MA: Human Activity Recognition Using an Orthogonal Radar Network

Task description:

Integration of smart home applications is becoming increasingly prevalent in the daily routines of individuals. While audio and RGB camera systems have already paved the way for voice and gesture control in certain households, concerns regarding privacy intrusion persist, particularly with the use of audiovisual sensor technology. In this context, radar sensors offer a distinct advantage by minimizing privacy concerns, as they gather data that does not contain any directly identifiable personal references. Radar sensors offer significant potential for both private residences and public buildings for task relating to human behavior while maintaining stringent data protection standards. They can be used, for instance, to detect people in the building, their general movements including gestures and even to measure vital parameters.

A comprehensive study of human activities is currently conducted at the Institute of Microwaves and Photonics (LHFT) recording time-synchronized raw radar data, RGB images, and optical motion capture (OMC) data. Recognized as the gold standard for motion recognition, OMC data serves as the ground truth for this investigation. The thesis focuses on human activity recognition (HAR) such as walking, sitting down and standing up again, by applying robust machine learning (ML) algorithms to radar raw data. The existing measurement protocol will be exceeded by extending the measurement setup with a secondary orthogonal radar, enabling the recording of human motions from multiple perspectives.

To achieve this goal, a thorough review of the literature is imperative to grasp the state-of-the-art ML techniques tailored for HAR from raw radar data. The measurement setup needs to be extended as well as measurements are conducted to acquire a foundational dataset for ML training. Subsequently, various ML approaches are developed and accurately evaluated. Finally, the accuracy of HAR using raw radar data is compared with existing results in literature, providing valuable insights into the efficacy of this novel approach.

Requirements: Python, Pre-knowledge in radar signal processing
Supervisors: Lukas Engel (M.Sc.), Dr.-Ing. Ingrid Ullmann, Prof. Dr.-Ing. Martin Vossiek
Date of issue: April 2024
Language: German or English