AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Tsinghua Science and Technology Article
PDF (1.9 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

A New High-Precision and Lightweight Detection Model for Illegal Construction Objects Based on Deep Learning

School of Cyberspace Security (School of Cryptology), Hainan University, Haikou 570228, China
School of Information Engineering, Capital Normal University, Beijing 100048, China
Show Author Information

Abstract

Illegal construction has caused serious harm around the world. However, current methods are difficult to detect illegal construction activities in time, and the calculation complexity and the parameters of them are large. To solve these challenges, a new and unique detection method is proposed, which detects objects related to illegal buildings in time to discover illegal construction activities. Meanwhile, a new dataset and a high-precision and lightweight detector are proposed. The proposed detector is based on the algorithm You Only Look Once (YOLOv4). The use of DenseNet as the backbone of YDHNet enables better feature transfer and reuse, improves detection accuracy, and reduces computational costs. Meanwhile, depthwise separable convolution is employed to lightweight the neck and head to further reduce computational costs. Furthermore, H-swish is utilized to enhance non-linear feature extraction and improve detection accuracy. Experimental results illustrate that YDHNet realizes a mean average precision of 89.60% on the proposed dataset, which is 3.78% higher than YOLOv4. The computational cost and parameter count of YDHNet are 26.22 GFLOPs and 16.18 MB, respectively. Compared to YOLOv4 and other detectors, YDHNet not only has lower computational costs and higher detection accuracy, but also timely identifies illegal construction objects and automatically detects illegal construction activities.

Keywords

illegal buildingsobject detectionillegal construction objectshigh-precisionlightweight

References

[1]
L. Yang, T. H. Chi, L. Peng, and X. Sun, Research of illegal building monitoring system construction with 3S integration technology, in Proc. 2nd Int. Conf. Information Science and Engineering, Hangzhou, China, 2010, pp. 3908–3911.
[2]
D. Liu, Photogrammetric approach for detection of rooftop illegal structures, https://theses.lib.polyu.edu.hk/handle/200/7044, 2013.
[3]
P. F. Lezaun and G. Olivieri, Undeclared constructions: A government’s support deep learning solution for automatic change detection, in Proc. 2018 ITU Kaleidoscope : Machine Learning for a 5G Future (ITU K), Santa Fe, Argentina, 2018, pp. 1–7.
Crossref
[4]
N. Seror and B. A. Portnov, Identifying areas under potential risk of illegal construction and demolition waste dumping using GIS tools, Waste Manag., vol. 75, pp. 22–29, 2018.
Crossref
[5]

F. da Conceição Leite, R. dos Santos Motta, K. L. Vasconcelos, and L. Bernucci, Laboratory evaluation of recycled construction and demolition waste for pavements, Constr. Build. Mater., vol. 25, no. 6, pp. 2972–2979, 2011.
Crossref Google Scholar
[6]

B. Varol, E. Ö. Yılmaz, D. Maktav, S. Bayburt, and S. Gürdal, Detection of illegal constructions in urban cities: Comparing LIDAR data and stereo KOMPSAT-3 images with development plans, Eur. J. Remote. Sens., vol. 52, no. 1, pp. 335–344, 2019.
Crossref Google Scholar
[7]

C. Ioannidis, C. Psaltis, and C. Potsiou, Towards a strategy for control of suburban informal buildings through automatic change detection, Comput. Environ. Urban Syst., vol. 33, no. 1, pp. 64–74, 2009.
Crossref Google Scholar
[8]
D. Perez, D. Banerjee, C. Kwan, M. Dao, Y. Shen, K. Koperski, G. Marchisio, and J. Li, Deep learning for effective detection of excavated soil related to illegal tunnel activities, in Proc. 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), New York, NY, USA, 2017, pp. 626–632.
Crossref
[9]

M. Awrangjeb, Effective generation and update of a building map database through automatic building change detection from LiDAR point cloud data, Remote. Sens., vol. 7, no. 10, pp. 14119–14150, 2015.
Crossref Google Scholar
[10]
T. Baylor, Active contour and prior information for change analysis: Applied to updating urban building digital maps based on high-resolution remote sensing optical images, (in French), PhD dissertation, National Institute of Technology, Toulouse, France, 2005.
[11]

E. P. Baltsavias, Object extraction and revision by image analysis using existing geodata and knowledge: Current status and steps towards operational systems, ISPRS J. Photogramm. Remote. Sens., vol. 58, nos. 3&4, pp. 129–151, 2004.
Crossref Google Scholar
[12]

Y. Tang, X. Huang, and L. Zhang, Fault-tolerant building change detection from urban high-resolution remote sensing imagery, IEEE Geosci. Remote. Sens. Lett., vol. 10, no. 5, pp. 1060–1064, 2013.
Crossref Google Scholar
[13]

X. Huang, L. Zhang, and T. Zhu, Building change detection from multitemporal high-resolution remotely sensed images based on a morphological building index, IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens., vol. 7, no. 1, pp. 105–115, 2014.
Crossref Google Scholar
[14]

V. Walter, Object-based classification of remote sensing data for change detection, ISPRS J. Photogramm. Remote. Sens., vol. 58, nos. 3&4, pp. 225–238, 2004.
Crossref Google Scholar
[15]

D. Konstantinidis, T. Stathaki, V. Argyriou, and N. Grammalidis, Building detection using enhanced HOG–LBP features and region refinement processes, IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens., vol. 10, no. 3, pp. 888–905, 2017.
Crossref Google Scholar
[16]

K. Karantzalos and D. Argialas, A region-based level set segmentation for automatic detection of man-made objects from aerial and satellite images, Photogramm. Eng. Remote. Sens., vol. 75, no. 6, pp. 667–677, 2009.
Crossref Google Scholar
[17]
P. V. C. Hough, Method and means for recognizing complex patterns, US Patent 3069654, 1962-12-18.
[18]

N. K. Moghadam, M. R. Delavar, and P. Hanachee, Automatic urban illegal building detection using multi-temporal satellite images and geospatial information systems, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. XL-1/W5, pp. 387–393, 2015.
Crossref Google Scholar
[19]

Y. Xu, L. Wu, Z. Xie, and Z. Chen, Building extraction in very high resolution remote sensing imagery using deep learning and guided filters, Remote. Sens., vol. 10, no. 1, p. 144, 2018.
Crossref Google Scholar
[20]
W. Liu, S. Zhang, and L. Zhou, High-precision snore detection method based on deep learning, in Proc. 5th Int. Conf. Mechatronics and Computer Technology Engineering (MCTE 2022), Chongqing, China, 2022, pp. 1492–1497.
Crossref
[21]
W. Liu, S. Zhang, and L. Zhou, Snoring detection method in sleep based on MBAM-ResNet, in Proc. 5th Int. Conf. Computer Information Science and Application Technology (CISAT 2022). Chongqing, China, 2022, pp. 547–551.
Crossref
[22]
L. Wang, Y. Liu, P. Du, Z. Ding, Y. Liao, Q. Qi, B. Chen, and S. Liu, Object-aware distillation pyramid for open-vocabulary object detection, in Proc. 2023 IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 2023, pp. 11186–11196.
Crossref
[23]

W. Liu, S. Zhang, L. Zhou, M. Xu, and Z. Ren, High-precision automatic detection method of illegal construction object images in complex scenes, J. Electron. Imag., vol. 32, no. 3, p. 031803, 2022.
Crossref Google Scholar
[24]
S. Zhang, X. Wang, J. Wang, J. Pang, C. Lyu, W. Zhang, P. Luo, and K. Chen, Dense distinct query for end-to-end object detection, in Proc. 2023 IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 2023, pp. 7329–7338.
Crossref
[25]
L. Zhou, W. Liu, S. Zhang, N. Luo, and M. Xu, CRMNet: Development of a deep-learning-based anchor-free detection method for illegal building objects, Int. J. Patt. Recogn. Artif. Intell., vol. 37, no. 6, p. 2352007, 2023.
Crossref
[26]

J. Han, D. Zhang, G. Cheng, N. Liu, and D. Xu, Advanced deep-learning techniques for salient and category-specific object detection: A survey, IEEE Signal Process. Mag., vol. 35, no. 1, pp. 84–100, 2018.
Crossref Google Scholar
[27]
Z. Wang, Y. Li, X. Chen, S. N. Lim, A. Torralba, H. Zhao, and S. Wang, Detecting everything in the open world: Towards universal object detection, in Proc. 2023 IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 2023, pp. 11433–11443.
Crossref
[28]

A. M. Roy, R. Bose, and J. Bhaduri, A fast accurate fine-grain object detection model based on YOLOv4 deep neural network, Neural Comput. Appl., vol. 34, no. 5, pp. 3895–3921, 2022.
Crossref Google Scholar
[29]
R. Girshick, J. Donahue, T. Darrell, and J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in Proc. 2014 IEEE Conf. Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 580–587.
Crossref
[30]
R. Girshick, Fast R-CNN, in Proc. 2015 IEEE Int. Conf. Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1440–1448.
Crossref
[31]

S. Ren, K. He, R. Girshick, and J. Sun, Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, 2017.
Crossref Google Scholar
[32]
A. Rahimzadeganasl and E. Sertel, Automatic building detection based on CIE LUV color space using very high resolution Pleiades images, in Proc. 2017 25th Signal Processing and Communications Applications Conference (SIU), Antalya, Turkey, 2017, pp. 1–4.
Crossref
[33]
T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, Focal loss for dense object detection, in Proc. 2017 IEEE Int. Conf. Computer Vision (ICCV), Venice, Italy, 2017, pp. 2999–3007.
Crossref
[34]
Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, YOLOX: Exceeding YOLO series in 2021, arXiv preprint arXiv: 2107.08430, 2021.
[35]
X. Zhou, D. Wang, and P. Krähenbühl, Objects as points, arXiv preprint arXiv: 1904.07850, 2019.
[36]
M. Tan, R. Pang, and Q. V. Le, EfficientDet: Scalable and efficient object detection, in Proc. 2020 IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, pp. 10778–10787.
Crossref
[37]
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, You only look once: Unified, real-time object detection, in Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779–788.
Crossref
[38]
J. Redmon and A. Farhadi, YOLO9000: Better, faster, stronger, in Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 6517–6525.
Crossref
[39]
J. Redmon and A. Farhadi, YOLOv3: An incremental improvement, arXiv preprint arXiv: 1804.02767, 2018.
[40]
A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, YOLOv4: Optimal speed and accuracy of object detection, arXiv preprint arXiv: 2004.10934, 2020.
[41]

J. Wang, N. Wang, L. Li, and Z. Ren, Real-time behavior detection and judgment of egg breeders based on YOLO v3, Neural Comput. Appl., vol. 32, no. 10, pp. 5471–5481, 2020.
Crossref Google Scholar
[42]

I. Martinez-Alpiste, G. Golcarenarenji, Q. Wang, and J. M. Alcaraz-Calero, Search and rescue operation using UAVs: A case study, Expert Syst. Appl., vol. 178, p. 114937, 2021.
Crossref Google Scholar
[43]

M. Choudhary, V. Tiwari, and V. Uduthalapally, Iris presentation attack detection based on best- k feature selection from YOLO inspired RoI, Neural Comput. Appl., vol. 33, no. 11, pp. 5609–5629, 2021.
Crossref Google Scholar
[44]
V. Ostankovich and I. Afanasyev, Illegal buildings detection from satellite images using GoogLeNet and cadastral map, in Proc. 2018 Int. Conf. Intelligent Systems (IS), Funchal, Portugal, 2018, pp. 616–623.
Crossref
[45]
G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, Densely connected convolutional networks, in Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 2261–2269.
Crossref
[46]
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, and A. C. Berg, SSD: Single shot multibox detector, in Proc. 14th European Conf. Computer Vision (CVPR), Amsterdam, the Netherlands, 2016, pp. 21–37.
Crossref
[47]
C. Y. Wang, A. Bochkovskiy, and H. Y. M. Liao, YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, arXiv preprint arXiv: 2207.02696, 2022.
Crossref
[48]
C. Benedek, X. Descombes, and J. Zerubia, Building detection in a single remotely sensed image with a point process of rectangles, in Proc. 2010 20th Int. Conf. Pattern Recognition, Istanbul, Turkey, 2010, pp. 1417–1420.
Crossref
[49]

D. Chen, S. Shang, and C. Wu, Shadow-based building detection and segmentation in high-resolution remote sensing image, J. Multimed., vol. 9, no. 1, pp. 181–188, 2014.
Crossref Google Scholar
[50]

S. Xu, G. Vosselman, and S. O. Elberink, Detection and classification of changes in buildings from airborne laser scanning data, Remote. Sens., vol. 7, no. 12, pp. 17051–17076, 2015.
Crossref Google Scholar
[51]

N. Khalilimoghadama, M. R. Delavar, and P. Hanachi, Performance evaluation of three different high resolution satellite images in semi-automatic urban illegal building detection, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. XLII-2/W7, pp. 505–514, 2017.
Crossref Google Scholar
[52]

P. D. Felice, Ranking of illegal buildings close to rivers: A proposal, its implementation and preliminary validation, ISPRS Int. J. Geo Inf., vol. 8, no. 11, p. 510, 2019.
Crossref Google Scholar
[53]
D. Zhu and J. Fan, IBMDCH: Illegal building monitoring in digital city based on HPC, in Proc. Geoinformatics 2008 and Joint Conf. GIS and Built Environment : Monitoring and Assessment of Natural Resources and Environments, Guangzhou, China, 2008, pp. 425–436.
Crossref
[54]

M. Bouziani, K. Goïta, and D. C. He, Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge, ISPRS J. Photogramm. Remote. Sens., vol. 65, no. 1, pp. 143–153, 2010.
Crossref Google Scholar
[55]

N. Moghadam, M. Delavar, and P. Hanachi, Semi-automatic illegal building detection in urban areas using satellite images and a pixel-based fuzzy XOR operator method, Geospatial Engineering Journal, vol. 7, no. 3, pp. 105–116, 2016.
Google Scholar
[56]

O. Benarchid, N. Raissouni, E. A. Samir, A. El Abbous, A. Azyat, N. B. Achhab, M. Lahraoua, and C. Asaad, Building extraction using object-based classification and shadow information in very high resolution multispectral images, a case study: Tetuan, Morocco, Canadian Journal on Image Processing and Computer Vision, vol. 4, no. 1, pp. 1–8, 2013.
Google Scholar
[57]
F. Dornaika, A. Moujahid, Y. El Merabet, and Y. Ruichek, A comparative study of image segmentation algorithms and descriptors for building detection, in Handbook of Neural Computation, P. Samui, S. Sekhar, and V. E. Balas, eds. New York, NY, USA: Academic Press, 2017, pp. 591–606.
Crossref
[58]

D. Comaniciu and P. Meer, Mean shift: A robust approach toward feature space analysis, IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 5, pp. 603–619, 2002.
Crossref Google Scholar
[59]
Q. Tan, Q. Wei, and F. Liang, Building extraction from VHR multi-spectral images using rule-based object-oriented method: A case study, in Proc. 2010 IEEE Int. Geoscience and Remote Sensing Symp., Honolulu, HI, USA, 2010, pp. 2754–2756.
Crossref
[60]
X. F. Chen, X. G. Zhang, R. K. He, and Y. Wang, An algorithm to detect illegal buildings using color transferring and texture difference, in Proc. 2018 IEEE 9th Int. Conf. Software Engineering and Service Science (ICSESS), Beijing, China, 2018, pp. 545–550.
Crossref
[61]

L. An and B. Guo, Outdoor illegal construction identification algorithm based on 3D point cloud segmentation, IOP Conf. Ser.: Mater. Sci. Eng., vol. 322, p. 052013, 2018.
Crossref Google Scholar
[62]

H. Wang, X. Ning, H. Zhang, Y. Liu, and F. Yu, Urban boundary extraction and urban sprawl measurement using high-resolution remote sensing images: A case study of China’s provincial, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. XLII-3, pp. 1713–1719, 2018.
Crossref Google Scholar
[63]
C. Zhang and N. Liu, Illegal construction detection of road based on unmanned aerial vehicle vision, http://en.cnki.com.cn/Article_en/CJFDTotal-WJFZ201807030.htm, 2018.
[64]
T. Ishii, E. Simo-Serra, S. Iizuka, Y. Mochizuki, A. Sugimoto, H. Ishikawa, and R. Nakamura, Detection by classification of buildings in multispectral satellite imagery, in Proc. 2016 23rd Int. Conf. Pattern Recognition (ICPR), Cancun, Mexico, 2016, pp. 3344–3349.
Crossref
[65]
G. Prathap and I. Afanasyev, Deep learning approach for building detection in satellite multispectral imagery, in Proc. 2018 Int. Conf. Intelligent Systems (IS), Funchal, Portugal, 2018, pp. 461–465.
Crossref
[66]
M. Vakalopoulou, K. Karantzalos, N. Komodakis, and N. Paragios, Building detection in very high resolution multispectral data with deep learning features, in Proc. 2015 IEEE Int. Geoscience and Remote Sensing Symp. (IGARSS), Milan, Italy, 2015, pp. 1873–1876.
Crossref
[67]
L. Martijn, S. Meijerink, and J. Ezeiza, Detect illegal buildings based on LiDAR point cloud data, https://event.cwi.nl/lsde/2019/results/group02.pdf, 2023.
[68]

Y. Liu, Y. Sun, S. Tao, M. Wang, Q. Shen, and J. Huang, Discovering potential illegal construction within building roofs from UAV images using semantic segmentation and object-based change detection, Photogramm. Eng. Remote. Sens., vol. 87, no. 4, pp. 263–271, 2021.
Crossref Google Scholar
[69]
Z. Liang, P. Deng, F. Jiang, S. Sheng, R. Wei, and G. Xie, The application of illegal building detection from VHR UAV remote sensing images based on convolutional neural network, Bulletin of Surveying and Mapping. doi: 10.13474/J.CNKI.11-2246.2021.0120
[70]
X. Li, L. Fu, Y. Fan, and C. Dong, Building recognition based on improved faster R-CNN in high point monitoring image, in Proc. 2021 33rd Chinese Control and Decision Conference (CCDC), Kunming, China, 2021, pp. 1803–1807.
Crossref
[71]

K. He, X. Zhang, S. Ren, and J. Sun, Spatial pyramid pooling in deep convolutional networks for visual recognition, IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 9, pp. 1904–1916, 2015.
Crossref Google Scholar
[72]
S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, Path aggregation network for instance segmentation, in Proc. 2018 IEEE/CVF Conf. Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 8759–8768.
Crossref
[73]
A. Howard, M. Sandler, B. Chen, W. Wang, L. C. Chen, M. Tan, G. Chu, V. Vasudevan, Y. Zhu, R. Pang, et al., Searching for MobileNetV3, in Proc. 2019 IEEE/CVF Int. Conf. Computer Vision (ICCV), Seoul, Republic of Korea, 2019, pp. 1314–1324.
Crossref
[74]
A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, MobileNets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv: 1704.04861, 2017.
[75]
X. Zhu, S. Lyu, X. Wang, and Q. Zhao, TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios, in Proc. 2021 IEEE/CVF Int. Conf. Computer Vision Workshops (ICCVW), Montreal, Canada, 2021, pp. 2778–2788.
Crossref
Tsinghua Science and Technology
Volume 29 Issue 4,
August 2024
Pages 1002-1022
DOI: 10.26599/TST.2023.9010090
Cite this article:
Liu W, Zhou L, Zhang S, et al. A New High-Precision and Lightweight Detection Model for Illegal Construction Objects Based on Deep Learning. Tsinghua Science and Technology, 2024, 29(4): 1002-1022. https://doi.org/10.26599/TST.2023.9010090

535

Views

66

Downloads

3

Crossref

2

Web of Science

5

Scopus

0

CSCD

Altmetrics
Received: 21 June 2023
Revised: 05 August 2023
Accepted: 27 August 2023
Published: 09 February 2024
© The Author(s) 2024.

The articles published in this open access journal are distributed under the terms of theCreative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Return