CNN-based object detection and segmentation for maritime domain awareness

Deep learning algorithms have been proven to be a powerful tool in image and video processing for security and surveillance operations. In a maritime environment, the fusion of electro-optical sensor data with human intelligence plays an important role to counter the security issues. For instance, the situational awareness can be enhanced through an automated system that generates reports on ship identity and signature together with detecting the changes on naval vessels activity. To date, various studies have been set out to explore the performance of deep neural networks using a ship signature database. In the current study, we investigate the Mask R-CNN method to address not only the naval vessel detection using bounding boxes, but also obtaining their segmentation masks. We train and validate the model on data captured by an on-board camera covering the visible spectral band under various weather and light conditions. The experimental results show that Mask RCNN provides high confidence scores on challenging scenarios with a mean average precision of 86.4%. However, the precision of the segmentation mask is slightly deteriorated when the ships are adjacent to the border of the captured scene. Moreover, the network tested on thermal images indicates a decrease in detection and segmentation performance since the training data distribution is not representative enough.