基于无人机图像比对的违章建筑检测方法

曲靖师范学院学报 ›› 2024, Vol. 43 ›› Issue (6): 63-73.

基于无人机图像比对的违章建筑检测方法

魏松林¹, 林静敏², 李伟权¹, 唐凯^3,4

1.厦门海洋职业技术学院信息工程学院,福建厦门 361100;
2.厦门城市职业学院人工智能学院,福建厦门 361008;
3.集美大学海洋信息工程学院,福建厦门 361021;
4.厦门唯识筋斗云科技有限公司,福建厦门 361115

收稿日期:2024-06-26 出版日期:2024-12-17 发布日期:2024-12-17
作者简介:魏松林,厦门海洋职业技术学院信息工程学院讲师,博士,主要从事图像处理、人工智能应用、电子系统设计研究.
基金资助:
福建省中青年教师教育科研项目“基于FPGA的海上目标的智能检测技术研究与实现”(JAT220627);厦门市自然科学基金项目“海上目标的快速与智能检测技术研究”(3502Z202374070);厦门海洋职业技术学院高层次人才科研启动经费专项“海上目标的快速与智能检测技术研究”(KYG202206)

An Illegal Building Detection Method Based on UAV Image Comparison

WEI Songlin¹, LIN Jingmin², LI Weiquan¹, TANG Kai^3,4

1. School of Information Engineering, Xiamen Ocean Vocational College, Xiamen Fujian 361100;
2. School of Artificial Intelligence, Xiamen City University, Xiamen Fujian 361008;
3. School of Marine Information Engineering, Jimei University, Xiamen Fujian 361021;
4. Xiamen Weishi Somersault Cloud Technology Co., Ltd., Xiamen Fujian 361115, China

Received:2024-06-26 Published:2024-12-17 Online:2024-12-17

摘要/Abstract

摘要： 针对当前违章建筑图像识别和图像变化检测中存在的误检、漏检等问题,提出了一套基于无人机图像比对的违章建筑检测方法,创新性地采用YCrCb颜色空间三分量分别进行差分运算和阈值化处理,结合图像分类算法排除非施工活动引起的图像变化,通过结构相似性检测,对新旧时相变化区域相似度进行评估,识别出在建违章建筑引起的图像变化区域.与目前主流的基于无人机图像的非单一类型违章建筑物检测方法相比,4032×3024分辨率图像的检测时间缩短40.9%至4.08 s,正确率提高15.3%达到86.3%且无漏检测. 结果表明,本方法可有效、快速识别在建违章建筑区域,有利于城市管理人员及时发现并处理这些违章行为,从而提高城市管理的效率和响应速度.

关键词: 违章建筑检测, 无人机图像比对, YCrCb颜色空间, 分类过滤

Abstract: In response to the problems of false positives and false negatives in the current illegal building image recognition and image change detection, this paper proposes a method for detecting illegal building using UAV (Unmanned Aerial Vehicle) images, innovatively using the YCrCb color space to perform differential operations and thresholding on the three components separately, and combining image classification algorithms to exclude image changes caused by non-construction activities. Finally, by using structural similarity detection to evaluate the similarity of image change regions in new and old-time phases, the method identifies the image change regions caused by illegal building. Compared with the current mainstream non-single type violation building detection methods based on drone images, the detection time of 4032×3024 resolution image is reduced by 40.9% to 4.08 seconds, and the accuracy is improved by 15.3% to reach 86.3%, with no missed detections. The results show that this method can effectively and quickly identify areas where illegal building is underway, which is beneficial for city managers to discover and handle these illegal activities in a timely manner, thus improving the efficiency and response speed of urban management.

Key words: illegal building detection, UAV image comparison, YCrCb color space, classification filtering

中图分类号:

TP391.41

魏松林, 林静敏, 李伟权, 唐凯. 基于无人机图像比对的违章建筑检测方法[J]. 曲靖师范学院学报, 2024, 43(6): 63-73.

WEI Songlin, LIN Jingmin, LI Weiquan, TANG Kai. An Illegal Building Detection Method Based on UAV Image Comparison[J]. Journal of Qujing Normal University, 2024, 43(6): 63-73.

参考文献

[1] 李雪. 基于多角度图像的建筑物三维重建 [D]. 哈尔滨: 哈尔滨工程大学, 2024.
[2] 李昌鹏. 基于无人机影像的违章建筑检测方法研究 [D]. 北京: 中国地质大学, 2020.
[3] 冯笑雨. 基于塔基监控图像的建设施工用地识别与空间定位方法研究 [D]. 南京: 南京师范大学, 2019.
[4] 陈孝烽. 定点监控下可疑违章建筑物识别关键技术研究 [D]. 南京: 东南大学, 2020.
[5] 严德赛. 基于数字图像处理的违章建筑物自动检测研究 [D]. 武汉: 湖北大学, 2022.
[6] 张怡, 陈平. 基于深度置信网络的无人机航拍图像变化检测 [J]. 测试技术学报, 2020, 34(3): 190-196.
[7] 梁哲恒, 邓鹏, 姜福泉, 等. 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 (4): 111-115.
[8] LIU Y, SUN Y, TAO S, et al. Discovering potential illegal construction within building roofs from UAV images using semantic segmentation and object-based change detection [J]. Photogrammetric Engineering & Remote Sensing, 2021, 87(4): 263-271.
[9] 丁立早. 基于深度学习的违章建筑物检测技术研究 [D]. 南京: 东南大学, 2022.
[10] 雷思文, 朱福珍. 基于ORB和改进RANSAC的无人机遥感图像配准算法 [J]. 黑龙江大学自然科学学报, 2020, 37(5): 623-630.
[11] LOWE D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[12] BAY H, TUYTELAARS T, VAN-GOOL L. Surf: Speeded up robust features [C]//Proceedings of 2006 European conference on computer vision. Graz, Austria: Springer, 2006: 404-417.
[13] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: an efficient alternative to SIFT or SURF [C]//Proceedings of 2011 International Conference on Computer Vision. Barcelona: IEEE, 2012: 2564-2571.
[14] CALONDER M, LEPETIT V, STRECHA C, et al. BRIEF: Binary robust independent elementary features [C]//Proceedings of 2010 European conference on computer vision. Heraklion, Crete, Greece: Springer, 2010: 778-792.
[15] 叶坤涛, 李文, 舒蕾蕾, 等. 结合改进显著性检测与NSST的红外与可见光图像融合方法 [J]. 红外技术, 2021, 43(12): 1212-1221.
[16] GHIASI G, LIN T Y, LE Q V. Nas-fpn: Learning scalable feature pyramid architecture for object detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 7036-7045.
[17] ABOBAKR A, HOSSNY M, NAHAVANDI S. SSIM Layer: towards robust deep representation learning via nonlinear structural similarity [C]//2019 IEEE International Conference on Systems, Man and Cybernetics (SMC). Bari, Italy: IEEE, 2019: 1234-1238.