Internship Proposal: Hand Gesture Recognition on embedded platforms
FBK is opening a new internship opportunity in the Energy Efficient Embedded Digital Architectures - E3DA research unit of DigiS research center. The E3DA research unit focuses on wireless resource-constrained embedded technologies with a system-level approach targeting energy efficiency and Artificial Intelligence (AI) embedding at the very edge. Energy Efficiency in networked embedded systems is one of the leading research challenges, particularly in recent years where the pervasiveness of smart, tiny low-cost electronics and new wireless protocols availability is enabling the Internet of Things (IoT). The activity spans from hardware-software development for low-power wireless smart sensing devices to power management techniques, low-power multi-hop wireless protocols, and on-board processing in resource-limited devices. We also apply RF technology for proximity detection and localization techniques. The unit applies the research results in several application domains, such as those typical of pervasive and wearable computing and IoT.
Internship opportunity This internship will provide hands-on experience in deep learning, embedded systems, and AI deployment on tiny devices. The selected candidate will work on platforms such as Nvidia Jetson, Raspberry Pi, custom AI accelerators, and microcontrollers, exploring the intersection of artificial intelligence and embedded systems.
Project Overview: The primary objective of this internship is to develop a robust hand gesture recognition system capable of running efficiently on tiny embedded devices. The system will utilize deep learning techniques to accurately recognize and interpret hand gestures in real-time. The developed model will be deployed onto one or more embedded devices, ensuring optimal performance and resource utilization.
Research and explore state-of-the-art deep learning approaches for hand gesture recognition.Develop and train deep learning models using frameworks such as TensorFlow or PyTorch.Optimize the trained models for deployment on embedded devices with limited computational resources.Evaluate and compare performance across different platforms, including Nvidia Jetson, Raspberry Pi, custom AI accelerators, and microcontrollers.Qualifications: Knowledge of machine learning, deep learning, and computer vision.Programming languages: Python and C/C++.Experience with deep learning frameworks like TensorFlow or PyTorch.Familiarity with embedded systems and hardware platforms is a plusWe offer: 3-6 months, depending on the candidate's needs and preparation;Canteen (except for UniTN students;Support for the search for accommodation at the affiliated structures (no allowance).For further details on the activities, please contact Elisabetta Farella: ******
#J-18808-Ljbffr