Synthetic data has shown to be an effective proxy for real data in order to train computer vision algorithms when acquiring labeled data is costly or impossible. Ship detection and classification from satellite imagery and surveillance video is one such area, and images generated using gaming engines such as Unity3D have been used successfully to circumvent the need for annotated real data. However, there is a lack of understanding of the effect of rendering quality of 3D models on algorithms that use synthetic data. In this work, we investigate how the level of detail (LOD) of objects in a maritime scene affects ship classification algorithms. To study this systematically, we create datasets featuring objects with varying LODs and observe their significance in computer vision algorithms. Specifically, we evaluate the impact of mismatched LOD datasets on classification algorithms, and investigate the effect of low or high LOD datasets on a model's ability to transfer to real data. The LOD of 3D objects are quantified using image quality metrics while the performance of computer vision algorithms is compared using accuracy metrics.
Capsule networks have shown promise in their ability to perform classification tasks with viewpoint invariance; outperforming the accuracy of other models in some cases. This capability applies to maritime classification tasks where there is a lack of labeled data and an inability to collect all viewpoints of objects that are needed to train machine learning algorithms. Capsule Networks lend themselves well to applying their unique network architecture to the maritime vessel BCCT dataset, which exhibits characteristics aligned with the theorized strengths of Capsule Networks. Comparing these with respect to traditional CNN architectures and data augmentation techniques provides a potential roadmap for incorporation into future classification tasks involving imagery in data starved domains relying heavily on viewpoint invariance. We present our results on the classification of ship using Capsule Networks and explore their usefulness at this task given their current state of development.
Explosive Ordnance Disposal (EOD) technicians are on call to respond to a wide variety of military ordnance. As experts in conventional and unconventional ordnance, they are tasked with ensuring the secure disposal of explosive weaponry. Before EOD technicians can render ordnance safe, the ordnance must be positively identified. However, identification of unexploded ordnance (UXO) in the field is made difficult due to a massive number of ordnance classes, object occlusion, time constraints, and field conditions. Currently, EOD technicians collect photographs of unidentified ordnance and compare them to a database of archived ordnance. This task is manual and slow - the success of this identification method is largely dependent on the expert knowledge of the EOD technician. In this paper, we describe our approach to automatic ordnance recognition using deep learning. Since the domain of ordnance classification is unique, we first describe our data collection and curation efforts to account for real-world conditions, such as object occlusion, poor lighting conditions, and non-iconic poses. We apply a deep learning approach using ResNet to this problem on our collected data. While the results of these experiments are quite promising, we also discuss remaining challenges and potential solutions to deploying a real system to assist EOD technicians in their extremely challenging and dangerous role.