面向小目标检测的像素重排与特征重排算法

doi:10.3778/j.issn.1002-8331.2405-0460

摘要/Abstract

摘要： 针对小目标检测任务中常见的目标漏检和误检问题，提出一种面向小目标检测的像素重排与特征重排算法PFR-YOLOv8s。为了提升模型的特征提取能力，构建一种结合注意力机制的像素重排特征提取模块（pixel rearrangement feature extraction，PRFE），能有效保留细粒度信息，捕捉复杂背景下小目标的重要特征。设计了一种多重特征融合机制（multi-feature fusion，MFF），能充分利用小目标的上下文信息及多尺度信息；基于MFF构建一种特征重排网络框架（feature rearrangement neck，FR-Neck），通过特征重排丰富目标特征，提升模型对小目标的感知能力。引入Inner-GIoU损失函数，提升对密集场景下小目标样本的学习能力。实验结果表明，该算法在VisDrone2019数据集上的平均检测精度较YOLOv8s原模型提高5.8个百分点，有效提升了对小目标的检测能力。在铁路工人安全施工小目标数据集上平均精度提升2.1个百分点，验证了该算法的泛化性。

关键词: 小目标检测, YOLOv8s, 像素重排, 特征重排, 多重特征融合

Abstract: 1.College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou 350000, China
2.Quanzhou Institute of Equipment Manufacturing, Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Quanzhou, Fujian 362000, China
3.Fujian College, University of Chinese Academy of Sciences, Fuzhou 350000, China
4.College of Advanced Manufacturing, Fuzhou University, Quanzhou, Fujian 362000, China
5.Fujian Fuyao Automotive Trim System Co., Ltd., Fuqing, Fujian 350300, China

Key words: small object detection, YOLOv8s, pixel rearrangement, feature rearrangement, multi-feature fusion

赵庆辉, 赖耀平, 官敬超, 曾燕芬, 巢建树. 面向小目标检测的像素重排与特征重排算法[J]. 计算机工程与应用, 2025, 61(17): 317-328.

ZHAO Qinghui, LAI Yaoping, GUAN Jingchao, ZENG Yanfen, CHAO Jianshu. Pixel Rearrangement and Feature Rearrangement Algorithms for Small Object Detection[J]. Computer Engineering and Applications, 2025, 61(17): 317-328.

参考文献

[1] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 936-944.
[2] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 8759-8768.
[3] 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 (Basel), 2023, 23(16): 7190.
[4] 苏佳, 秦一畅, 贾泽, 等. 基于ATO-YOLO的小目标检测算法[J]. 计算机工程与应用, 2024, 60(6): 68-77.
SU J, QIN Y C, JIA Z, et al. Small object detection algorithm based on ATO-YOLO[J]. Computer Engineering and Applications, 2024, 60(6): 68-77.
[5] CAI Z W, FAN Q F, FERIS R S, et al. A unified multi-scale deep convolutional neural network for fast object detection[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2016: 354-370.
[6] ZHU Y S, ZHAO C Y, WANG J Q, et al. CoupleNet: coupling global structure with local parts for object detection[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 4146-4154.
[7] LI Y J, LI S S, DU H H, et al. YOLO-ACN: focusing on small target and occluded object detection[J]. IEEE Access, 2020, 8: 227288-227303.
[8] LIM J S, ASTRID M, YOON H J, et al. Small object detection using context and attention[C]//Proceedings of the International Conference on Artificial Intelligence in Information and Communication. Piscataway: IEEE, 2021: 181-186.
[9] KIM M, JEONG J, KIM S. ECAP-YOLO: efficient channel attention pyramid YOLO for small object detection in aerial image[J]. Remote Sensing, 2021, 13(23): 4851.
[10] ZHU X K, LYU S C, WANG X, et al. TPH-YOLOv5: impr-oved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Piscataway: IEEE, 2021: 2778-2788.
[11] 齐向明, 柴蕊, 高一萌. 重构SPPCSPC与优化下采样的小目标检测算法[J]. 计算机工程与应用, 2023, 59(20): 158-166.
QI X M, CHAI R, GAO Y M. Algorithm of reconstructed SPPCSPC and optimized downsampling for small object detection[J]. Computer Engineering and Applications, 2023, 59(20): 158-166.
[12] 董刚, 谢维成, 黄小龙, 等. 深度学习小目标检测算法综述[J]. 计算机工程与应用, 2023, 59(11): 16-27.
DONG G, XIE W C, HUANG X L, et al. Review of small object detection algorithms based on deep learning[J]. Computer Engineering and Applications, 2023, 59(11): 16-27.
[13] ZHANG S F, CHI C, YAO Y Q, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogn-ition. Piscataway: IEEE, 2020: 9756-9765.
[14] SUNKARA R, LUO T. No more strided convolutions or poo-ling: a new CNN building block forLow-resolution images andSmall objects[C]//Proceedings of the Machine Learning and Knowledge Discovery in Databases. Cham: Springer Nature Switzerland, 2023: 443-459.
[15] LEE Y, PARK J. CenterMask: real-time anchor-free instance segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 13903-13912.
[16] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141.
[17] WU T, TANG S, ZHANG R, et al. CGNet: a light-weight context guided network for semantic segmentation[J]. IEEE Transactions on Image Processing, 2021, 30: 1169-1179.
[18] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision, 2018: 3-19.
[19] HUANG H, CHEN Z, ZOU Y, et al. Channel prior convolutional attention for medical image segmentation[J]. arXiv: 2306.05196, 2023.
[20] ZHANG H, XU C, ZHANG S. Inner-IoU: more effective intersection over union loss with auxiliary bounding box[J]. arXiv:2311.02877, 2023.
[21] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 658-666.
[22] CAO Y R, HE Z J, WANG L J, et al. VisDrone-DET2021: the vision meets drone object detection challenge results[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Piscataway: IEEE, 2021: 2847-2854.
[23] YU W P, YANG T, CHEN C. Towards resolving the challenge of long-tail distribution in UAV images for object detection[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2021: 3257-3266.
[24] ZHOU X, WANG D, KRAHENBUHL P. Objects as points[J]. arXiv:1904.07850, 2019.
[25] WANG L, SHI Y, MAO G J, et al. Consumer-centric insights into resilient small object detection: SCIoU loss and recursive transformer network[J]. IEEE Transactions on Consumer Electronics, 2024, 70(1): 2178-2187.
[26] WU M J, YUN L J, WANG Y B, et al. Detection algorithm for dense small objects in high altitude image[J]. Digital Signal Processing, 2024, 146: 104390.
[27] SUI J C, CHEN D K, ZHENG X, et al. A new algorithm for small target detection from the perspective of unmanned aerial vehicles[J]. IEEE Access, 2024, 12: 29690-29697.
[28] TAHIR N U A, LONG Z, ZHANG Z P, et al. PVswin-YOLOv8s: UAV-based pedestrian and vehicle detection for traffic management in smart cities using improved YOLOv8[J]. Drones, 2024, 8(3): 84.