[1]张张详,陈 宁.改进的YOLOv8n在复杂环境下的车辆识别算法[J].浙江科技大学学报,2024,(05):404-416.[doi:10.3969/j.issn.2097-5236.2024.05.006]
　ZHANG Zhangxiang,CHEN Ning.Improved YOLOv8n vehicle recognition algorithm under complex circumstances[J].,2024,(05):404-416.[doi:10.3969/j.issn.2097-5236.2024.05.006]
点击复制

改进的YOLOv8n在复杂环境下的车辆识别算法(/HTML)
分享到：

《浙江科技大学学报》[ISSN:2097-5236/CN:33-1431/Z]

卷:
期数:
2024年05期
页码:
404-416
栏目:
出版日期:
2024-10-28

文章信息/Info

Title:
Improved YOLOv8n vehicle recognition algorithm under complex circumstances
文章编号:
2097-5236(2024)05-0404-13
作者:
张张详; 陈 宁
(浙江科技大学 机械与能源工程学院,杭州 310023)
Author(s):
ZHANG Zhangxiang;  CHEN Ning
(School of Mechanical and Energy Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, Zhejiang, China)
关键词:
车辆检测;  ECA通道注意力;  可变形卷积网络;  加权双向特征金字塔;  Focal-EIOU loss
分类号:
TP391.41
DOI:
10.3969/j.issn.2097-5236.2024.05.006
文献标志码:
A
摘要:
【目的】针对城市复杂环境下的车辆难识别问题,提出了基于YOLOv8n(you only look once version 8n)的改进模型DB -YOLOv8n(deformable block YOLOv8n)。【方法】首先在颈部网络融合通道注意力机制(efficient channel attention,ECA)和改进加权双向特征金字塔网络(bidirectional feature pyramid network,BiFPN),以增强在昏暗光线下的车辆检测性能及对多尺度图像的处理能力,特别是对远处或部分遮挡的车辆; 其次在主干网络引入可变型卷积(deformable convolutional networks,DCN),以增强模型对不同尺寸车辆的适应性; 最后使用精确边界框回归的高效交并比损失函数(focal and efficient intersection over union loss,Focal-EIOU loss)替换高效交并比(efficient intersection over union,EIOU),进一步提升模型的稳定性。【结果】DB -YOLOv8n在自制车辆数据集上相比YOLOv8n,平均精度、精度和召回率分别提高了3.2%、3%和2%。【结论】本研究结果能为提高车辆检测的精确度提供理论参考。

参考文献/References:

[1] 郑玉珩,黄德启.改进MobileViT与YOLOv4的轻量化车辆检测网络[J].电子测量技术,2023,46(2):175.
[2] DONG X D, YAN S, DUAN C Q. A lightweight vehicles detection network model based on YOLOv5[J]. Engineering Applications of Artificial Intelligence, 2022, 113:104914.
[3] 胡伟超,郭宇阳,张奇,等.基于改进YOLOX的轻量化交通监控目标检测算法[J].计算机工程与应用,2024,60(7):167.
[4] 刘浩翰,樊一鸣,贺怀清,等.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.
[5] 周飞,郭杜杜,王洋,等.基于改进YOLOv8的交通监控车辆检测算法[J].计算机工程与应用,2024,60(6):110.
[6] 张利丰,田莹.改进YOLOv8的多尺度轻量型车辆目标检测算法[J].计算机工程与应用,2024,60(3):129.
[7] ZHENG X, ZOU J, DU S, et al. Small target detection in refractive panorama surveillance based on improved YOLOv8[J]. Sensors, 2024, 24(3):819.
[8] NIU Y, CHENG W, SHI C, et al. YOLOv8-CGRNet:a lightweight object detection network leveraging context guidance and deep residual learning[J]. Electronics, 2023, 13(1):43.
[9] LIU Q, YE H, WANG S, et al. YOLOv8-CB:dense pedestrian detection algorithm based on In-Vehicle camera[J]. Electronics, 2024, 13(1):236.
[10] LI N, YE T, ZHOU Z, et al. Enhanced YOLOv8 with BiFPN-SimAM for percise defect detection in miniature capacitors[J]. Applied Sciences, 2024, 14(1):429.
[11] ZHU X Z, HU H, LIN S, et al. Deformable convnets v2:more deformable, better results[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE/CVF, 2019:9308.
[12] WANG Q L, WU B G, ZHU P F, et al. ECA-Net:Efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition. Seattle:IEEE/CVF, 2020:11534.
[13] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C] // Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE, 2017:936.
[14] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation [C] // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE/CVF, 2018:8759.
[15] TAN M, PANG R, LE Q V. Efficientdet:scalable and efficient object detection [C] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle:IEEE/CVF, 2020:10781.

备注/Memo

备注/Memo:
收稿日期:2024-02-26
基金项目:国家重点研发计划“政府间国际科技创新合作重点专项”项目(2019YFE0126100); 浙江省“一带一路”国际科技合作项目(2019C04025)
通信作者:陈 宁(1975— ),男,陕西省汉中人,教授,博士,主要从事智能交通系统、智能网联汽车研究。E-mail:neilching@163.com。
更新日期/Last Update: 2024-10-28