| 28 | 0 | 565 |
| 下载次数 | 被引频次 | 阅读次数 |
随着深度学习在目标检测领域的发展，涌现出越来越多类型的高精度检测算法。然而，现有方法对动态目标的检测准确率较低。针对上述问题，提出一种高效的多尺度目标无锚框检测方法。该方法设计一种无锚检测器，不需定义显式的锚框。本文方法将不同尺度的特征进行融合，并在骨干网络之后添加了特征金字塔和可变形卷积，以准确检测不同尺寸的物体。仿真分析与实验结果表明，本文算法可以极大地提高动态目标检测的精度。
Abstract：With the development of deep learning in the field of object detection, an increasing number of highprecision detection algorithms of various types have emerged. However, existing methods exhibit relatively low detection accuracy for dynamic objects. To address this issue, an efficient multi-scale anchor-free object detection method was proposed, which does not require the explicit definition of anchor boxes. The proposed method integrates features at different scales and incorporates a feature pyramid and deformable convolution layers after the backbone network to accurately detect objects of various sizes. Simulation analysis and experimental results demonstrate that the proposed algorithm significantly improves the accuracy of dynamic object detection.
[1] REDMON J, FARHADI A. YOLO9000:better,faster, stronger[C]∥Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2017:6517-6525.
[2] NAGA JYOTHI D, HARISH REDDY G,PRASHANTH B, et al. Collaborative training of object detection and re-identification in multi-object tracking using YOLOv8[C]∥Proceedings of the 2024International Conference on Computing and Data Science. Piscataway:IEEE Press, 2024:1-6.
[3] MAI H N, HUANG L B, AN Z L, et al. OLN:improved object localization network for open-world object detection[C]∥Proceedings of the ICASSP2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway:IEEE Press, 2025:1-5.
[4] YANG Y, LIANG C B, HUANG S Y, et al. BOAformer:object detection network based on backgroundobject attention transformer[C]∥Proceedings of the2024 6th International Conference on Communications,Information System and Computer Engineering. Piscataway:IEEE Press, 2024:1133-1138.
[5] REN S Q, HE K M, GIRSHICK R, et al. Faster RCNN:towards real-time object detection with region proposal networks[C]∥Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence. Piscataway:IEEE Press, 2017:1137-1149.
[6] LAW H, DENG J. CornerNet:detecting objects as paired keypoints[C]∥Computer Vision-ECCV 2018.Cham:Springer International Publishing, 2018:765-781.
[7] DUAN K W, BAI S, XIE L X, et al. CenterNet:keypoint triplets for object detection[C]∥Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Long Beach, CA:IEEE Press, 2019:6568-6577.
[8] ZHOU X Y, ZHUO J C, KR?HENBüHL P. Bottom-up object detection by grouping extreme and center points[C]∥Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press, 2019:850-859.
[9] FANG S K, HONG Y, XU L, et al. Research on insulator defect detection based on synthetic fog and improved YOLOv5[C]∥Proceedings of the 202510th Asia Conference on Power and Electrical Engineering. Piscataway:IEEE Press, 2025:2056-2060.
[10] JEONG I, JEON J Y, KIM K, et al. Input-adaptive mixed-precision framework for efficient object detection[C]∥Proceedings of the 2025 IEEE International Symposium on Circuits and Systems. Piscataway:IEEE Press, 2025:1-5.
[11] ZHOU X G, WANG D Q, KRAHENBUHL P.Objects as points[EB/OL].[2019-04-16]. https：∥arxiv. org/abs/1904. 07850.
[12] TIAN Z, SHEN C H, CHEN H, et al. FCOS:fully convolutional one-stage object detection[C]∥Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Long Beach, CA:IEEE Press,2019:9626-9635.
[13] LIU Z L, ZHENG T, XU G D, et al. Training-timefriendly network for real-time object detection[C]∥Proceedings of the AAAI Conference on Artificial Intelligence. New York, NY:AAAI Press, 2020:11685-11692.
[14] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO:common objects in context[C]∥Computer Vision-ECCV 2014. Cham:Springer, 2014:740-755.
[15] CARION N, MASSA F, SYNNAEVE G, et al.End-to-end object detection with transformers[C]∥Computer Vision-ECCV 2020. Cham:Springer,2020:213-229.
[16] DUAN K W, XIE L X, QI H G, et al. Corner proposal network for anchor-free, two-stage object detection[C]∥Computer Vision–ECCV 2020. Cham:Springer, 2020:399-416.
基本信息:
中图分类号:TP391.41;TP18
引用信息:
[1]杨松祥,沈全成,贾爽,等.一种高效的多尺度目标无锚框检测方法[J].中国科技论文,2025,20(10):864-871.
基金信息:
上海市白玉兰人才计划浦江项目（23PJD042）