Deep Learning Methods for Ship Classification: From Visible to Infrared Images

• Published in: 2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) pp. 1116 - 1120
• Main Authors: Liu, Tianci, Qin, Hengjia, Zhan, Zhuo, Liu, Yunpeng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2023
• Subjects: Convolutional neural networks; Deep learning; Image recognition; infrared images; Marine vehicles; neural network; Ship recognition; Target recognition; Visualization
• DOI: 10.1109/RICAI60863.2023.10489039

Deep learning methods have achieved excellent performances on visual tasks of target recognition and classification. The rapid development of autonomous seafaring vessels comes up with the requirement to recognize other maritime ships day and night. However, the recognition of ships based on the deep neural networks may not always access the results as expectation when the ships are under the nighttime environment. To this issue, we consider the ship recognition task under the deep learning framework with paired visible images and infrared images. In this article, we propose an end-to-end convolutional network based on visible images and infrared images of the autonomous seafaring vessels. To demonstrate the effectiveness of our model, we choose the V AIS dataset to test the performance of classifying the maritime ships. Experimental results show that the proposed network outperforms the state-of-the-art methods based on the V AIS database.