Improved Detector Based on Yolov5 for Typical Targets on the Sea Surfaces
-
Published:2023-06-29
Issue:13
Volume:13
Page:7695
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Sun Anzhu1, Ding Jun1, Liu Jiarui1, Zhou Heng1, Zhang Jiale1, Zhang Peng1, Dong Junwei1, Sun Ze1
Affiliation:
1. China Ship Scientific Research Center, No. 222 East Shanshui Road, Binhu District, Wuxi 214082, China
Abstract
Detection of targets on sea surfaces is an important area of application that can bring great benefits to the management and control systems in marine environments. However, there are few open-source datasets accessible for the purpose of object detection on seas and rivers. In this paper, a study is conducted on the improved detection algorithms based on the YOLOv5 model. The dataset for the tests contains ten categories of typical objects that are commonly seen in the contexts of seas, including ships, devices, and structures. Multiple augmentation methods are employed in the pre-processing of the input data, which are verified to be effective in enhancing the generalization ability of the algorithm. Moreover, a new form of the loss function is proposed that highlights the effects of the high-quality boxes during training. The results demonstrate that the adapted loss function contributes to a boost in the model performance. According to the ablation studies, the synthesized methods raise the inference accuracy by making up for several shortcomings of the baseline model for the detection tasks of single or multiple targets from varying backgrounds.
Funder
Ministry of Science and Technology National Key Research and Development Program of China Ministry of Industry and Information Technology
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference28 articles.
1. Ship detection with deep learning: A survey;Er;Artif. Intell. Rev.,2023 2. He, Y., Zhu, C., Wang, J., Savvides, M., and Zhang, X. (2018, January 18–23). Bounding Box Regression With Uncertainty for Accurate Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA. 3. Benjumea, A., Teeti, I., Cuzzolin, F., and Bradley, A. (2021). YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles. arXiv. 4. Zhang, H., Chang, H., Ma, B., Wang, N., and Chen, X. (2020). Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training. arXiv. 5. Girshick, R.B., Donahue, J., Darrell, T., and Malik, J. (2013, January 23–28). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.
|
|