RepViTS-YOLOX：水下模糊及遮挡目标检测方法

doi:10.3778/j.issn.1002-8331.2312-0153

摘要/Abstract

摘要： 针对水下目标检测中的目标模糊和遮挡问题，提出基于YOLOX改进的RepViTS-YOLOX水下目标检测方法。该方法采用RepViTS作为特征提取网络并通过结构重参数化，有效提升了对水下目标的特征提取能力和模型推理速度。引入空间和通道重构（spatial and channel reconstruction convolution，SCConv）模块，增强网络对模糊目标的关注。改进特征融合网络，通过跨尺度连接和多尺度融合，加强不同层次特征间的信息交流，使模型更好理解遮挡目标特征。针对定位和分类任务对特征的不同需求，引入上下文解耦头（task-specific context decoupling head，TSCODE），对遮挡目标更精准地定位和分类。实验结果证明，RepViTS-YOLOX方法在RUOD数据集上取得了85.7%的检测效果，较YOLOX提高了3.8个百分点。检测结果显示，该方法可以有效改善水下模糊和遮挡目标的检测情况，提高水下目标检测精度。

关键词: YOLOX, 目标检测, 结构重参数化, 解耦检测头, 注意力机制

Abstract: The RepViTS-YOLOX method is proposed to address target blurring and occlusion in underwater target detection, improving upon the YOLOX framework. This approach employs RepViTS for feature extraction and incorporates structural reparameterization to enhance underwater target feature extraction and model inference speed. It features a spatial and channel reconstruction convolution (SCConv) module to better focus on blurred targets. The feature fusion network uses cross-scale and multi-scale fusion to better interpret occluded target characteristics. Additionally, a task-specific context decoupling head (TSCODE) is introduced for more accurate localization and classification of occluded targets. Experiments on the RUOD dataset show that RepViTS-YOLOX achieves 85.7% detection accuracy, surpassing YOLOX by 3.8 percentage points. These findings indicate that the method effectively improves the detection of blurred and occluded underwater targets, thus enhancing the precision of underwater target detection.

Key words: YOLOX, target detection, structural re-parameterization, decouple detection head, attention mechanism

陶洋, 朱腾, 钟邦乾, 周昆, 周立群. RepViTS-YOLOX：水下模糊及遮挡目标检测方法[J]. 计算机工程与应用, 2024, 60(13): 200-208.

TAO Yang, ZHU Teng, ZHONG Bangqian, ZHOU Kun, ZHOU Liqun. RepViTS-YOLOX：Underwater Blurred and Occluded Target Detection Method[J]. Computer Engineering and Applications, 2024, 60(13): 200-208.

参考文献

[1] XU S, ZHANG M, SONG W, et al. A systematic review and analysis of deep learning-based underwater object detection[J]. Neurocomputing, 2023, 527: 204-232.
[2] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.
[3] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[4] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015, 28.
[5] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2961-2969.
[6] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, Oct 11-14, 2016. Cham: Springer International Publishing, 2016: 21-37.
[7] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[8] 叶赵兵, 段先华, 赵楚. 改进YOLOv3-SPP水下目标检测研究[J]. 计算机工程与应用, 2023, 59(6): 231-240.
YE Z B, DUAN X H, ZHAO C. Research on underwater target detection by Improved YOLOv3-SPP[J]. Computer Engineering and Applications, 2023, 59(6): 231-240.
[9] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[10] LEI F, TANG F, LI S. Underwater target detection algorithm based on improved YOLOv5[J]. Journal of Marine Science and Engineering, 2022, 10(3): 310.
[11] YAN J, ZHOU Z, ZHOU D, et al. Underwater object detection algorithm based on attention mechanism and cross-stage partial fast spatial pyramidal pooling[J]. Frontiers in Marine Science, 2022, 9: 1056300.
[12] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 7464-7475.
[13] SUN Y, ZHENG W, DU X, et al. Underwater small target detection based on YOLOX combined with MobileViT and double coordinate attention[J]. Journal of Marine Science and Engineering, 2023, 11(6): 1178.
[14] GE Z, LIU S, WANG F, et al. YOLOX: exceeding YOLO series in 2021[J]. arXiv:2107.08430, 2021.
[15] WANG J, QI S, WANG C, et al. B-YOLOX-S: a lightweight method for underwater object detection based on data augmentation and multiscale feature fusion[J]. Journal of Marine Science and Engineering, 2022, 10(11): 1764.
[16] WANG A, CHEN H, LIN Z, et al. RepViT: revisiting mobile CNN from ViT perspective[J]. arXiv:2307.09283, 2023.
[17] LI J, WEN Y, HE L. SCConv: spatial and channel reconstruction convolution for feature redundancy[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 6153-6162.
[18] ZHUANG J, QIN Z, YU H, et al. Task-specific context decoupling for object detection[J]. arXiv:2303.01047, 2023.
[19] LIU Z, LIN Y, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 10012-10022.
[20] PAN J, BULAT A, TAN F, et al. Edgevits: competing light-weight CNNs on mobile devices with vision transformers[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 294-311.
[21] GUO M H, XU T X, LIU J J, et al. Attention mechanisms in computer vision: a survey[J]. Computational Visual Media, 2022, 8(3): 331-368.
[22] 赵珊, 郑爱玲, 刘子路, 等. 通道分离双注意力机制的目标检测算法[J]. 计算机科学与探索, 2023, 17(5): 1112-1125.
ZHAO S, ZHENG A L, LIU Z L, et al. Object detection algorithm based on channel separation dual attention mechanism[J]. Journal of Frontiers of Computer Science & Technology, 2022, 8(3): 331-368.
[23] CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1251-1258.
[24] ZHU X, LYU S, WANG X, et al. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 2778-2788.
[25] GHIASI G, LIN T Y, LE Q V. NAS-FPN: learning scalable feature pyramid architecture for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 7036-7045.
[26] 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, 2017: 2117-2125.
[27] 赵睿, 刘辉, 刘沛霖, 等. 基于改进YOLOv5s的安全帽检测算法[J]. 北京航空航天大学学报, 2023, 49(8): 2050-2061.
ZHAO R, LIU H, LIU P L, et al. Safety helmet detection algorithm based on improved YOLOv5s[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(8): 2050-2061.
[28] ZHAO Z, HE C, ZHAO G, et al. RA-YOLOX: re-parameterization align decoupled head and novel label assignment scheme based on YOLOX[J]. Pattern Recognition, 2023, 140: 109579.
[29] TIAN Z, SHEN C, CHEN H, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 9627-9636.