基于改进YOLOv8与ByteTrack的航拍多目标跟踪算法

doi:10.19678/j.issn.1000-3428.0252029

摘要/Abstract

摘要： 目标检测与多目标跟踪技术日益成熟,但在复杂场景下执行航拍多目标跟踪任务时,目标尺寸小、尺寸变化大、遮挡等问题仍会导致检测与跟踪效果不理想。为此,提出一种基于改进YOLOv8与ByteTrack的航拍多目标跟踪算法(YBTrack)。构建MSA-YOLO(Multi-Scale Attention YOLO)检测器,设计空间-深度卷积替换YOLOv8原有卷积,将空间信息转换为通道维度,有效保留目标细节,减少多尺度特征图融合过程中信息丢失导致的漏检、误检。同时设计轻量加速空间-通道注意力模块,用于颈部卷积,降低计算复杂度,并作为检测头前的特征细化模块,进一步增强算法对目标特征信息提取的能力。为提高跟踪效果,对ByteTrack跟踪模型进行优化,设计空间-外观相似度矩阵(ASM),提升模型区分相似目标的性能,并提出目标校正函数,减少卡尔曼滤波器产生的误差积累,降低目标偏移、丢失率。将MSA-YOLO与优化后的ByteTrack结合,开展多目标跟踪实验。其中,MSA-YOLO在VisDrone2019-DET数据集上平均精度均值(mAP@0.5)提高了9.4百分点;多目标跟踪算法在VisDrone2019-MOT、MOT17数据集上多目标跟踪准确率(MOTA)分别提升了11.2和8.3百分点,ID调和均值(IDF1)分别提升了8.9和7.4百分点,实验结果表明本文所提方法跟踪效果显著。此外,与其他多目标跟踪算法的对比实验也证明了本文算法的优越性。

关键词: YOLOv8, ByteTrack, 多目标跟踪, 特征信息, 卡尔曼滤波器

Abstract: Object detection and multi-target tracking technologies are becoming increasingly mature. However, when performing aerial multi-target tracking tasks in complex scenarios, issues such as small target size, large size variation, and occlusion lead to unsatisfactory detection and tracking performances. Therefore, this paper proposes an aerial multi-target tracking algorithm based on an improved YOLOv8 and ByteTrack method called YBTrack. First, a detector called Multi-Scale Attention YOLO (MSA-YOLO) is constructed. The original convolution in YOLOv8 is replaced with a space-depth convolution that transforms spatial information into channel dimensions, effectively preserves target details, and reduces missed and false detections caused by information loss during multiscale feature map fusion. Simultaneously, a lightweight accelerated space-channel attention module is designed for neck convolution to reduce computational complexity. This module also acts as a feature refinement module before the detection head, further enhancing its ability to extract target feature information. Next, the ByteTrack tracking model is optimized to improve the tracking performance. A Spatial-Appearance Similarity Matrix (ASM) is designed to enhance the model's ability to distinguish similar targets. In addition, a target correction function is proposed to reduce the error accumulation of the Kalman filter and decrease the target offset and loss rates. Finally, MSA-YOLO and the optimized ByteTrack are combined for multi-target tracking experiments. MSA-YOLO achieves a 9.4 percentage points improvement in mAP@0.5 on the VisDrone2019-DET dataset. The multi-target tracking algorithm improves the Multiple Object Tracking Accuracy (MOTA) by 11.2 and 8.3 percentage points and the Identification F1 Score (IDF1) by 8.9 and 7.4 percentage points on the VisDrone2019-MOT and MOT17 datasets, respectively. Experimental results demonstrate the excellent tracking performance of the proposed method. Furthermore, comparison experiments with other multitarget tracking algorithms confirm the superiority of the proposed algorithm.

Key words: YOLOv8, ByteTrack, multiple target tracking, feature information, Kalman filter

中图分类号:

TP391

郑明宇, 邵慧超, 邵延华, 楚红雨. 基于改进YOLOv8与ByteTrack的航拍多目标跟踪算法[J]. 计算机工程, 2026, 52(10): 263-274.

ZHENG Mingyu, SHAO Huichao, SHAO Yanhua, CHU Hongyu. Multi-Target Tracking Algorithm for Aerial Photography Based on Improved YOLOv8 and ByteTrack[J]. Computer Engineering, 2026, 52(10): 263-274.

https://www.ecice06.com/CN/Y2026/V52/I10/263

参考文献

[1] 苑玉彬, 吴一全, 赵朗月, 等. 基于深度学习的无人机航拍视频多目标检测与跟踪研究进展[J]. 航空学报, 2023, 44(18): 028334. YUAN Y B, WU Y Q, ZHAO L Y, et al. Research progress of UAV aerial video multi-object detection and tracking based on deep learning[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(18): 028334. (in Chinese)
[2] JIANG P Y, ERGU D, LIU F Y, et al. A review of Yolo algorithm developments[J]. Procedia Computer Science, 2022, 199: 1066-1073.
[3] 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.
[4] 王国明, 贾代旺. 基于YOLOv8的小目标检测模型的优化[J]. 计算机工程, 2025, 51(12): 294-303. WANG G M, JIA D W. Optimization of small object detection model based on YOLOv8[J]. Computer Engineering, 2025, 51(12): 294-303. (in Chinese)
[5] LI H D, QU H C. DASSF: dynamic-attention scale-sequence fusion for aerial object detection[EB/OL]. [2024-12-01]. https://arxiv.org/abs/2406.12285.
[6] SU J, QIN Y C, JIA Z, et al. MPE-YOLO: enhanced small target detection in aerial imaging[J]. Scientific Reports, 2024, 14(1): 17799.
[7] 何植仟, 曹立杰. UAVAI-YOLO: 无人机航拍图像的小目标检测模型[J]. 智能科学与技术学报, 2024, 6(2): 262-271. HE Z Q, CAO L J. UAVAI-YOLO: dense small target detection algorithm based on UAV aerial images[J]. Chinese Journal of Intelligent Science and Technology, 2024, 6(2): 262-271. (in Chinese)
[8] 蒋凌云, 杨金龙. 检测优化的标签多伯努利视频多目标跟踪算法[J]. 计算机科学与探索, 2023, 17(6): 1343-1358. JIANG L Y, YANG J L. Detection optimized labeled multi-bernoulli algorithm for visual multi-target tracking[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(6): 1343-1358. (in Chinese)
[9] WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric[C]//Proceedings of the IEEE International Conference on Image Processing (ICIP). Beijing, China: IEEE Press, 2018: 3645-3649.
[10] BEWLEY A, GE Z Y, OTT L, et al. Simple online and realtime tracking[C]//Proceedings of the IEEE International Conference on Image Processing (ICIP). Phoenix, USA: IEEE Press, 2016: 3464-3468.
[11] CAO J K, PANG J M, WENG X S, et al. Observation-centric SORT: rethinking SORT for robust multi-object tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada: IEEE Press, 2023: 9686-9696.
[12] ZHANG Y F, WANG C Y, WANG X G, et al. FairMOT: on the fairness of detection and re-identification in multiple object tracking[J]. International Journal of Computer Vision, 2021, 129(11): 3069-3087.
[13] HAN K, WANG Y H, CHEN H T, et al. A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 87-110.
[14] SUN P Z, CAO J K, JIANG Y, et al. TransTrack: multiple object tracking with transformer[EB/OL]. [2024-12-01]. https://arxiv.org/abs/2012.15460.
[15] ZHANG Y F, SUN P Z, JIANG Y, et al. ByteTrack: multi-object tracking by associating every detection box[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2022: 1-21.
[16] AHARON N, ORFAIG R, BOBROVSKY B Z. BoT-SORT: robust associations multi-pedestrian tracking[EB/OL]. [2024-12-01]. https://arxiv.org/abs/2206.14651.
[17] WANG Y H, HSIEH J W, CHEN P Y, et al. SMILEtrack: SiMIlarity LEarning for occlusion-aware multiple object tracking[C]//Proceedings of the AAAI Conference on Artificial Intelligence. [S.l.]: AAAI Press, 2024: 5740-5748.
[18] YOU L X, CHEN Y J, XIAO C, et al. Multi-object vehicle detection and tracking algorithm based on improved YOLOv8 and ByteTrack[J]. Electronics, 2024, 13(15): 3033.
[19] TERVEN J, CÓRDOVA-ESPARZA D M, ROMERO-GONZÁLEZ J A. A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS[J]. Machine Learning and Knowledge Extraction, 2023, 5(4): 1680-1716.
[20] SUNKARA R, LUO T. No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects[C]//Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Germany: Springer, 2023: 443-459.
[21] YUN S, RO Y. SHViT: single-head vision transformer with memory efficient macro design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE Press, 2024: 5756-5767.
[22] YANG L X, ZHANG R Y, LI L D, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[C]//Proceedings of International Conference on Machine Learning. [S. l.]: PMLR, 2021: 11863-11874.
[23] LI J F, WEN Y, HE L H. SCConv: spatial and channel reconstruction convolution for feature redundancy[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada: IEEE Press, 2023: 6153-6162.
[24] LI C, ZHOU A J, YAO A B. Omni-dimensional dynamic convolution[EB/OL]. [2024-12-01]. https://arxiv.org/abs/2209.07947.
[25] CHEN J R, KAO S H, HE H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada: IEEE Press, 2023: 12021-12031.
[26] WANG C Y, YEH I H, MARK LIAO H Y. YOLOv9: learning what you want to learn using programmable gradient information[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2024: 1-21.
[27] WANG A, CHEN H, LIU L H, et al. YOLOv10: real-time end-to-end object detection[EB/OL]. [2024-12-01]. https://arxiv.org/abs/2405.14458.
[28] HUANG J W, WANG K B, HOU Y, et al. LW-YOLO11: a lightweight arbitrary-oriented ship detection method based on improved YOLO11[J]. Sensors, 2024, 25(1): 65.
[29] ZHANG Y K, XIE H S, JIA Y H, et al. AIPT: Adaptive information perception for online multi-object tracking[J]. Knowledge-Based Systems, 2024, 285: 111369.
[30] ZHANG Y A, WANG T C, ZHANG X Y. MOTRv2: bootstrapping end-to-end multi-object tracking by pretrained object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada: IEEE Press, 2023: 22056-22065.

选择文件类型/文献管理软件名称

选择包含的内容