PanopticUAV: Panoptic Segmentation of UAV Images for Marine Environment Monitoring

被引:0
|
作者
Dou, Yuling [1 ]
Yao, Fengqin [1 ]
Wang, Xiandong [1 ]
Qu, Liang [2 ]
Chen, Long [3 ]
Xu, Zhiwei [4 ]
Ding, Laihui [4 ]
Bullock, Leon Bevan [1 ]
Zhong, Guoqiang [1 ]
Wang, Shengke [1 ]
机构
[1] Ocean Univ China, Sch Comp Sci & Technol, Qingdao 266100, Peoples R China
[2] State Ocean Adm, North China Sea Environm Monitoring Ctr, Qingdao 266000, Peoples R China
[3] Univ Leicester, Dept Informat, Leicester LE1 7RH, England
[4] Shandong Willand Intelligent Technol Co Ltd, Res & Dev Dept, Qingdao 266102, Peoples R China
来源
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES | 2024年 / 138卷 / 01期
关键词
Panoptic segmentation; UAV marine monitoring; attention mechanism; boundary mask enhancement; DATASET;
D O I
10.32604/cmes.2023.027764
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
UAV marine monitoring plays an essential role in marine environmental protection because of its flexibility and convenience, low cost and convenient maintenance. In marine environmental monitoring, the similarity between objects such as oil spill and sea surface, Spartina alterniflora and algae is high, and the effect of the general segmentation algorithm is poor, which brings new challenges to the segmentation of UAV marine images. Panoramic segmentation can do object detection and semantic segmentation at the same time, which can well solve the polymorphism problem of objects in UAV ocean images. Currently, there are few studies on UAV marine image recognition with panoptic segmentation. In addition, there are no publicly available panoptic segmentation datasets for UAV images. In this work, we collect and annotate UAV images to form a panoptic segmentation UAV dataset named UAV-OUC-SEG and propose a panoptic segmentation method named PanopticUAV. First, to deal with the large intraclass variability in scale, deformable convolution and CBAM attention mechanism are employed in the backbone to obtain more accurate features. Second, due to the complexity and diversity of marine images, boundary masks by the Laplacian operator equation from the ground truth are merged into feature maps to improve boundary segmentation precision. Experiments demonstrate the advantages of PanopticUAV beyond the most other advanced approaches on the UAV-OUC-SEG dataset.
引用
收藏
页码:1001 / 1014
页数:14
相关论文
共 50 条
  • [21] Monitoring of infrastructures in the marine environment
    Del Grosso, A
    STRUCTURAL CONTROL FOR CIVIL AND INFRASTRUCTURE ENGINEERING, 2001, : 107 - 117
  • [22] Article Citrus Tree Segmentation from UAV Images Based on Monocular Machine Vision in a Natural Orchard Environment
    Chen, Yayong
    Hou, Chaojun
    Tang, Yu
    Zhuang, Jiajun
    Lin, Jintian
    He, Yong
    Guo, Qiwei
    Zhong, Zhenyu
    Lei, Huan
    Luo, Shaoming
    SENSORS, 2019, 19 (24)
  • [23] Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images
    Gosala, Nikhil
    Valada, Abhinav
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02) : 1968 - 1975
  • [24] Transmission Tower Environment Monitoring Using UAV
    Redzuwan, Redia Mohd
    Din, Norashidah Md
    Baharuddin, Mohd Zafri
    Mustafa, Intan Shafinaz
    Omar, Rohayu Che'
    4TH INTERNATIONAL CONFERENCE ON ENERGY AND ENVIRONMENT 2013 (ICEE 2013), 2013, 16
  • [25] Unsupervised Bayesian learning for rice panicle segmentation with UAV images
    Hayat, Md Abul
    Wu, Jingxian
    Cao, Yingli
    PLANT METHODS, 2020, 16 (01)
  • [26] Segmentation Method of Concrete Small Cracks Based on UAV Images
    Pan Y.
    Zou W.
    Xv Q.
    Zhao Y.
    Liang Q.
    Zhao T.
    Recent Advances in Computer Science and Communications, 2024, 17 (05) : 71 - 81
  • [27] Unsupervised Semantic Segmentation of Aerial Images With Application to UAV Localization
    Jaimes, Brayan Rene Acevedo
    Ferreira, Joao Pedro Klock
    Castro, Cristiano Leite
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [28] Semantic segmentation and path planning for orchards based on UAV images
    Sun, Qilin
    Zhang, Ruirui
    Chen, Liping
    Zhang, Linhuan
    Zhang, Hongming
    Zhao, Chunjiang
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2022, 200
  • [29] Unsupervised Bayesian learning for rice panicle segmentation with UAV images
    Md Abul Hayat
    Jingxian Wu
    Yingli Cao
    Plant Methods, 16
  • [30] Fast Geocoding of UAV Images for Disaster Site Monitoring
    Nho, Hyunju
    Shin, Dong Yoon
    Sohn, Hong-Gyoo
    Kim, Seongsam
    KOREAN JOURNAL OF REMOTE SENSING, 2020, 36 (05) : 1221 - 1229