Abstract
Countries around the world have paid increasing attention to the issue of marine security, and sea target detection is a key task to ensure marine safety. Therefore, it is of great significance to propose an efficient and accurate sea-surface target detection algorithm. The anchor-setting method of the traditional YOLO v3 only uses the degree of overlap between the anchor and the ground-truth box as the standard. As a result, the information of some feature maps cannot be used, and the required accuracy of target detection is hard to achieve in a complex sea environment. Therefore, two new anchor-setting methods for the visual detection of sea targets were proposed in this paper: the average method and the select-all method. In addition, cross PANet, a feature fusion structure for cross-feature maps was developed and was used to obtain a better baseline cross YOLO v3, where different anchor-setting methods were combined with a focal loss for experimental comparison in the datasets of sea buoys and existing sea ships, SeaBuoys and SeaShips, respectively. The results showed that the method proposed in this paper could significantly improve the accuracy of YOLO v3 in detecting sea-surface targets, and the highest value of mAP in the two datasets is 98.37% and 90.58%, respectively.
Highlights
As human maritime activities have gradually expanded with the rapidly growing marine economy, countries have paid increasing attention to the protection of coastlines
Cross path aggregation network (PANet), Generalized Intersection over Union (GIOU) loss and threshold method were employed in this study to infer a better baseline cross YOLO v3, where the threshold method, averaged method, select-all method and focal loss can be combined in different ways and tested in different datasets of sea-surface targets
Cross YOLO v3 with the average method and focal loss achieved the best performance on true positive (TP) and false positive (FP) indicators
Summary
As human maritime activities have gradually expanded with the rapidly growing marine economy, countries have paid increasing attention to the protection of coastlines. In addition to selecting a good backbone network, multiscale feature map fusion is a key component of modern target detection algorithms He et al proposed a feature pyramid structure to conduct top-down feature fusion [9]. The more complex feature fusion structure will improve accuracy, but it will reduce detection speed and increase network complexity [27,28]. In order to solve the sea-surface target detection problem, the pursuit of higher accuracy often brings additional calculations, such as larger backbone networks and feature fusion structures, and additional components such as attention mechanisms. The anchor-setting method proposed in this paper can improve the accuracy of target detection without reducing the detection speed, which meets the needs of sea target detection tasks. The final experimental results demonstrated that these improvements enhanced the ability of YOLO v3 to detect sea-surface targets
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
