计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (3): 266-276.doi: 10.11896/jsjkx.241100115

• 计算机图形学 & 多媒体 • 上一篇    下一篇

融合ByteTrack的EAP-YOLOv8无人机Marker点检测与追踪

唐心亮1, 潘晓润1, 王建超1, 苏鹤2   

  1. 1 河北科技大学信息科学与工程学院 石家庄 050018
    2 河北工业大学电气工程 天津 300401
  • 收稿日期:2024-11-19 修回日期:2025-03-04 发布日期:2026-03-12
  • 通讯作者: 王建超(15380349158@163.com)
  • 作者简介:(375555@qq.com)
  • 基金资助:
    河北省高等学校科学技术研究项目(QN2023185)

Integrate ByteTrack’s EAP-YOLOv8 UAV Marker Point Detection and Tracking

TANG Xinliang1, PAN Xiaorun1, WANG Jianchao1, SU He2   

  1. 1 School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China
    2 Electrical Engineering, Hebei University of Technology, Tianjin 300401, China
  • Received:2024-11-19 Revised:2025-03-04 Online:2026-03-12
  • About author:TANG Xinliang,born in 1977,Ph.D,researcher.His main research interests include intelligent manufacturing and image processing.
    WANG Jianchao,born in 1991,Ph.D,lecturer.His main research interests include intelligent information processing and machine vision.
  • Supported by:
    Hebei Provincial Higher Education Science and Technology Research Project(QN2023185).

PDF (PC)

151

摘要： 随着科技不断发展,无人机的应用越来越广泛,实现无人机的精准动作捕捉成为其核心技术。光学动作捕捉系统在对无人机进行检测与追踪时,由于受到复杂环境、飞行速度等多方面的干扰,会出现对无人机所粘贴的Marker点识别不准确的情况。为了解决这一问题,提出一种基于YOLOv8改进的目标检测算法EAP-YOLOv8,以提高Marker点识别检测的准确率。首先,在骨干部分构建新型通道注意力机制MAP-ECA,增强全局视角信息和不同尺度大小的特征,提升了小目标的检测能力;其次,在原有检测头的基础上利用多层次自适应特征融合形成新的检测头D-SASFF,利用多尺度融合来强化小目标特征信息;最后,设计了损失函数PIoUv3,通过改进加快了模型收敛速度,提高了小目标检测能力。为验证EAP-YOLOv8算法的有效性,在自制数据集上进行实验,结果表明,EAP-YOLOv8算法在mAP@0.5和mAP@0.5:0.95上分别达到了96.5%和50.2%,相较于其他算法有显著提升。在此基础之上,通过结合多目标追踪算法ByteTrack显著提高了Marker点的追踪准确率。此外,在公开数据集MOT16上进行追踪实验,结果表明,所提模型在HOTA,MOTA,MOTP上追踪准确率分别达到了37.60%,25.64%,80.76%,相较于当前算法有显著提升,为后续实现无人机精准跟踪提供了有效途径。

关键词: EAP-YOLOv8, 无人机检测, Marker点, 小目标检测, 多目标追踪, ByteTrack

Abstract: With the development of science and technology,drones are more and more widely used,and the realization of accurate motion capture of drones has become its core technology.When the optical motion capture system detects and tracks the UAV,due to the interference of complex environment,flight speed and other aspects,the Marker point pasted by the UAV will be inaccurate.In order to solve this problem,an improved object detection algorithm EAP-YOLOv8 based on YOLOv8 is proposed to improve the accuracy of Marker point recognition detection.Firstly,a new channel attention mechanism MAP-ECA is constructed in the backbone part,which enhances the global perspective information and the characteristics of different scales,and improves the detection ability of small targets.Secondly,on the basis of the original detection head,the multi-level adaptive feature fusion is used to form a new detection head,D-SASFF,and the multi-scale fusion is used to strengthen the feature information of small targets.Finally,the loss function PIoUv3 is designed,which accelerates the convergence speed of the model and improves the detection ability of small targets.In order to verify the effectiveness of the EAP-YOLOv8 algorithm,experiments are carried out on the self-made dataset,and the results show that the EAP-YOLOv8 algorithm reaches 96.5% and 50.2% on mAP@0.5 and mAP@0.5:0.95,respectively,which is significantly improved compared with other algorithms.On this basis,the tracking accuracy of Marker points is significantly improved by combining the multi-target tracking algorithm ByteTrack,and the tracking experiments are carried out on the public dataset MOT16,and the results show that the new model reaches 37.60%,25.64% and 80.76% on HOTA,MOTA and MOTP,respectively,which is significantly improved compared with the current algorithms,providing an effective way for the subsequent accurate tracking of UAVs.

Key words: EAP-YOLOv8, Drone detection, Marker point, Small target detection, Multi-target tracking, ByteTrack

中图分类号: 

  • TP391
[1]BALLARD D H.Generalizing the Hough transform to detect arbitrary shapes[J].Pattern Recognition,1981,13(2):111-122.
[2]LYU X,LIU F,REN P,et al.An image processing approach to measuring the sphericity and roundness of fracturing proppants[J].IEEE Access,2019,7:16078-16087.
[3]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich FeatureHierarchies for Accurate Object Detection and Semantic Segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.2014.
[4]REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:To-wards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis and Machine Lntelligence,2017,39(6):1137-1149.
[5]LI W K,ZHANG S Q.Mask feature fusion:a new paradigm of instance segmentation[J].Computer Engineering,2025(2):126-138.
[6]XU Y W,LI J,DONG Y F,et al.YOLO series object detection algorithm review[J].Computer Science and Exploration,2024,18(9):2221-2238.
[7]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single ShotMultibox Detector[C]//European Conference on Computer Vision.Berlin:Springer,2016:21-37.
[8]WANG G,CHEN Y,AN P,et al.UAV-YOLOv8:A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios[J].Sensors,2023,23(16):7190.
[9]LIU L,ZHANG S,BAI Y A,et al.Improving YOLOv8’s Lightweight Military Aircraft Detection Algorithm[J].Computer Engineering and Application,2024,60(18):114-125.
[10]YADAV A,CHATURVEDI P K,RANI S.Object Detection and Tracking using YOLOv8 and DeepSORT[EB/OL].https://www.publications.scrs.in/uploads/final_menuscript/6200cb6958c1909085022aae542b8792.pdf.
[11]ZHAI X,HUANG Z,LI T,et al.YOLO-Drone:An Optimized YOLOv8 Network for Tiny UAV Object Detection[J].Electronics,2023,12(17):3664.
[12]HU J F,LI B C,ZHU H,et al.Lightweight UAV target detection algorithm for improved YOLOv8[J].Computer Engineering and Applications,2024,60(8):182-191.
[13]LIU Y,LI Y,XU D.et al.Adaptive Kalman Filter with power transformation for online multi-object tracking[J].Multimedia Systems,2023,29:1231-1244.
[14]YOU L,CHEN Y,XIAO C,et al.Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack[J].Electronics,2024,13(15):3033.
[15]YASIR M,LIU S W,XU M M,et al.YOLOv8-BYTE:Shiptracking algorithm using short-time sequence SAR images for disaster response leveraging GeoAI[J].International Journal of Applied Earth Observation and Geoinformation,2024,128:103771.
[16]ARIOKA K,SAWADA Y.Improved Kalman Filter and Ma-tching Strategy for Multi-Object Tracking System[C]//2023 62nd Annual Conference of the Society of Instrument and Control Engineers(SICE).IEEE,2023:772-777.
[17]XU C J,WANG X F,YANG Y D.Attention-YOLO:YOLO detection algorithm with attention mechanism[J].Computer Engineering and Applications,2019,55(6):13-23,125.
[18]WANG Q,WU B,ZHU P,et al.ECA-Net:Efficient channel attention for deep convolutional neural networks[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:11534-11542.
[19]LIU S,HUANG D,WANG Y.Learning spatial fusion for single-shot object detection[J].arXiv:1911.09516,2019.
[20]LIU Y,CHEN J,LU P,et al.MFID-Net:multi-scaled feature-fused image dehazing via dynamic weights[J].Displays,2023,78:102416.
[21]SEKHARAMANTRY P K,MELGANI F,MALACARNE J.Deep learning-based apple detection with attention module and improved loss function in YOLO[J].Remote Sensing,2023,15(6):1516.
[22]ZHENG Z,WANG P,LIU W,et al.Distance-IoU loss:Fasterand better learning for bounding box regression[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.2020:12993-13000.
[23]LIU Y,LI Y,XU D,et al.Adaptive Kalman Filter with power transformation for online multi-object tracking[J].Multimedia Systems,2023,29(3):1231-1244.
[24]LIANG X G,LI H,CHENG Y Z,et al.Multi-target trackingbased on spatio-temporal embedding perception and multi-task collaborative optimization[J].Computer Engineering and Applications,2024,60(6):282-292.
[25]LUITEN J,OSEP A,DENDORFER P,et al.Hota:A higher order metric for evaluating multi-object tracking[J].International Journal of Computer Vision,2021,129:548-578.
[26]GE Q B,LI K,ZHANG X G.Relative Pose Estimation Algo-rithm for UAV Based on Multi-Key Point Detection Weighted Fusion[J].Acta Automatica Sinica,2024,50(7):1-15.
[27]YIN X,YU Z,FEI Z,et al.Pe-yolo:Pyramid enhancement network for dark object detection[C]//International Conference on Artificial Neural Networks.Cham:Springer,2023:163-174.
[28]WANG C C,HE W,NIE Y,et al.Gold-YOLO:Efficient object detector via gather-and-distribute mechanism[J].arXiv:2309.11331,2023.
[29]SHENG W,SHEN J,HUANG Q,et al.Multi-objective pedestrian tracking method based on YOLOv8 and improved DeepSORT.[J].Mathematical Biosciences and Engineering,2024,21(2):1791-1805.
[30]LIN M Y.Research on vehicle pedestrian detection and tracking algorithm based on improved YOLOv5[D].Liuzhou:Guangxi University of Science and Technology,2023.
[31]MILAN A,LEAL-TAIXÉ L,REID I,et al.MOT16:A benchmark for multi-object tracking[J].arXiv:1603.00831,2016.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发