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

被引:4
作者
Liu, Wenjin [1 ]
Zhou, Lijuan [1 ]
Zhang, Shudong [1 ]
Luo, Ning [1 ]
Xu, Min [2 ]
机构
[1] Hainan Univ, Sch Cyberspace Secur, Sch Cryptol, Haikou 570228, Peoples R China
[2] Capital Normal Univ, Sch Informat Engn, Beijing 100048, Peoples R China
来源
TSINGHUA SCIENCE AND TECHNOLOGY | 2024年 / 29卷 / 04期
基金
中国国家自然科学基金;
关键词
illegal buildings; object detection; illegal construction objects; high-precision; lightweight; BUILDING CHANGE DETECTION; IMAGES; CLASSIFICATION; SEGMENTATION;
D O I
10.26599/TST.2023.9010090
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:1002 / 1022
页数:21
相关论文
共 75 条
[1]   Outdoor Illegal Construction Identification Algorithm Based on 3D Point Cloud Segmentation [J].
An, Lu ;
Guo, Baolong .
2017 INTERNATIONAL SYMPOSIUM ON APPLICATION OF MATERIALS SCIENCE AND ENERGY MATERIALS (SAMSE 2017), 2018, 322
[2]   Effective Generation and Update of a Building Map Database Through Automatic Building Change Detection from LiDAR Point Cloud Data [J].
Awrangjeb, Mohammad .
REMOTE SENSING, 2015, 7 (10) :14119-14150
[3]   Object extraction and revision by image analysis using existing geodata and knowledge: current status and steps towards operational systems [J].
Baltsavias, EP .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2004, 58 (3-4) :129-151
[4]  
Baylor T., 2005, PhD dissertation
[5]  
Benarchid O., 2013, Canadian Journal on Image Processing and Computer Vision, V4, P1
[6]  
Benedek C., 2010, Proceedings of the 2010 20th International Conference on Pattern Recognition (ICPR 2010), P1417, DOI 10.1109/ICPR.2010.350
[7]  
Bochkovskiy A, 2020, Arxiv, DOI [arXiv:2004.10934, 10.48550/arXiv.2004.10934]
[8]   Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge [J].
Bouziani, Mourad ;
Goita, Kalifa ;
He, Dong-Chen .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2010, 65 (01) :143-153
[9]  
Chen XF, 2018, INT CONF SOFTW ENG, P545, DOI 10.1109/ICSESS.2018.8663938
[10]   Iris presentation attack detection based on best-kfeature selection from YOLO inspired RoI [J].
Choudhary, Meenakshi ;
Tiwari, Vivek ;
Uduthalapally, Venkanna .
NEURAL COMPUTING & APPLICATIONS, 2021, 33 (11) :5609-5629