1. Current state and future research directions of radar-based human-computer interactionKlen Čopič Pucihar, Dariush Salami, Nuwan Attygalle, 2026, samostojni znanstveni sestavek ali poglavje v monografski publikaciji Opis: This chapter provides an overview of the current state of radar-based Human-Computer Interaction (HCI) and outlines future research directions. While earlier chapters in this book have explored specialised domains, such as through-material sensing, ambient intelligence, surface context awareness, hand air-writing, and on-object gesture detection, this chapter expands this perspective by examining fifty carefully selected publications that address a broad range of design and technical considerations in radar-based HCI. We review key design choices, including gesture set definitions, sensor placements, radar types, frequency ranges, signal representations, and classification algorithms. Building on this foundation, the chapter then presents a forward-looking discussion of research opportunities. Particular emphasis is placed on the need for miniaturised, energy-efficient, and adaptive radar systems capable of functioning reliably in diverse, real-world settings. Additionally, the chapter stresses the importance of developing open, standardised datasets to support reproducibility, improve generalizability, and promote inclusive design.
Ključne besede: radar-based human-computer interaction, future directions, current state
Objavljeno v RUP: 19.05.2026; Ogledov: 175; Prenosov: 9
 Celotno besedilo (4,86 MB)
Gradivo ima več datotek! Več... |
2. Radar-based human-computer interaction when sensing through materialsNuwan Attygalle, Matjaž Kljun, Arthur Sluÿters, Klen Čopič Pucihar, 2026, samostojni znanstveni sestavek ali poglavje v monografski publikaciji Opis: We increasingly interact with computing devices that are either worn on the body (e.g. smartphones, smartwatches) or are embedded within our surroundings (e.g. smart homes, smart offices). These interactions occur through a variety of input methods, including physical buttons and knobs, mid-air gestures, touch and voice commands. With the exception of voice, these modalities require direct or near-direct physical contact with the device, typically involving line-of-sight or proximity for touch or grasp. However, interaction becomes constrained or entirely infeasible (i) when the interaction device is covered (e.g. when a smartphone is inside a pocket or a smartwatch is covered by a jacket sleeve), (ii) in sterile environments requiring separation between the user and device (e.g. when wearing personal protective equipment) or (iii) when interfaces are deliberately concealed for aesthetic, safety or functional reasons. Enabling interaction in such contexts is important to leverage the computational capabilities embedded in our environments. Yet, current technologies remain limited when interaction through occluding materials is needed. In this chapter, we examine existing research on the use of radar-based systems for interaction through materials, focusing on how materials affect system performance, principles for designing such interfaces and strategies to advance these systems.
Ključne besede: radar, human-computer interaction, sensing through materials
Objavljeno v RUP: 18.05.2026; Ogledov: 214; Prenosov: 8
Celotno besedilo (53,62 MB)
Gradivo ima več datotek! Več... |
3. Digital signal processing tools for radar-based human-computer interactionNuwan Attygalle, Matjaž Kljun, Klen Čopič Pucihar, 2026, samostojni znanstveni sestavek ali poglavje v monografski publikaciji Opis: In recent years, miniature radar-on-chip sensors have been explored for HCI by both academia and industry. This is driven by the availability of affordable radar hardware and advances in signal processing and machine learning. However, comparative evaluation of radar-based gesture interaction systems is challanging and rear. One important dimension for comparison is the set of radar signal representa- tions derived from raw voltage data. These representations commonly include range- Doppler, range-azimuth-angle, range-elevation-angle, point cloud and In-phase and Quadrature (IQ) radar cube formats. However, existing studies often restrict com- parative analysis to a single signal representation type, typically focusing on gesture recognition algorithms or minor variations within Digital Signal Processing (DSP) pipelines. To promote comparative evaluation of radar signal representations, this chapter develops an open-source application designed to facilitate efficient and reli- able dataset preparation of various radar signal representations. The application sup- ports visualisation of generated signal representations and includes a command-line interface for batch processing, thereby streamlining the dataset preparation workflow.
Ključne besede: digital signal processing, radar, human-computer interaction
Objavljeno v RUP: 18.05.2026; Ogledov: 226; Prenosov: 5
Celotno besedilo (41,69 MB)
Gradivo ima več datotek! Več... |
