[1]胡立华,王敏敏,刘爱琴,等.基于影响空间与 YOLOv3 的古建筑检测方法[J].计算机技术与发展,2022,32(12):185-193.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 028]
　HU Li-hua,WANG Min-min,LIU Ai-qin,et al.An Ancient Architectural Detection Method Combining Influence Space with YOLOv3 Network[J].,2022,32(12):185-193.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 028]
点击复制

基于影响空间与 YOLOv3 的古建筑检测方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年12期
页码:
185-193
栏目:
新型计算应用系统
出版日期:
2022-12-10

文章信息/Info

Title:
An Ancient Architectural Detection Method Combining Influence Space with YOLOv3 Network
文章编号:
1673-629X(2022)12--0185-09
作者:
胡立华1 ; 王敏敏1; 2 ; 刘爱琴1 ; 张素兰1
1. 太原科技大学 计算机科学与技术学院,山西 太原 030024;
2. 佛山市科自智能系统技术有限公司,广东 佛山 528010
Author(s):
HU Li-hua1 ; WANG Min-min1; 2 ; LIU Ai-qin1 ; ZHANG Su-lan1
1. School of Computer Science and Technology,Taiyuan University of Science and Technology,Taiyuan 030024,China;
2. Foshan Science and Automation Intelligence Technology Corporations,Foshan 528010,China
关键词:
影响空间; YOLOv3; 古建筑检测; 交并比; 检出率
Keywords:
influence space; YOLOv3; ancient architectural detection; intersection over union; average intersection over union
分类号:
TP391. 41
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 12. 028
摘要:
物体检测是计算机视觉领域的一个关键内容,主要研究如何在静态图像或动态视频流中快速、准确地识别及定位出其中的目标。 基于图像的古建筑检测可用于古建筑三维重建、智慧旅游等领域,具有重要的研究意义和实际应用价值。然而,受到古建筑样式、形状、花纹及纹理质地等影响,目前的物体检测器存在检测精度低和定位不准的问题。 针对上述问题,基于 YOLOv3 网络模型,结合密度聚类和距离聚类思想,设计了一种基于 RNN-DBSCAN+k-means 的古建筑检测方法。 该方法首先结合影响空间思想,采用 RNN-DBSCAN 算法对已标注的古建筑图像聚类,生成聚类结果集;其次从聚类结果集中选取最优的 k 个结果作为 k-means 的初始聚类中心;然后将这 k 个聚类中心作为聚类初始值,结合 k-means 算法得出聚类结果,并作为 YOLOv3 网络的先验框;最后以 voc 数据集(20 类) 和古建筑数据集为对象,验证了算法的有效性。针对古建筑数据集,算法检出率提高了 0. 33% ;而在 voc 数据集单类检测中,算法检出率提高了 0. 04% ~ 0. 84% 。
Abstract:
Object detection is a key content in the field of computer vision,which mainly studies how to quickly and accurately identifyand locate objects in static images or dynamic video streams. Image - based detection of ancient architectures can be used in 3Dreconstruction of ancient architectures, intelligent tourism and other fields, which has important research significance and practicalapplication value. However,affected by the ancient architectures爷 style,shape,pattern and texture,　the object detectors have the problemsof poor detection accuracy and inaccurate positioning at present. In order to solve those troubles,a new detective method of ancient architectures based on YOLOv3 network model is proposed. The method named RNN-DBSCAN+k-means combines density clustering ideawith distance clustering idea. In this method,combined with the idea of influence space,RNN - DBSCAN algorithm is used to clusterlabeled images of ancient architectures and generate the clustered result set firstly. Secondly,the optimal k results are selected from theclustered result set as the initial clustering centers of k-means. Thirdly,　those clustered centers are taken as the initial values of clustering,and the clustered results are obtained by through k - means algorithm, which are used as anchors of YOLOv3 network. Finally, vocdatasets (20 categories) and ancient architectural datasets are used to verify the effectiveness of the algorithm. The detection rate of theproposed algorithm is improved by 0. 33% in the datasets of ancient architectures,while in voc datasets,it is increased by 0. 04% ~0. 84% .

相似文献/References:

[1]李 轩,李 静,王海燕.密集交通场景的目标检测算法研究[J].计算机技术与发展,2020,30(07):46.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 011]
　LI Xuan,LI Jing,WANG Hai-yan.Research on Object Detection Algorithm in Dense Traffic Scenes[J].,2020,30(12):46.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 011]
[2]余 进,史燕中,王春华,等.一种轻量化目标检测算法研究[J].计算机技术与发展,2020,30(11):42.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
　YU Jin,SHI Yan-zhong,WANG Chun-hua,et al.Research of a Lightweight Object Detection Algorithm[J].,2020,30(12):42.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
[3]杨学杰,李思毛,李建业,等.面向巡检机器人的电力设备状态检测算法研究[J].计算机技术与发展,2021,31(03):201.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 035]
　YANG Xue-jie,LI Si-mao,LI Jian-ye,et al.Research on Algorithm for Equipment Condition Monitoring Based on Inspection Robot[J].,2021,31(12):201.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 035]
[4]谭芳喜,肖世德,周亮君,等.基于改进 YOLOv3 算法在道路目标检测中的应用[J].计算机技术与发展,2021,31(08):118.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 020]
　TAN Fang-xi,XIAO Shi-de,ZHOU Liang-jun,et al.Application in Road Target Detection Based on ImprovedYOLOV3 Algorithm[J].,2021,31(12):118.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 020]
[5]许 伟,熊卫华.一种改进的轻量级垃圾目标检测算法[J].计算机技术与发展,2022,32(02):63.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 010]
　XU Wei,XIONG Wei-hua.An Improved Lightweight Garbage Target Detection Algorithm[J].,2022,32(12):63.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 010]
[6]张 剑,王等准,莫光健,等.基于改进 YOLOv3 的高铁异物入侵检测算法[J].计算机技术与发展,2022,32(02):69.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 011]
　ZHANG Jian,WANG Deng-zhun,MO Guang-jian,et al.High-speed Rail Foreign Body Intrusion Detection Algorithm Based on Improved YOLOv3[J].,2022,32(12):69.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 011]
[7]吴春香,吴 恋.面向视频的人员入侵检测方法研究及应用[J].计算机技术与发展,2022,32(04):116.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 020]
　WU Chun-xiang,WU Lian.Research and Application of Video Oriented Personnel Intrusion Detection Method[J].,2022,32(12):116.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 020]
[8]戴 威,陆小锋,钟宝燕,等.一种基于视觉分析的指针式仪表智能抄读方法[J].计算机技术与发展,2023,33(01):200.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 030]
　DAI Wei,LU Xiao-feng,ZHONG Bao-yan,et al.An Intelligent Reading Method of Pointer Instrument Based on Visual Analysis[J].,2023,33(12):200.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 030]

更新日期/Last Update: 2022-12-10