Improved YOLOv7-tiny’s Object Detection Lightweight Model

doi:10.3778/j.issn.1002-8331.2302-0115

Abstract

Abstract: At present, the object detection algorithm has a large number of parameters and high computational complexity. However, the storage capacity and computing power of mobile terminals are limited and it is difficult to deploy it. So in this paper, it proposes the improved YOLOv7-tiny for mobile terminal devices. An efficient backbone network and a lightweight feature fusion network are further proposed with the ShuffleNet v1-improved and EALN-GS as the basic building units. The combination of the two part can reduce computational complexity, obtain more rich semantic information, and further improve detection accuracy. The Mish activation function is used to increase nonlinear expression and improve the generalization ability of the model. Experimental results show that compared with the original model, the accuracy of the improved model is improved by 3.3%, the number of parameters and calculations are reduced by 4.8% and 13.7%, and the model scale is reduced by 8.7%. The improved YOLOv7-tiny reduces the amount of parameters and calculations of the model while maintaining high accuracy, further improves the detection effect, and provides feasibility for deployment in edge terminal devices.

Key words: object detection, YOLOv7-tiny, ShuffleNet v1, lightweight, Mish activation function, GSConv module

摘要： 当前目标检测算法参数量大、计算复杂度高，难以部署在计算资源有限的边缘终端设备上，为此，提出一种改进的YOLOv7-tiny模型。引入ShuffleNet v1网络，改进后作为新的特征提取网络，增强对图像特征的提取，降低计算复杂度，获取更多丰富的语义信息，进一步提升检测精度；引入GSConv（鬼影混洗卷积）模块改进网络的Neck层，在降低参数量和计算量前提下，提升检测效果；采用Mish激活函数，增加非线性表达，提高模型的泛化能力。实验结果表明，改进后的模型与原模型相比，精度提高了3.3%，参数量和计算量分别下降了4.8%和13.7%，模型规模降低了8.7%。改进后的YOLOv7-tiny在保持较高的精度下，降低了模型的参数量和计算量，进一步提升了检测效果，为在边缘终端设备部署提供了可行性。

关键词: 目标检测, YOLOv7-tiny, ShuffleNet v1, 轻量化, Mish激活函数, GSConv模块

LIU Haohan, FAN Yiming, HE Huaiqing, HUI Kanghua. Improved YOLOv7-tiny’s Object Detection Lightweight Model[J]. Computer Engineering and Applications, 2023, 59(14): 166-175.

刘浩翰, 樊一鸣, 贺怀清, 惠康华. 改进YOLOv7-tiny的目标检测轻量化模型[J]. 计算机工程与应用, 2023, 59(14): 166-175.

References

[1] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[2] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[3] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：1137-1149.
[4] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[5] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision，2016：21-37.
[6] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[7] HOWARD A G，ZHU M，CHEN B，et al.Mobilenets：efficient convolutional neural networks for mobile vision applications[J].arXiv：1704.04861，2017.
[8] HAN K，WANG Y，TIAN Q，et al.Ghostnet：more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：1580-1589.
[9] ZHANG X，ZHOU X，LIN M，et al.Shufflenet：an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：6848-6856.
[10] 张利红，蔡敬菊.基于轻量化Yolov5算法的目标检测系统[J].计算机技术与发展，2022，32（11）：134-139.
ZHANG L H，CAI J J.Target detection system based on lightweight Yolov5 algorithm[J].Computer Technology and Development，2022，32（11）：134-139.
[11] 黄磊，杨媛，杨成煜，等.FS-YOLOv5：轻量化红外目标检测方法[J].计算机工程与应用，2023，59（9）：215-224.
HUANG L，YANG Y，YANG C Y，et al.FS-YOLOv5：lightweight infrared rode target detection method[J].Computer Engineering and Applications，2023，59（9）：215-224.
[12] 郭宇阳，胡伟超，戴帅，等.面向路侧交通监控场景的轻量车辆检测模型[J].计算机工程与应用，2022，58（6）：192-199.
GUO Y Y，HU W C，DAI S，et al.Ligh weight vehicle detection model for roadside traffic monitoring scenarios[J].Computer Engineering and Applications，2022，58（6）：192-199.
[13] 徐正军，张强，许亮.一种基于改进YOLOv5s-Ghost网络的交通标志识别方法[J].光电子·激光，2023，34（1）：52-61.
XU Z J，ZHANG Q，XU L.A traffic sign recognition method based on improved YOLOv5s-Ghost network[J].Journal of Optoelectronics·Laser，2023（1）：52-61.
[14] HUANG Y，ZHOU Y，LAN J，et al.Ghost feature network for super-resolution[C]//2020 Cross Strait Radio Science & Wireless Technology Conference（CSRSWTC），2020：1-3.
[15] 薄景文，张春堂.基于YOLOv3的轻量化口罩佩戴检测算法[J].电子测量技术，2021，44（23）：105-110.
BO J W，ZHANG C T.Lightweight mask wearing detection algorithm based on YOLOv3[J].Electronic Measurement Technology，2021，44（23）：105-110.
[16] MA N，ZHANG X，ZHENG H T，et al.Shufflenet v2：practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：116-131.
[17] 王新彦，易政洋.基于改进YOLOv5的割草机器人工作环境障碍物检测方法研究[J].中国农机化学报，2023，44（3）：171-176.
WANG X Y，YI Z Y.Research on obstacle detection method of mowing robot working environment based on improved YOLOv5[J].Journal of Chinese Agricultural Mecha-
nization，2023，44（3）：171-176.
[18] 李成跃，姚剑敏，林志贤，等.基于改进YOLO轻量化网络的目标检测方法[J].激光与光电子学进展，2020，57（14）：45-53.
LI C Y，YAO J M，LIN Z X，et al.Object detection method based on improved YOLO lightweight network[J].Laser & Optoelectronics Progress，2022，57（14）：45-53.
[19] LI H，LI J，WEI H，et al.Slim-neck by GSConv：a better design paradigm of detector architectures for autonomous vehicles[J].arXiv：2206.02424，2022.
[20] MISRA D.Mish：a self regularized non-monotonic neural activation function[J].arXiv：1908.08681，2019.
[21] WANG C Y，BOCHKOVSKIY A，LIAO H Y M.YOLOv7：trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J].arXiv：2207.02696，2022.
[22] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.Yolov4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[23] GE Z，LIU S，WANG F，et al.Yolox：exceeding yolo series in 2021[J].arXiv：2107.08430，2021.
[24] 邱天衡，王玲，王鹏.基于改进YOLOv5的目标检测算法研究[J].计算机工程与应用，2022，58（13）：63-73.
QIU T H，WANG L，WANG P.Research on object detection algorithm based on improved YOLOv5[J].Computer Engineering and Application，2022，58（13）：63-73.