Object detection method based on CIoU improved bounding box loss function

您当前的位置：

首页 >

文章列表页 >

Object detection method based on CIoU improved bounding box loss function

Image Processing | 更新时间：2023-05-09

- Object detection method based on CIoU improved bounding box loss function
- Chinese Journal of Liquid Crystals and Displays Vol. 38, Issue 5, Pages: 656-665(2023)
- 作者机构：
  
  1.武汉科技大学信息科学与工程学院，湖北武汉430081
  2.冶金自动化与检测技术教育部工程研究中心，湖北武汉430081
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62173262)
- DOI：10.37188/CJLCD.2022-0282
  CLC： TP391
- Received：25 August 2022，
  
  Revised：16 September 2022，
  
  Published：05 May 2023
- 稿件说明：
移动端阅览
LIU Xiong-biao, YANG Xian-zhao, CHEN Yang, et al. Object detection method based on CIoU improved bounding box loss function[J]. Chinese journal of liquid crystals and displays, 2023, 38(5): 656-665.
DOI：

LIU Xiong-biao, YANG Xian-zhao, CHEN Yang, et al. Object detection method based on CIoU improved bounding box loss function[J]. Chinese journal of liquid crystals and displays, 2023, 38(5): 656-665. DOI： 10.37188/CJLCD.2022-0282.

摘要

损失函数对于目标检测任务的检测精度和模型收敛速度具有重要作用，而损失函数中的边界框损失函数是影响检测结果和模型收敛速度的重要因素。针对传统模型定位精度低和训练时模型收敛慢的问题，本文在CIoU边界框损失函数的基础上提出一种改进的边界框损失函数，解决了CIoU损失函数求导过程中由边界框宽高比带来的梯度爆炸问题和模型提前退化的问题，并且引入重叠区域与目标框的宽高关系和中心点之间的归一化距离作为附加的惩罚项，提高了模型的检测精度和收敛速度，这种损失函数称为BCIoU（Better CIoU）。在PASACL VOC 2007数据集上的实验结果表明，改进的BCIoU边界框损失函数在YOLOv3网络下相对于IoU损失的mAP50指标相对提升了2.09%，AP指标相对提升了6.88%；相对于CIoU损失的mAP50指标相对提升了1.64%，AP指标相对提升了5.35%。模型的收敛速度也有一定程度的提升。本文提出的BCIoU损失函数提高了模型的检测精度和模型收敛速度，并且可以很方便地纳入到当前目标检测算法中。

Abstract

The loss function plays an important role in the detection accuracy and model convergence speed of the object detection task， and the bounding box loss function in the loss function is an important factor affecting the detection results and model convergence speed. To address the problems of low accuracy for traditional model localization and slow convergence of the model during training， an improved bounding box loss function is proposed based on the CIoU bounding box loss function， which solves the problem of gradient explosion and early degradation of the model brought by the bounding box aspect ratio during the derivation of CIoU loss function， and introduces the normalized distance between the aspect relationship and centroid of the overlap region and the target box as additional penalty terms to improve the detection accuracy and convergence speed of the model， which is called BCIoU （Better CIoU）. Experimental results on the PASACL VOC 2007 dataset show that the improved BCIoU bounding box loss function improves the IoU loss mAP50 metric by 2.09% and the AP metric by 6.88% relatively under the YOLOv3 network， the CIoU loss mAP50 metric improves by 1.64% and the AP metric improves by 5.35%. The convergence speed of the model is also improved to some extent. The proposed BCIoU loss function improves detection accuracy and convergence speed of the model， and can be easily incorporated into current object detection algorithms.

关键词

Keywords

references

LIU L ， OUYANG W L ， WANG X G ， et al . Deep learning for generic object detection： a survey ［J］. International Journal of Computer Vision ， 2020 ， 128 （ 2 ）： 261 - 318 . doi: 10.1007/s11263-019-01247-4 http://dx.doi.org/10.1007/s11263-019-01247-4

ZHAO Z Q ， ZHENG P ， XU S T ， et al . Object detection with deep learning： a review ［J］. IEEE Transactions on Neural Networks and Learning Systems ， 2019 ， 30 （ 11 ）： 3212 - 3232 . doi: 10.1109/tnnls.2018.2876865 http://dx.doi.org/10.1109/tnnls.2018.2876865

GIRSHICK R ， DONAHUE J ， DARRELL T ， et al . Rich feature hierarchies for accurate object detection and semantic segmentation ［C］// Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition . Columbus ： IEEE ， 2014 ： 580 - 587 . doi: 10.1109/cvpr.2014.81 http://dx.doi.org/10.1109/cvpr.2014.81

KRIZHEVSKY A ， SUTSKEVER I ， HINTON G E . ImageNet classification with deep convolutional neural networks ［C］// Proceedings of the 25th International Conference on Neural Information Processing Systems . Lake Tahoe Nevada ： Curran Associates Inc. ， 2012 ： 1097 - 1105 .

HE K M ， ZHANG X Y ， REN S Q ， et al . Spatial pyramid pooling in deep convolutional networks for visual recognition ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2015 ， 37 （ 9 ）： 1904 - 1916 . doi: 10.1109/tpami.2015.2389824 http://dx.doi.org/10.1109/tpami.2015.2389824

GIRSHICK R . Fast R-CNN ［C］// Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago ： IEEE ， 2015 ： 1440 - 1448 . doi: 10.1109/iccv.2015.169 http://dx.doi.org/10.1109/iccv.2015.169

SIMONYAN K ， ZISSERMAN A . Very deep convolutional networks for large-scale image recognition ［C］// Proceedings of the 3rd International Conference on Learning Representations . San Diego ： ICLR ， 2015 ： 384 - 388 .

EVERINGHAM M ， VAN GOOL L ， WILLIAMS C K I ， et al . The Pascal visual object classes （VOC） challenge ［J］. International Journal of Computer Vision ， 2010 ， 88 （ 2 ）： 303 - 338 . doi: 10.1007/s11263-009-0275-4 http://dx.doi.org/10.1007/s11263-009-0275-4

REN S Q ， HE K M ， GIRSHICK R ， et al . Faster R-CNN： towards real-time object detection with region proposal networks ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2017 ， 39 （ 6 ）： 1137 - 1149 . doi: 10.1109/tpami.2016.2577031 http://dx.doi.org/10.1109/tpami.2016.2577031

REDMON J ， DIVVALA S ， GIRSHICK R ， et al . You only look once： unified， real-time object detection ［C］// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas ： IEEE ， 2016 ： 779 - 788 . doi: 10.1109/cvpr.2016.91 http://dx.doi.org/10.1109/cvpr.2016.91

LIU W ， ANGUELOV D ， ERHAN D ， et al . SSD： single shot MultiBox detector ［C］// Proceedings of the 14th European Conference on Computer Vision . Amsterdam， The Netherlands ： Springer ， 2016 ： 21 - 37 . doi: 10.1007/978-3-319-46448-0_2 http://dx.doi.org/10.1007/978-3-319-46448-0_2

REDMON J ， FARHADI A . YOLO9000： better， faster， stronger ［C］// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu ： IEEE ， 2017 ： 6517 - 6525 . doi: 10.1109/cvpr.2017.690 http://dx.doi.org/10.1109/cvpr.2017.690

REDMON J ， FARHADI A . YOLOv3： an incremental improvement ［J/OL］. arXiv ， 2018 ： 1804 . 02767 . doi: 10.1109/cvpr.2017.690 http://dx.doi.org/10.1109/cvpr.2017.690

LIN T Y ， GOYAL P ， GIRSHICK R ， et al . Focal loss for dense object detection ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2020 ， 42 （ 2 ）： 318 - 327 . doi: 10.1109/tpami.2018.2858826 http://dx.doi.org/10.1109/tpami.2018.2858826

TAN M X ， PANG R M ， LE Q V . EfficientDet： scalable and efficient object detection ［C］// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle ： IEEE ， 2020 . doi: 10.1109/cvpr42600.2020.01079 http://dx.doi.org/10.1109/cvpr42600.2020.01079

YU J H ， JIANG Y N ， WANG Z Y ， et al . UnitBox： an advanced object detection network ［C］// Proceedings of the 24th ACM international conference on Multimedia . Amsterdam ： ACM ， 2016 ： 516 - 520 . doi: 10.1145/2964284.2967274 http://dx.doi.org/10.1145/2964284.2967274

REZATOFIGHI H ， TSOI N ， GWAK J ， et al . Generalized intersection over union： a metric and a loss for bounding box regression ［C］// Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach ： IEEE ， 2019 . doi: 10.1109/cvpr.2019.00075 http://dx.doi.org/10.1109/cvpr.2019.00075

ZHENG Z H ， WANG P ， LIU W ， et al . Distance-IoU loss： faster and better learning for bounding box regression ［J］. Proceedings of the AAAI Conference on Artificial Intelligence ， 2020 ， 34 （ 7 ）： 12993 - 13000 . doi: 10.1609/aaai.v34i07.6999 http://dx.doi.org/10.1609/aaai.v34i07.6999

董潇潇，何小海，吴晓红，等 . 基于注意力掩模融合的目标检测算法［J］. 液晶与显示， 2019 ， 34 （ 8 ）： 825 - 833 ． doi: 10.3788/yjyxs20193408.0825 http://dx.doi.org/10.3788/yjyxs20193408.0825

DONG X X ， HE X H ， WU X H ， et al . Object detection algorithm based on attention mask fusion ［J］. Chinese Journal of Liquid Crystals and Displays ， 2019 ， 34 （ 8 ）： 825 - 833 . （in Chinese） . doi: 10.3788/yjyxs20193408.0825 http://dx.doi.org/10.3788/yjyxs20193408.0825

唐悦，吴戈，朴燕 . 改进的GDT-YOLOv3目标检测算法［J］. 液晶与显示， 2020 ， 35 （ 8 ）： 852 - 860 ． doi: 10.37188/yjyxs20203508.0852 http://dx.doi.org/10.37188/yjyxs20203508.0852

TANG Y ， WU G ， PIAO Y . Improved algorithm of GDT-YOLOv3 image target detection ［J］. Chinese Journal of Liquid Crystals and Displays ， 2020 ， 35 （ 8 ）： 852 - 860 . （in Chinese） . doi: 10.37188/yjyxs20203508.0852 http://dx.doi.org/10.37188/yjyxs20203508.0852

吴海滨，魏喜盈，刘美红，等 . 结合空洞卷积和迁移学习改进YOLOv4的X光安检危险品检测［J］. 中国光学， 2021 ， 14 （ 6 ）： 1417 - 1425 ． doi: 10.37188/CO.2021-0078 http://dx.doi.org/10.37188/CO.2021-0078

WU H B ， WEI X Y ， LIU M H ， et al . Improved YOLOv4 for dangerous goods detection in X-ray inspection combined with atrous convolution and transfer learning ［J］. Chinese Optics ， 2021 ， 14 （ 6 ）： 1417 - 1425 . （in Chinese） . doi: 10.37188/CO.2021-0078 http://dx.doi.org/10.37188/CO.2021-0078

0

Views

400

下载量

5

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Related Articles

Object detection algorithm based on adaptive focal CRIoU loss

Object detection algorithm based on attention mask fusion

Improved autonomous driving object detection based on YOLOv8s

Related Author

XIAO Zhen-jiu

ZHAO Hao-ze

ZHANG Li-li

XIA Yu

GUO Jie-long

YU Hui

LI Cheng-long

WANG Li-wen

Related Institution

College of Software Engineering， Liaoning Technical University

Air Ammunition Research Institute Co. Ltd.， NORINCO Group， Haerbin

Shanghai Institute of Aerospace System Engineer

Quanzhou Institute of Equipment Manufacturing， Haixi Institutes， Chinese Academy of Sciences

College of Electronics and Information Engineering, Sichuan University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰