Abstract
With the rapid development of the marine industry, intelligent ship detection plays a very important role in the marine traffic safety and the port management. Current detection methods mainly focus on synthetic aperture radar (SAR) images, which is of great significance to the field of ship detection. However, these methods sometimes cannot meet the real-time requirement. To solve the problems, a novel ship detection network based on SSD (Single Shot Detector), named NSD-SSD, is proposed in this paper. Nowadays, the surveillance system is widely used in the indoor and outdoor environment, and its combination with deep learning greatly promotes the development of intelligent object detection and recognition. The NSD-SSD uses visual images captured by surveillance cameras to achieve real-time detection and further improves detection performance. First, dilated convolution and multiscale feature fusion are combined to improve the small objects' performance and detection accuracy. Second, an improved prediction module is introduced to enhance deeper feature extraction ability of the model, and the mean Average Precision (mAP) and recall are significant improved. Finally, the prior boxes are reconstructed by using the K-means clustering algorithm, the Intersection-over-Union (IoU) is higher, and the visual effect is better. The experimental results based on ship images show that the mAP and recall can reach 89.3% and 93.6%, respectively, which outperforms the representative model (Faster R-CNN, SSD, and YOLOv3). Moreover, our model's FPS is 45, which can meet real-time detection acquirement well. Hence, the proposed method has the better overall performance and achieves higher detection efficiency and better robustness.
Highlights
With the rapid development of the shipping industry, there are more frequent human activities on the ocean in recent years. erefore, robust ship detection is strongly needed to meet the demand
To test the detection performance of Novel Ship Detection SSD (NSD-SSD), the comparative experiments are implemented using several popular baseline methods: Faster R-Convolutional Neural Networks (CNN), SSD series, and YOLO series. e backbone networks of these models are pretrained on ImageNet
We record the accuracy of the four models based on the evaluation indicators, as shown in Table 5. e detection performance of Faster R-CNN is significantly better than YOLO series and SSD series
Summary
With the rapid development of the shipping industry, there are more frequent human activities on the ocean in recent years. erefore, robust ship detection is strongly needed to meet the demand. Modern radar target tracking equipment and ship automatic identification systems are mainly based on positioning, and ship detection needs substantial improvements. In response to these problems, many researchers have used traditional machine learning methods to explore this field in search of better results. They used features of ships combined with classifiers [1, 2] These methods achieve good results, they require manual extraction of features and a classifier with good performance, which needs further validation in terms of efficiency and accuracy. The performance of CNNs has been improved with the appearance of deeper and more complex CNNs such as AlexNet [5], VGGNet [6], GoogLeNet [7], Computational Intelligence and Neuroscience
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.
