WiFi sensing, i.e., using WiFi signals to scan the environment, is a promising technology with a plurality of potential applications in the automotive domain. In addition to being cost-effective, since WiFi sensing does not rely on images, it addresses privacy concerns and/or regulations in vehicle interiors. However, there is a notorious lack of publicly available datasets necessary to train the underlying machine learning (ML) models and further develop the technology in this domain. Here, we propose one such dataset consisting of CSI (Channel State Information) (i.e., phase and amplitude) recordings in more than 100 different scenarios involving multiple individuals and different vehicles. The core idea of this dataset is to better configure safety and comfort features of a vehicle, e.g., airbag inflation, headrest position, seat belts, etc., based on actual phenotypic information obtain by WiFi sensing from within the cabin. The dataset itself however has a much wider range of potential applications. We have not only labeled CSI data by participants' height, weight, gender, and seat position among others, but also include anonymized video recordings for further labeling in the future (say, for example, activity, etc.). In addition, CSI data was collected every time from multiple spots within the vehicle allowing for later studies concerning sensor positioning in an application of interest.
WiSe4Car: A Dataset for WiFi Sensing in Automotive Vehicles
Research Data
Electronic Resource
Unknown
Automotive WiFi Availability in Dynamic Urban Canyon Environments
Online Contents | 2016
|Automotive WiFi Availability in Dynamic Urban Canyon Environments
Tema Archive | 2014
|European Patent Office | 2025
|Engineering Index Backfile | 1928
|