[1]张元,关瑜,熊风光,等.基于改进Yolov5s的增强现实文物识别方法[J].计算机技术与发展,2024,34(07):17-23.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0118]
　ZHANG Yuan,GUAN Yu,XIONG Feng-guang,et al.An Augmented Reality Cultural Relics Recognition Method Based on Improved Yolov5s[J].,2024,34(07):17-23.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0118]
点击复制

基于改进Yolov5s的增强现实文物识别方法()

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

卷:
34
期数:
2024年07期
页码:
17-23
栏目:
媒体计算
出版日期:
2024-07-10

文章信息/Info

Title:
An Augmented Reality Cultural Relics Recognition Method Based on Improved Yolov5s
文章编号:
1673-629X(2024)07-0017-07
作者:
张元1; 2; 3; 关瑜1; 2; 3; 熊风光1; 2; 3; 庞敏1; 2; 3; 况立群1; 2; 3
1. 中北大学 计算机科学与技术学院,山西 太原 030051;2. 机器视觉与虚拟现实山西省重点实验室,山西 太原 030051;3. 山西省视觉信息处理及智能机器人工程研究中心,山西 太原 030051
Author(s):
ZHANG Yuan1; 2; 3; GUAN Yu1; 2; 3; XIONG Feng-guang1; 2; 3; PANG Min1; 2; 3; KUANG Li-qun1; 2; 3
1. School of Computer Science and Technology,North University of China,Taiyuan 030051,China;2. Shanxi Provincial Key Laboratory of Machine Vision and Virtual Reality,Taiyuan 030051,China;3. Shanxi Province Visual Information Processing and Intelligent Robot Engineering Research Center,Taiyuan 030051,China
关键词:
增强现实; 文物识别; Yolov5s; 注意力机制; 多头自注意力机制; DIoU-NMS
Keywords:
augmented reality; cultural relic identification; Yolov5s; attention mechanism; multi-head self-attention; DIoU-NMS
分类号:
TP311
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0118
摘要:
将增强现实技术应用于数字博物馆的文物展览,有助于拉近参观者与文物的距离,使展览更具趣味性。 针对增强现实技术在文物展览应用场景中,增强现实设备采集的文物目标图像背景复杂、文物形状纹理丰富而导致的误检、识别准确率低的问题,提出一种基于改进的 Yolov5s 的文物识别方法。 在 Yolov5s 网络结构中的骨干网络与颈部网络之间引入了CBAM 注意力机制,并在骨干网络中的 Bottleneck 模块中,使用多头注意力机制替换普通卷积,有效捕获局部信息,降低了无用信息的干扰。 为了提高识别网络对于目标文物的边界框定位精度,采用 DIoU-NMS 方法挑选最优的目标识别框作为最终的预测框。 实验结果表明,该方法提高了文物的平均识别精度,比原模型更适用于 AR 应用文物的目标识别。
Abstract:
Applying augmented reality technology to the cultural relics exhibition of the digital museum helps to shorten the distance between the visitors and the cultural relics,and make the exhibition more interesting. Aiming at the problems of false detection and low recognition accuracy caused by complex background and rich shape and texture of cultural relics collected by augmented reality equipment in the application scene of cultural relics exhibition,an improved cultural relics recognition method based on Yolov5s is proposed. The CBAM attention mechanism is introduced between the backbone network and the neck network in the Yolov5s network structure. In addition,a multi-head attention mechanism is used to replace common convolution in the Bottleneck module of the backbone network,which effectively captures local information and reduces the interference of unnecessary information. In order to improve the location accuracy of the boundary frame of the target cultural relics,the DIoU-NMS method is used to select the optimal target identification frame as the final prediction frame. Experimental results show that the proposed algorithm improves the average detection accuracy of the cultural relics,which is more suitable for the target detection of cultural relics than the original algorithm in AR application.

相似文献/References:

[1]李利军 杨西平.基于标识与自然纹理特征的三维注册方法研究[J].计算机技术与发展,2007,(07):77.
　LI Li-jun,YANG Xi-ping.3D Registration Method Based on Marker and Natural Texture Feature[J].,2007,(07):77.
[2]程委 廖学军 李智[].增强现实及其军事应用研究[J].计算机技术与发展,2007,(12):165.
　CHENG Wei,LIAO Xue-jun,LI Zhi.Study on Augmented Reality and Its Military Application[J].,2007,(07):165.
[3]邹优嘉.移动设备增强现实技术与书本交互的应用[J].计算机技术与发展,2013,(08):227.
　ZOU You-jia.Application of Mobile Augment Reality Technology Interacted with Books[J].,2013,(07):227.
[4]李玥,丁友东.并行正向反馈ICP算法研究[J].计算机技术与发展,2013,(11):6.
　LI Yue,DING You-dong.Research of Positive Feedback ICP Algorithm in Parallel[J].,2013,(07):6.
[5]宋燕燕,曹效业,周灵. 移动增强现实技术在互动展示中的应用研究[J].计算机技术与发展,2016,26(09):83.
　SONG Yan-yan,CAO Xiao-ye,ZHOU Ling. Research on Application of Mobile AR Technology in Product Interaction Exhibition[J].,2016,26(07):83.
[6]毛立平,孙刘杰,王文举,等.基于增强现实的钢铁生产线可视化仿真系统[J].计算机技术与发展,2021,31(05):157.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 027]
　,,et al.ＶｉｓｕａｌＳｉｍｕｌａｔｉｏｎＳｙｓｔｅｍ ｏｆＳｔｅｅｌＰｒｏｄｕｃｔｉｏｎＬｉｎｅＢａｓｅｄｏｎＡｕｇｍｅｎｔｅｄＲｅａｌｉｔｙ[J].,2021,31(07):157.[doi:10. 3969 / j. issn. 1673-629X. 2021. 05. 027]
[7]宋根龙,田 彤,陈 轩,等.基于人脸关键特征的眼镜增强匹配算法[J].计算机技术与发展,2022,32(04):181.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 031]
　SONG Gen-long,TIAN Tong,CHEN Xuan,et al.Glasses Augmented Matching Algorithm Based on Key Features of Facial Detection[J].,2022,32(07):181.[doi:10. 3969 / j. issn. 1673-629X. 2022. 04. 031]
[8]宋燕燕.基于 ARCore 的移动增强现实应用系统设计[J].计算机技术与发展,2022,32(07):196.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 034]
　SONG Yan-yan.Design of Mobile Augmented Reality System Based on ARCore[J].,2022,32(07):196.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 034]
[9]贾一鑫,邓魏永,殷 强,等.基于改进 SURF 的增强现实图像匹配方法[J].计算机技术与发展,2024,34(01):59.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 009]
　JIA Yi-xin,DENG Wei-yong,YIN Qiang,et al.Augmented Reality Image Matching Method Based on Improved SURF[J].,2024,34(07):59.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 009]

更新日期/Last Update: 2024-07-10