Abstract
Submarines are considered extremely strategic for any naval army due to their stealth capability. Periscopes are crucial sensors for these vessels, and emerging to the surface or periscope depth is required to identify visual contacts through this device. This maneuver has many procedures and usually has to be fast and agile to avoid exposure. This paper presents and implements a novel architecture for real submarine periscopes developed for future Brazilian naval fleet operations. Our system consists of a probe that is connected to the craft and carries a 360 camera. We project and take the images inside the vessel using traditional VR/XR devices. We also propose and implement an efficient computer vision-based MR technique to estimate and display detected vessels effectively and precisely. The vessel detection model is trained using synthetic images. So, we built and made available a dataset composed of 99,000 images. Finally, we also estimate distances of the classified elements, showing all the information in an AR-based interface. Although the probe is wired-connected, it allows for the vessel to stand in deep positions, reducing its exposure and introducing a new way for submarine maneuvers and operations. We validate our proposal through a user experience experiment using 19 experts in periscope operations.
Highlights
Submarines are among the most capable and strategic naval units to operate in areas where the enemy exercises some degree of control
Max; Images generation: The images were extracted from our Bridge Simulator, which is built in Unity; Dataset augmentation and split: A Python script was developed to perform an image augmentation and dataset split in training and testing subsets; Image labelling: An AutoIt script was developed to label the images; Model training: The configuration files and images were uploaded to the cloud for training the model on Google Colab Pro machines; Convolutional Neural Networks (CNNs) application and user interface: The CNN classification is performed; Data acquisition: The data acquisition (DAQ) module was developed in AutoIt
The model was tested with the testing subset and with real vessel images, always restricted to the point of view of the periscope
Summary
Submarines are among the most capable and strategic naval units to operate in areas where the enemy exercises some degree of control. One critical maneuver for submarines is the periscope observation, which requires the ship to navigate at periscope depth (Figure 1) This exposition is strategically dangerous because the submarine can be detected by nearby enemies visually or by radar, becoming vulnerable. Due to the degree of danger, this exposure should occur for just a few seconds It must be performed by a trained officer operating the periscope, which is assigned to identify contacts in the visual range considered potential hazards during that short period. This paper proposes a Mixed Reality (MR) periscope device, which is a novel and powerful solution capable of decreasing the periscope’s exposure time and drastically increasing the observation tasks through Computer Vision techniques.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
