为解决当前施工现场塔吊检测范围小、检测过程复杂、易受干扰物影响等问题,利用无需预先训练的DSOD(deeply supervised object detector)算法,来研究施工塔吊的检测新方法.首先,通过摄像机从施工现场采集大量清晰的塔吊图像建立数据集,然后反复训练DSOD模型使其达到理想的收敛效果,最后分别在不同的条件(拍摄角度、拍摄距离、遮挡程度)下评估该模型的性能,并将该模型与以前的检测方法对比.实验结果表明:DSOD模型在检测精度和检测速度方面有明显优势,并且在满足“正面拍摄”、“中距离拍摄”和“遮挡程度低于50%”的条件下,该模型对塔吊检测的精确度和召回率可达到90%以上,为施工管理人员解决工程的实际问题提供了新的思路.
In order to solve the problems of small detection range, complex detection process and susceptiblility to interference, a new detection method of construction tower crane is proposed by using DSOD(deeply supervised object detector)algorithm without model pre training. Firstly, a large number of clear tower crane images are collected from the construction site by camera to establish the data sets, and then the DSOD model is trained repeatedly to achieve the ideal convergence effect. Finally, the performance of this model is evaluated under different conditions(shooting angle, shooting distance and occlusion degree), and it is compared with the previous detection methods. The experimental results show that DSOD does have obvious advantages in detection accuracy and detection speed, and under the conditions of “front shooting”, “medium distance shooting” and “shielding degree less than 50%”, the precision and recall rate of tower crane detection can reach more than 90%, which provides a new idea for construction managers to solve practical problems of the project.
[1] 国家统计局.2021年建筑业发展统计分析[R].北京:中国建筑业协会, 2022.
[2] 赵挺生,胡俊杰,师玉栋,等.塔吊安装与拆卸作业安全性分析[J].中国安全科学学报, 2021, 31(10): 32-38. DOI: 10.16265/j.cnki.issn1003-3033.2021.10.005.
[3] FANG Y H, CHO Y K, CHEN J D. A framework for real-time pro-active safety assistance for mobile crane lifting operations[J]. Autom Constr, 2016, 72: 367-379. DOI: 10.1016/j.autcon.2016.08.025.
[4] 谢晨晨,刘欣.基于BIM和定位技术的塔吊安全事故预警[J].建筑安全, 2020, 35(11): 34-38. DOI: 10.3969/j.issn.1004-552X.2020.11.009.
[5] 刘文平.基于BIM与定位技术的施工事故预警机制研究[D].北京:清华大学, 2015.
[6] 陈国栋,王翠瑜,张神德,等.基于改进YOLO V3的塔式起重机裂缝检测研究[J].贵州大学学报(自然科学版), 2021, 38(3): 76-82. DOI: 10.15958/j.cnki.gdxbzrb.2021.03.11.
[7] SHEN Z Q, LIU Z, LI J G, et al. DSOD: learning deeply supervised object detectors from scratch[C] //2017 IEEE International Conference on Computer Vision(ICCV), 2017, Venice, Italy, IEEE, 2017: 1937-1945. DOI: 10.1109/ICCV.2017.212.
[8] 王文成.基于深度学习的鱼类识别与检测的算法研究[D].舟山:浙江海洋大学, 2021.
[9] HOU X L, ZENG Y, XUE J G. Detecting structural components of building engineering based on deep-learning method[J]. J Constr Eng Manage, 2020, 146(2): 04019097.1-04019097.11. DOI: 10.1061/(asce)co.1943-7862.0001751.
[10] 刘爽,田兆星,李浩然,等.一种基于改进YOLOv5s网络的结直肠腺瘤实时检测方法[J].河北大学学报(自然科学版), 2022, 42(3): 327-336. DOI: 10.3969/j.issn.1000-1565.2022.03.016.
[11] 王林,赵红.改进YOLOv3的火灾检测[J].计算机系统应用, 2022, 31(4): 143-153. DOI: 10.15888/j.cnki.csa.008404.
[12] 杨观赐,杨静,苏志东,等.改进的YOLO特征提取算法及其在服务机器人隐私情境检测中的应用[J].自动化学报, 2018, 44(12): 2238-2249. DOI: 10.16383/j.aas.2018.c170265.
[13] 王静,孙紫雲,郭苹,等.改进YOLOv5的白细胞检测算法[J].计算机工程与应用, 2022, 58(4): 134-142. DOI: 10.3778/j.issn.1002-8331.2107-0332. (
