基于注意力机制及Ghost-YOLOv5的水下垃圾目标检测

袁红春; 臧天祺

doi:10.13205/j.hjgc.202307029

基于注意力机制及Ghost-YOLOv5的水下垃圾目标检测

doi: 10.13205/j.hjgc.202307029

袁红春,
臧天祺^,

上海海洋大学信息学院, 上海 201306

基金项目:

国家自然科学基金项目（41776142）

详细信息

作者简介:
袁红春(1971-),男,教授,主要研究方向为人工智能应用。hcyuan@shou.edu.cn

通讯作者:
臧天祺(1997-),男,硕士研究生,主要研究方向为计算机视觉。m200711494@st.shou.edu.cn

计量
- 文章访问数: 177
- HTML全文浏览量: 28
- PDF下载量: 5
- 被引次数: 0
出版历程
- 收稿日期: 2022-05-15

DETECTION OF UNDERWATER TRASH BASED ON Ghost-YOLOv5 AND ATTENTION MECHANISM

YUAN Hongchun,
ZANG Tianqi^,

College of Information Technology, Shanghai Ocean University, Shanghai 201306, China

摘要

摘要: 水下垃圾的目标检测技术对水下机器人实现垃圾自动清除有着重要意义。然而，复杂的水下环境和水底光线不足，易导致检测精度受限、计算量大等问题。针对这些问题，提出了一种基于YOLOv5的水下垃圾目标检测的改进算法。在该方法中，在预处理部分引入Gamma变换提高水下图像的灰度和对比度，便于模型检测。同时，在YOLOv5检测部分嵌入CBAM注意力机制，以突出目标特征并抑制次要信息，从而提高算法精度。此外，将颈部层中的普通卷积模块替换为Ghost卷积模块，减少计算量，加快检测速度。采用真实环境下的水下垃圾数据集进行模型验证，与当前热门的目标检测算法进行对比，该方法在分辨率为640×640的图像上的最高检测精度为93.7%，且计算时间仅为6.7 ms，满足实时性的要求。该研究成果对水下垃圾的目标检测具有良好的借鉴意义。
- 深度学习 /
- 水下垃圾检测 /
- 注意力机制 /
- Gamma转换 /
- Ghost卷积
Abstract: Underwater trash detection technology is of great significance for automatic trash removal tasks by underwater robots. However, it faces some challenges, such as an unsatisfactory detection rate due to poor underwater light conditions and high computation load. To solve these problems, this paper proposed an improved YOLOv5 model for underwater trash detection. First, in the preprocessing stage, Gamma transform was introduced to improve the grey level and contrast of underwater images for model detection. Meanwhile, the CBAM attention mechanism was embedded in the detection part of the YOLOv5 model to select the information important to underwater trash detection tasks and suppress uncritical information, thus improving the accuracy of the algorithm. Besides, in the neck layer, the traditional convolution module was replaced by the Ghost convolution module to reduce the calculation amount and improve the detection speed. The proposed model was evaluated on an underwater trash dataset in the real environment. Compared with mainstream object detection algorithms, the proposed model achieved the highest detection accuracy of 93.7% in images with a resolution of 640×640, and the calculation time was only 6.7 ms, meeting the requirements of real-time performance. The study results provide a good reference for underwater trash detection.
- deep learning /
- underwater trash detection /
- attention mechanism /
- Gamma transformation /
- ghost convolution

HTML全文

参考文献(27)

[1]	DERRAIK J G B.The pollution of the marine environment by plastic debris:a review[J].Marine pollution bulletin, 2002, 44(9):842-852.
[2]	National oceanic and atmospheric administration.What is marine debris?[EB/OL].[2018-10-02].https://oceanservice.noaa.gov/facts/marinedebris.html.
[3]	VALAVANIDIS A, VLACHOGIANNI T.Marine litter:man-made solid waste pollution in the Mediterranean Sea and coastline.Abundance, composition and sources identification[J].Science Advances on Environmental Chemistry, Toxicology and Ecotoxicology, 2012, 1:1-18.
[4]	LANDRIGAN P J, STEGEMAN J J, FLEMING L E, et al.Human health and ocean pollution[J].Annals of global health, 2020, 86(1):1-64.
[5]	RODINELIUSSEN R.Caring for water:underwater waste, trash diving, and publicity in stockholm[J].kritisk etnografi:Swedish Journal of Anthropology, 2021, 4(2):73-92.
[6]	WU Y C, SHIH P Y, CHEN L P, et al.Towards underwater sustainability using ROV equipped with deep learning system[C]//2020 International Automatic Control Conference (CACS), IEEE, 2020:1-5.
[7]	FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al.Object detection with discriminatively trained part-based models[J].IEEE transactions on Pattern Analysis and Machine Intelligence, 2009, 32(9):1627-1645.
[8]	LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004, 60(2):91-110.
[9]	DALAL N, TRIGGS B.Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), Ieee, 2005, 1:886-893.
[10]	PLATT J C.Sequential minimal optimization:a fast algorithm for training support vector machines[J].Microsoft Research, 1998,98(14):208.
[11]	HIPOLITO J C, ALON A S, AMORADO R V, et al.Detection of underwater marine plastic debris using an augmented low sample size dataset for machine vision system:a deep transfer learning approach[C]//2021 IEEE 19th Student Conference on Research and Development (SCOReD), IEEE, 2021:82-86.
[12]	GIRSHICK R, Donahue J, Darrell T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Beijing,China,IEEE,2014:580-587.
[13]	GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, Chongqing,China,IEEE,2015:1440-1448.
[14]	LIU W, ANGUELOV D, ERHAN D, et al.Ssd:Single shot multibox detector[C]//European Conference on Computer Vision, Springer, Cham, 2016:21-37.
[15]	REN S Q, HE K M, GIRSHICK R, et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].Advances in Neural Information Processing Systems, 2017, 36(9):1137-1149.
[16]	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.
[17]	MACE T H.At-sea detection of marine debris:overview of technologies, processes, issues, and options[J].Marine Pollution Bulletin, 2012, 65(1/2/3):23-27.
[18]	MATIAS V.Submerged marine debris detection with autonomous underwater vehicles[C]//2016 International Conference on Robotics and Automation for Humanitarian Applications (RAHA), IEEE, 2016:1-7.
[19]	FULTON M, HONG J, Islam M J, et al.Robotic detection of marine litter using deep visual detection models[C]//2019 International Conference on Robotics and Automation (ICRA), IEEE, 2019:5752-5758.
[20]	FULTON M, HONG J, SATTAR J.Trash-icra19:a bounding box labeled dat aset of unde rwa ter trash[J].Data Repository for the University of Minnesota, 2020,10:132.
[21]	ARKIN E, YADIKAR N, MUHTAR Y, et al.A survey of object detection based on CNN and transformer[C]//2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML), IEEE, 2021:99-108.
[22]	HU K, WENG C H, ZHANG Y W, et al.An overview of underwater vision enhancement:from traditional methods to recent deep learning[J].Journal of Marine Science and Engineering, 2022, 10(2):241.
[23]	HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattem Recogrition, New York:IEEE Press,2018:7132-7141.
[24]	WOO S, PARK J, LEE J Y, et al.Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision,Munich, Germany,ECCV,2018:3-19.
[25]	HAN K, WANG Y, TIAN Q, et al.Ghostnet:More features from cheap operations[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Guangxi, China,IEEE,2020:1580-1589.
[26]	HONG J, FULTON M, SATTAR J.TrashCan:A semantically-segmented dataset towards visual detection of marine Debris[J].2020.DOI: 1048550/arXiv.2007.08097.
[27]	GE Z, LIU S, WANG F, et al.YOLOX:Exceeding YOLO Series in 2021[J].2021.DOI: 10.48550/arXiv:2107.08430.