To improve the anti-ship missiles' ability for accurate and efficient detection of maritime targets, YOLOv4 detection network is used in this paper. By using YOLOv4 network to detect the self-built marine ship targets' data set, to verify the accuracy and speed of the ship's recognition of the network. Empirical results show that YOLOv4 network can achieve better detection results for single or multiple targets in the pictures, and had superior performance in detecting small and obscure targets. In the real-time detection link, it can quickly and accurately detect the ship target in the transformed scene. Compared with traditional marine ship targets detection methods, YOLOv4 can better avoid the influence of background, lighting, occlusion, etc. It provides the oretical and technical support for the fine selection of targets for anti-ship missiles.
Detection of Self-Build Data Set Based on YOLOv4 Network
27.09.2020
1262860 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Improved YOLOv4-tiny network for pedestrian detection
IEEE | 2022
|Real-Time Vehicle Detection Based on YOLOv4 Neutral Network
Springer Verlag | 2022
|Pedestrian Detection Algorithm Based on Improved YOLOv4
IEEE | 2023
|Vehicle Detection System using YOLOv4
IEEE | 2022
|