Master Thesis Project "Improvement Of Virtual Body Tracking Through Deep Learning And Imu Sensors"

OverviewItaldesign is an Italian design and engineering company specializing in automotive, transportation, and product development sectors.Based in Moncalieri (Turin) with over 1,300 employees worldwide, it has been innovating and working with top car makers and emerging players for more than 57 years.Italdesign offers services spanning exterior and interior design, prototyping, engineering, and turnkey project management, with a vertically integrated approach supporting clients from the first idea to homologation and series production.It also develops new technologies and mobility solutions, including electronic systems such as infotainment, ADAS, high-voltage batteries, and Software Defined Vehicles (SDVs).Since joining the Audi Group in ****, Italdesign has grown by delivering solutions that combine aesthetics and functionality.In **** Italdesign obtained the Top Employers Certification for the tenth year in a row.Posizione: Italdesign is looking for an enthusiastic and smart student passionate about automotive, eager to join an innovative and international business environment, working in an agile way and embracing a strong team spirit.You will gain valuable experience learning instruments, procedures and technical aspects with the support of your tutor and colleagues in the Department.Italdesign has long-standing expertise in augmented reality, mixed reality, and virtual reality within its XR-Solutions team, part of the Strak & XR-Solutions Department.You will be part of the XR-Solutions team and will collaborate to refine and improve an innovative system developed from previous research aimed at evaluating the feasibility of controlling a 3D avatar using IMU-type sensors instead of digital cameras and markers.As a thesis student you will be supported by your Tutor to analyse and develop the following thesis project.Thesis ProjectThe project focuses on expanding the dataset and improving a motion estimation AI model used for 3D avatar tracking:Expanding the dataset by acquiring realistic movement data in the ConceptLab laboratory using the ART (Advanced Realtime Tracking) system with 28 infrared cameras and a full-body tracking setup to obtain high-precision data and a wide variety of postures.Optimizing the AI model by training it on data acquired in realistic conditions, evaluating hardware solutions (e.g., adding IMUs) and software solutions (e.g., preprocessing, tuning, validation) to improve reliability of motion estimation.Managing data drift (cumulative time error) by studying software and hardware approaches to compensate for it.The different stages of the thesis may include:Study of the previous research activity, focusing on the AI algorithm and the sensor system;Experimental data acquisition at the Italdesign laboratory;Use of the acquired data to improve the training dataset;Modeling and optimization of the AI algorithm to reach millimeter-level accuracy compared to the real system controlled by AR;Validation in real time by comparing the avatar tracked by ART with the avatar tracked by IMU + AI (analysis of graphical stability, initial alignment, and motion consistency over time).Key RequirementsSoftware skills in Python (basic knowledge of data processing and deep learning libraries).Familiarity with Linux Ubuntu operating system;Fundamentals knowledge of AI and machine learning;Academic experience with signal and temporal data processing;Good teamwork and collaboration skills;Innovation orientation; responsibility and integrity;Good interpersonal and communicative skills;Good knowledge of Microsoft Office (Word, Excel, PowerPoint).Additional InformationEducation:attending master's degree in Computer Science or Electronic Engineering;Language skills:Fluent written and spoken Italian and English (at least B2 level);Workplace:Moncalieri (TO), Italy;Contract type:thesis project with estimated duration from 3 to 6 months;Benefits:company canteen, multicultural environment.Italdesign is committed to creating an inclusive, diverse and safe workplace, and we are proud to be an equal opportunity employer (L.******).We welcome applications from all candidates, regardless of gender, ethnicity, religion, sexual orientation, disability, parental status, or social origin.#J-*****-Ljbffr