Experimental Assessment of Feature Extraction Techniques Applied to the Identification of Properties of Common Objects, Using a Radar System

  1. José Francisco Díez-Pastor 1
  2. Pedro Latorre-Carmona 1
  3. José Luis Garrido-Labrador 1
  4. José Miguel Ramírez-Sanz 1
  5. Juan J. Rodríguez 1
  1. 1 Universidad de Burgos
    info

    Universidad de Burgos

    Burgos, España

    ROR https://ror.org/049da5t36

Revista:
Applied Sciences

ISSN: 2076-3417

Año de publicación: 2021

Volumen: 11

Páginas: 1-24

Tipo: Artículo

DOI: 10.3390/APP11156745 GOOGLE SCHOLAR

Otras publicaciones en: Applied Sciences

Objetivos de desarrollo sostenible

Resumen

Radar technology has evolved considerably in the last few decades. There are many areas where radar systems are applied, including air traffic control in airports, ocean surveillance, and research systems, to cite a few. Other types of sensors have recently appeared, which allow tracking sub-millimeter motion with high speed and accuracy rates. These millimeter-wave radars are giving rise to myriad new applications, from the recognition of the material close objects are made, to the recognition of hand gestures. They have also been recently used to identify how a person interacts with digital devices through the physical environment (Tangible User Interfaces, TUIs). In this case, the radar is used to detect the orientation, movement, or distance from the objects to the user’s hands or the digital device. This paper presents a thoughtful comparative analysis of different feature extraction techniques and classification strategies applied on a series of datasets that cover problems such as the identification of materials, element counting, or determining the orientation and distance of objects to the sensor. The results outperform previous works using these datasets, especially when the accuracy was lowest, showing the benefits feature extraction techniques have on classification performance.