基于改进PPYOLOE-R的信息码矫正研究

doi:10.19678/j.issn.1000-3428.0068127

计算机工程 ›› 2024, Vol. 50 ›› Issue (6): 358-366. doi: 10.19678/j.issn.1000-3428.0068127

基于改进PPYOLOE-R的信息码矫正研究

赵云涛¹, 肖俊杰², 李维刚², 熊雅婷²

1. 武汉科技大学冶金自动化与检测技术教育部工程研究中心, 湖北武汉 430081;
2. 武汉科技大学信息科学与工程学院, 湖北武汉 430081

收稿日期:2023-07-21 修回日期:2023-08-23 发布日期:2023-10-30
通讯作者: 肖俊杰,E-mail:1632191437@qq.com E-mail:1632191437@qq.com
基金资助:
湖北省教育厅科学技术研究项目(B2020012)。

Research on Information Code Correction Based on Improved PPYOLOE-R

ZHAO Yuntao¹, XIAO Junjie², LI Weigang², XIONG Yating²

1. Engineering Research Center of Metallurgical Automation and Testing Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, Hubei, China;
2. College of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, Hubei, China

Received:2023-07-21 Revised:2023-08-23 Published:2023-10-30

摘要/Abstract

摘要： 信息码识别技术推动着社会的进步,使人们的生活更加便捷。由于受所处拍照环境影响,信息码识别效果有待提高,而且信息码角度倾斜也会影响解码正确率。以基于信息码的电力互感器误差实验接线判断为背景,提出一种基于改进PPYOLOE-R的信息码矫正算法。首先以PPYOLOE-R检测算法为基础,融合轻量级网络ESNet,在提升精度的同时降低模型参数量;其次引入动态卷积进一步加强特征提取,减少模型因下采样丢失信息,加强模型通道特征提取能力;最后为满足人工智能(AI)边缘设备上的实时性要求,采用模型融合技术将推理模型进行融合,保证在模型精度不变的情况下提升模型检测速度。为丰富数据集,采用两步旋转数据增强和Mosaic+Mixup数据增强方法,充分利用数据集中已有信息,提高模型学习能力。实验结果表明,改进后算法精度达到89.46%,较原模型提升了1.95%,检测照片速度从每张154 ms提升至每张50 ms。相较其他算法,改进算法具有体积小和速度快的优势,通过算法矫正后的信息码,可显著提高解码效率和正确率。

关键词: 信息码矫正, 人工智能边缘计算, PPYOLOE-R算法, 动态卷积, 模型融合

Abstract: Information-code recognition technology promotes societal progress and provides convenience. Owing to the effect of the photography environment, the information-code recognition effect must be improved, and the information-code angle tilt affects the decoding accuracy. Using information code-based power-transformer error test wiring judgment as the background, this paper proposes an information-code correction algorithm based on the improved PPYOLOE-R. First, based on the PPYOLOE-R detection algorithm, a lightweight network, ESNet, is integrated to improve accuracy and reduce the number of model parameters. Second, dynamic convolution is introduced to further enhance feature extraction, reduce information loss in the model due to subsampling, and enhance the feature-extraction capability of the model channel. Finally, to satisfy the real-time requirements of Artificial Intelligence(AI) edge devices, model fusion technology is applied to fuse the inference model to improve the model detection speed without changing the accuracy of the model. To enrich the dataset, two-step rotation data-enhancement and Mosaic + Mixup data-enhancement methods are used to fully utilize existing information in the dataset and improve the learning ability of the model. Experimental results show that the accuracy of the improved algorithm is 89.46%, which is 1.95% higher than that of the original model, and that the detection speed increases from 154 to 50 ms per photograph. Compared with other algorithms, the improved algorithm offers the advantages of small size and high speed, and the decoding efficiency and accuracy can be improved significantly using the corrected information code.

Key words: information code correction, Artificial Intelligence(AI) edge computing, PPYOLOE-R algorithm, dynamic convolution, model fusion

中图分类号:

TP391

赵云涛, 肖俊杰, 李维刚, 熊雅婷. 基于改进PPYOLOE-R的信息码矫正研究[J]. 计算机工程, 2024, 50(6): 358-366.

ZHAO Yuntao, XIAO Junjie, LI Weigang, XIONG Yating. Research on Information Code Correction Based on Improved PPYOLOE-R[J]. Computer Engineering, 2024, 50(6): 358-366.

https://www.ecice06.com/CN/Y2024/V50/I6/358

参考文献

[1] XU L C, KAMAT V R, MENASSA C C. Automatic extraction of 1D barcodes from video scans for drone-assisted inventory management in warehousing applications[J]. International Journal of Logistics Research and Applications, 2018, 21(3):243-258.
[2] YUN I, KIM J. Vision-based 1D barcode localization method for scale and rotation invariant[C]//Proceedings of TENCON'17. Washington D. C.,USA:IEEE Press, 2017:2204-2208.
[3] WANG Z H, CHEN A, LI J J, et al. 1D barcode region detection based on the Hough transform and support vector machine[M]. Berlin, Germany:Springer, 2016.
[4] CHOU T H, HO C S, KUO Y F. QR code detection using convolutional neural networks[C]//Proceedings of 2015 International Conference on Advanced Robotics and Intelligent Systems. Washington D. C.,USA:IEEE Press, 2015:1-5.
[5] ZHANG L, SUI Y, ZHU F, et al. Fast barcode detection method based on ThinYOLOv4[C]//Proceedings of the 5th International Conference on Cognitive Systems and Signal Processing. Berlin, Germany:Springer, 2021:41-55.
[6] ZHANG J H, MIN X K, JIA J, et al. Fine localization and distortion resistant detection of multi-class barcode in complex environments[J]. Multimedia Tools and Applications, 2021, 80(11):16153-16172.
[7] 易帆,李功燕,许绍云.基于多任务目标检测的条形码倾斜矫正算法研究[J].计算机应用与软件, 2019, 36(10):139-144. YI F, LI G Y, XU S Y. Barcode tilt correction algorithm based on multi-task object detection[J]. Computer Applications and Software, 2019, 36(10):139-144.(in Chinese)
[8] WANG X, WANG G, DANG Q, et al. PP-YOLOE-R:an efficient anchor-free rotated object detector[EB/OL].[2023-06-10]. https://arxiv.org/abs/2211.02386.
[9] XU S, WANG X, LU W, et al. PP-YOLOE:an evolved version of YOLO[EB/OL].[2023-06-10]. https://arxiv.org/abs/2203.16250.
[10] 王程,刘元盛,刘圣杰.基于改进YOLOv4的小目标行人检测算法[J].计算机工程, 2023, 49(2):296-302, 313. WANG C, LIU Y S, LIU S J. Small-target pedestrian-detection algorithm based on improved YOLOv4[J]. Computer Engineering, 2023, 49(2):296-302, 313.(in Chinese)
[11] 刘俊豪,王美林,谢兴,等.基于改进YOLOv5的皮革瑕疵检测算法[J].计算机工程, 2023, 49(8):240-249. LIU J H, WANG M L, XIE X, et al. Leather defect detection algorithm based on improved YOLOv5[J]. Computer Engineering, 2023, 49(8):240-249.(in Chinese)
[12] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C.,USA:IEEE Press, 2016:770-778.
[13] DING X H, ZHANG X Y, MA N N, et al. RepVGG:making VGG-style ConvNets great again[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C.,USA:IEEE Press, 2021:13733-13742.
[14] HAN K, WANG Y H, TIAN Q, et al. GhostNet:more features from cheap operations[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C.,USA:IEEE Press, 2020:1580-1589.
[15] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C.,USA:IEEE Press, 2018:7132-7141.
[16] LI C, ZHOU A, YAO A. Omni-dimensional dynamic convolution[EB/OL].[2023-06-10]. https://arxiv.org/abs/2209.07947.
[17] YANG B, BENDER G, LE Q V, et al. Condconv:conditionally parameterized convolutions for efficient inference[C]//Proceedings of NIPS'19. Cambridge, USA:MIT Press, 2019, 32.
[18] ZHANG Y, ZHANG J, WANG Q, et al. Dynet:dynamic convolution for accelerating convolutional neural networks[EB/OL].[2023-06-10]. https://arxiv.org/abs/2004.10694.[JP]
[19] VASU P K A, GABRIEL J, ZHU J, et al. MobileOne:an improved one millisecond mobile backbone[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C.,USA:IEEE Press, 2023:7907-7917.
[20] WADEKAR S N, CHAURASIA A. Mobilevitv3:mobile-friendly vision transformer with simple and effective fusion of local, global and input features[EB/OL].[2023-06-10]. https://arxiv.org/abs/2209.15159.
[21] HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3[C]//Proceedings of IEEE/CVF International Conference on Computer Vision. Washington D. C.,USA:IEEE Press, 2019:1314-1324.
[22] MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNet V2:practical guidelines for efficient CNN architecture design[C]//Proceedings of the 15th European Conference on Computer Vision. Berlin, Germany:Springer, 2018:122-138.
[23] YU G, CHANG Q, LU W, et al. PP-PicoDet:a better real-time object detector on mobile devices[EB/OL].[2023-06-10]. https://arxiv.org/abs/2111.00902.
[24] LI Z H, HOU B, WU Z T, et al. FCOSR:a simple anchor-free rotated detector for aerial object detection[EB/OL].[2023-06-10]. https://arxiv.org/abs/2111.10780.
[25] HAN J M, DING J, LI J, et al. Align deep features for oriented object detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-11.

选择文件类型/文献管理软件名称

选择包含的内容

基于改进PPYOLOE-R的信息码矫正研究

Research on Information Code Correction Based on Improved PPYOLOE-R

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	虞秋辰, 周若华, 袁庆升. 基于Ghost-SE-Res2Net的多模型融合语音唤醒词检测方法[J]. 计算机工程, 2024, 50(3): 52-59.
[2]	邵良杉, 赵松泽. 基于多模型融合的不完整数据分数插补算法[J]. 计算机工程, 2023, 49(9): 79-88, 98.
[3]	郭艳霞, 金勇, 唐宏, 彭金枝. 基于动态卷积与残差门控的多模态情感识别[J]. 计算机工程, 2023, 49(7): 94-101.
[4]	马嘉翔, 宋晓宁. 基于彩票假设的软剪枝算法[J]. 计算机工程, 2023, 49(5): 97-104.
[5]	张法正, 杨娟, 汪荣贵, 薛丽霞. 基于动态自适应层叠网络的轻量化图像超分辨率重建[J]. 计算机工程, 2022, 48(12): 196-202.
[6]	刘月峰, 张公, 张晨荣, 张丽娜, 杨宇慧. 锂离子电池RUL预测方法综述[J]. 计算机工程, 2020, 46(4): 11-18.
[7]	胡彬,王春东,胡思琦,周景春. 基于机器学习的移动终端高级持续性威胁检测技术研究[J]. 计算机工程, 2017, 43(1): 241-246.
[8]	程婷婷,郭立君,黄元捷. 基于鲁棒高阶条件随机场的视频自动分割[J]. 计算机工程, 2015, 41(7): 261-268.
[9]	程乐凯, 翟素兰, 涂铮铮, 罗斌. 视频动态场景下运动物体的自适应跟踪算法[J]. 计算机工程, 2011, 37(19): 22-25.
[10]	曾定;刘加. 母语与非母语语音识别声学建模[J]. 计算机工程, 2010, 36(8): 170-172.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于改进PPYOLOE-R的信息码矫正研究

Research on Information Code Correction Based on Improved PPYOLOE-R

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价