As Austria's largest research and technology organisation for applied research, we are dedicated to make substantial contributions to solving the major challenges of our time, climate change and digitalisation. To achieve our goals, we rely on our specific research, development and technology competencies, which are the basis of our commitment to excellence in all areas. With our open culture of innovation and our motivated, international teams, we are working to position AIT as Austria's leading research institution at the highest international level and to make a positive contribution to the economy and society.

Our Center for Vision, Automation & Control located in Vienna invites applications for a master’s thesis position. At the Center for Vision, Automation & Control our research unit “Assistive & Autonomous Systems” closely works with industrial partners in order to develop safe and reliable technology components for assistance systems, that can be used in various areas of applications, for e.g.: Aviation, Railway / Public Transport, Construction Industry, Logistics & Transportation as well as in Agriculture & Forestry.

Foundation models in Computer Vision and Natural Language Processing present promising opportunities for enhancing object detection and tracking tasks. In our specific multi-view wide-area surveillance scenario, achieving human-like vision capabilities is highly challenging. This is due to factors such as the presence of extremely small objects, the occurrence of previously unseen object classes, and the complexity of cluttered and busy environments. Therefore, the development of innovative methodologies will focus on enabling spatially precise and stable object detection and tracking, a critical component for advancing remote digital tower operations in the aviation industry.

• Throughout this master’s thesis, you will closely work with our researchers and engineers, who focus on the development and deployment of assistive and autonomous systems, particularly in the area of real-time wide-area surveillance.
• Under the guidance of our experts, you will contribute to the development of cutting-edge methodologies in multi-modal learning and multi-target tracking schemes.
• You investigate state-of-the-art deep learning advancements in few-shot object detection, identifying gaps and proposing innovative solutions.
• You apply your findings to practical challenges, designing and implementing a proof-of-concept demonstration to validate your methods.

• You use an existing synthetic data generation tool in Blender to test and iterate data-intensive learning schemes.
• You design, implement, and optimise deep learning models which can perform the targeted detection & tracking tasks.
• You benchmark and evaluate model performance, improving robustness, efficiency, and generalization capabilities across varied scenarios.
• You exchange insights with interdisciplinary and international experts in machine learning and computer vision, contributing to a dynamic and collaborative environment.
• You document and present your results, with the potential to publish your work in conference proceedings or peer-reviewed journals.