Citation:
Ao Sun, Xin Jin, Xiangyuan Guan, Pingfan Shi, Rui Kang, Zhao Xu. Research on Extraction Method of UAV Building Spatial Features Based on YOLOv3. Journal of Information Technologyin Civil Engineering and Architecture,
2022, 14(1): 126-131.
doi: 10.16670/j.cnki.cn11-5823/tu.2022.01.16
2022, 14(1): 126-131. doi: 10.16670/j.cnki.cn11-5823/tu.2022.01.16
Research on Extraction Method of UAV Building Spatial Features Based on YOLOv3
School of Civil Engineering of Southeastern University, Nanjing 211189, China |
With the development of smart cities, the requirement of sampling spatial characteristics of building regarding to efficiencies and accuracies are becoming much higher.Focusing on those limitations of current available technologies in AEC market, which is poor of flexibilities, lack of intelligences, and high of labor cost, this paper has proposed a new solution based on UAV(Unmanned Aerial Vehicle)scanning and YOLO(You Only Look Once)recognition to enable the real-time identification and extraction of window components from as-built projects. In this paper, the algorithm of YOLOv3 is being optimized to train the algorithm model by using integrated dataset. Nginx is being used to build RTMP(Real Time Messaging Protocol)for receiving the data from UAV scanning through streaming server for displaying the live results in ground station. The proposed solution has improved the efficiencies of recognition and has reduced the delays of streaming, which reflects the advantages of UAV technologies from the aspects of simultaneous, efficiencies, and intelligences for satisfying those demands in building components detection.
| [1] |
林文修, 袁兵, 张超. 既有建筑BIM运维的实现方法研究[J]. 重庆建筑, 2020, 19(7): 18-20.doi: 10.3969/j.issn.1671-9107.2020.07.18 |
| [2] | |
| [3] |
罗峰, 黄振妥. 基于无人机倾斜摄影测量技术的大区域房屋测量——以广州市金融城西区房屋现状摸查测量为例[J]. 工程勘察, 2019, 47(3): 55-58. |
| [4] |
杨明, 石小伟, 葛浩然. 无人机空地一体三维激光扫描技术应用研究[J]. 测绘通报, 2020(3): 134-139. |
| [5] |
马金龙, 于沭, 王国志, 等. 基于无人机巡检的渠道衬砌破损图像识别方法研究[J]. 水利科学与寒区工程, 2020, 3(5): 41-46.doi: 10.3969/j.issn.1002-3305.2020.05.009 |
| [6] |
邓瑞, 林金朝, 杨宏志. 基于深度学习的建筑物识别[J]. 重庆工商大学学报(自然科学版), 2019, 36(4): 17-22. |
| [7] |
高磊. 基于邻域高差分析的资源三号影像建筑物识别[J/OL]. 测绘地理信息: 1-7[2020-11-04]. http://kns.cnki.net/kcms/detail/42.1840.P.20200103.1540.022.html. |
| [8] |
许博鸣, 刘晓峰, 业巧林, 等. 基于卷积神经网络面向自然场景建筑物识别技术的移动端应用[J]. 南京师范大学学报(工程技术版), 2019, 19(3): 37-44. |
| [9] |
Redmon J, Farhadi A. Yolov3: An incremental improvement[EB/OL]. (2018-04-08)[2019-12-05]. https://arxiv.org/ads/1804.02767. |
| [10] |
Rebekka Volk, Julian Stengel, Frank Schultmann. Building Information Modeling(BIM)for existing buildings—2 Literature review and future needs[J]. Automation in Construction, 2014, 38. REDMON J, DIVVALA S, GIRSHICK R, etal. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788. |
| [11] |
Pingbo Tang, Daniel Huber, Burcu Akinci, Robert Lipman, Alan Lytle. Automatic reconstruction of as-built building information models from laser-scanned point clouds: A review of related techniques[J]. Automation in Construction, 2010, 19(7). |
| [12] |
Radim Tylecek, Radim Sara. Spatial Pattern Templates for Recognition of Objects with Regular Structure[C]//Proceedings of German conference on pattern recognition. 2013. |
| [13] |
张峻宁, 苏群星, 刘鹏远, 等. 一种基于透视投影的单目3D目标检测网络[J]. 机器人, 2020, 42(3): 278-288. DOI:10.13973/j.cnki.robot.190221.doi: 10.13973/j.cnki.robot.190221 |
| [14] |
赵明月, 吴健平. 基于CityEngine的建筑物自动化建模[J]. 测绘地理信息, 2017, 42(5): 92-95. |
| [15] |
赵云凡, 邓雪原, 赖华辉. 基于深度学习的结构构件识别方法研究[A]. 中国图学学会建筑信息模型(BIM)专业委员会. 第五届全国BIM学术会议论文集[C]. 中国图学学会建筑信息模型(BIM)专业委员会: 中国建筑工业出版社数字出版中心, 2019, 4. |
| [16] | |
| [17] |
陶磊, 洪韬, 钞旭. 基于YOLOv3的无人机识别与定位追踪[J]. 工程科学学报, 2020, 42(4): 463-468. |
Metrics
- PDF Downloads(35)
- Abstract views(2176)
- HTML views(901)
