UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection

被引:6
|
作者
Pan, Haixia [1 ]
Lan, Jiahua [1 ]
Wang, Hongqiang [1 ]
Li, Yanan [1 ]
Zhang, Meng [1 ]
Ma, Mojie [1 ]
Zhang, Dongdong [1 ]
Zhao, Xiaoran [1 ]
机构
[1] Beihang Univ, Sch Software, Beijing 100191, Peoples R China
关键词
underwater video; object detection; coordinate attention; loss function; frame-level optimization;
D O I
10.3390/s23104859
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Underwater video object detection is a challenging task due to the poor quality of underwater videos, including blurriness and low contrast. In recent years, Yolo series models have been widely applied to underwater video object detection. However, these models perform poorly for blurry and low-contrast underwater videos. Additionally, they fail to account for the contextual relationships between the frame-level results. To address these challenges, we propose a video object detection model named UWV-Yolox. First, the Contrast Limited Adaptive Histogram Equalization method is used to augment the underwater videos. Then, a new CSP_CA module is proposed by adding Coordinate Attention to the backbone of the model to augment the representations of objects of interest. Next, a new loss function is proposed, including regression and jitter loss. Finally, a frame-level optimization module is proposed to optimize the detection results by utilizing the relationship between neighboring frames in videos, improving the video detection performance. To evaluate the performance of our model, We construct experiments on the UVODD dataset built in the paper, and select mAP@0.5 as the evaluation metric. The mAP@0.5 of the UWV-Yolox model reaches 89.0%, which is 3.2% better than the original Yolox model. Furthermore, compared with other object detection models, the UWV-Yolox model has more stable predictions for objects, and our improvements can be flexibly applied to other models.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] A systematic review and analysis of deep learning-based underwater object detection
    Xu, Shubo
    Zhang, Minghua
    Song, Wei
    Mei, Haibin
    He, Qi
    Liotta, Antonio
    NEUROCOMPUTING, 2023, 527 : 204 - 232
  • [22] Hovering control of UUV through underwater object detection based on deep learning
    Jin, Han-Sol
    Cho, Hyunjoon
    Jiafeng, Huang
    Lee, Ji-Hyeong
    Kim, Myung-Jun
    Jeong, Sang-Ki
    Ji, Dae-Hyeong
    Joo, Kibum
    Jung, Dongwook
    Choi, Hyeung-Sik
    OCEAN ENGINEERING, 2022, 253
  • [23] Realistic Sonar Image Simulation Using Deep Learning for Underwater Object Detection
    Minsung Sung
    Jason Kim
    Meungsuk Lee
    Byeongjin Kim
    Taesik Kim
    Juhwan Kim
    Son-Cheol Yu
    International Journal of Control, Automation and Systems, 2020, 18 : 523 - 534
  • [24] Vision-based Deep Learning algorithm for Underwater Object Detection and Tracking
    Alla, Durga Nooka Venkatesh
    Jyothi, V. Bala Naga
    Venkataraman, H.
    Ramadass, G. A.
    OCEANS 2022, 2022,
  • [25] Realistic Sonar Image Simulation Using Deep Learning for Underwater Object Detection
    Sung, Minsung
    Kim, Jason
    Lee, Meungsuk
    Kim, Byeongjin
    Kim, Taesik
    Kim, Juhwan
    Yu, Son-Cheol
    INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, 2020, 18 (03) : 523 - 534
  • [26] A Camouflaged Object Detection Model Based on Deep Learning
    Wang, Yong
    Li, Ling
    Yang, Xin
    Wang, Xinxin
    Liu, Hui
    PROCEEDINGS OF 2020 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INFORMATION SYSTEMS (ICAIIS), 2020, : 150 - 153
  • [27] Real-time underwater object detection technology for complex underwater environments based on deep learning
    Zhou, Hui
    Kong, Meiwei
    Yuan, Hexiang
    Pan, Yanyan
    Wang, Xinru
    Chen, Rong
    Lu, Weiheng
    Wang, Ruizhi
    Yang, Qunhui
    ECOLOGICAL INFORMATICS, 2024, 82
  • [28] Hybridization of Deep Convolutional Neural Network for Underwater Object Detection and Tracking Model
    Krishnan, Vijiyakumar
    Vaiyapuri, Govindasamy
    Govindasamy, Akila
    MICROPROCESSORS AND MICROSYSTEMS, 2022, 94
  • [29] Lightweight Deep Neural Network for Joint Learning of Underwater Object Detection and Color Conversion
    Yeh, Chia-Hung
    Lin, Chu-Han
    Kang, Li-Wei
    Huang, Chih-Hsiang
    Lin, Min-Hui
    Chang, Chuan-Yu
    Wang, Chua-Chin
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (11) : 6129 - 6143
  • [30] Underwater object detection using Invert Multi-Class Adaboost with deep learning
    Chen, Long
    Liu, Zhihua
    Tong, Lei
    Jiang, Zheheng
    Wang, Shengke
    Dong, Junyu
    Zhou, Huiyu
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,