A. Abdullah

A. Abdullah, T. Barua, R. Tibbetts et al.

In this paper, we present CaveSeg - the first visual learning pipeline for semantic segmentation and scene parsing for AUV navigation inside underwater caves. We address the problem of scarce annotated training data by preparing a comprehensive dataset for semantic segmentation of underwater cave scenes. It contains pixel annotations for important navigation markers (e.g. caveline, arrows), obstacles (e.g. ground plane and overhead layers), scuba divers, and open areas for servoing. Through comprehensive benchmark analyses on cave systems in USA, Mexico, and Spain locations, we demonstrate that robust deep visual models can be developed based on CaveSeg for fast semantic scene parsing of underwater cave environments. In particular, we formulate a novel transformer-based model that is computationally light and offers near real-time execution in addition to achieving state-of-the-art performance. Finally, we explore the design choices and implications of semantic segmentation for visual servoing by AUVs inside underwater caves. The proposed model and benchmark dataset open up promising opportunities for future research in autonomous underwater cave exploration and mapping.

A. Abdullah, A. N. Zainab

This paper describes the digital library of historical resources, a research project which involves building a testbed for the purpose of developing and testing new collaborative digital library functionality and presents an initial analysis of the digital library's public use on the web. The digital library is modeled to focus on serving secondary students information needs in conducting history projects. As such, in the implementation of the digital library, the use of online resources would be an integral part of history project based learning activities. Students should be enabled to access digital resources, create and publish their own documents in the digital library and share them with others. As a testbed system, the collaborative digital library known as CoreDev has demonstrated its capabilities in serving an educational community as has been reflected by the positive feedback on the functional requirements from 44 users. Over 75% of the respondents in the user survey considered themselves capable of using the digital library easily. The beta tester demographics (n = 105) indicate that the digital library is reaching its target communities.