):122-132.
[21] SHEN P, LU X G, LI S, et al.Conditional generative adversarial nets classifier for spoken language identification[C]//Proceedings of INTERSPEECH.[S.l.]:ISCA Press, 2017:20-24.
[22] WANG X L, SHRIVASTAVA A, GUPTA A.A-Fast-RCNN:hard positive generation via adversary for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:258-265.
[23] SPRINGENBERG J T.Unsupervised and semi-supervised learning with categorical generative adversarial networks[EB/OL].[2020-10-03].https://arxiv.org/pdf/1511.06390.pdf.
[24] GIRSHICK R.Fast R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2015:1440-1448.
[25] JADERBERG M, SIMONYAN K, ZISSERMAN A, et al.Spatial transformer networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems.New York, USA:ACM Press, 2015:2017-2025.

Please choose a citation manager

Content to export