Abstract:
Advanced driver-assistance systems (ADAS) are more prevalent in high-end vehicles than in low-end
vehicles. The research proposes an alternative for drivers without having to wait years to gain access
to the safety ADAS offers. Wireless Multimedia Sensor Networks (WMSN) for ADAS applications
in collaboration with smartphones is non-existent. Intra-vehicle environments cause difficulties in
data transfer for wireless networks where performance of such networks in an intra-vehicle network is
investigated.
A low-cost alternative was proposed that extends a smartphone’s sensor perception, using a camera-
based wireless sensor network. This dissertation presents the design of a low-cost ADAS alternative
that uses an intra-vehicle wireless sensor network structured by a Wi-Fi Direct topology, using a
smartphone as the processing platform. In addition, to expand on the smartphone’s other commonly
available wireless protocols, the Bluetooth protocol was used to collect blind spot sensory data, being
processed by the smartphone. Both protocols form part of the Intra-Vehicular Wireless Sensor Network
(IVWSN).
Essential ADAS features developed on the smartphone ADAS application carried out both lane
detection and collision detection on a vehicle. A smartphone’s processing power was harnessed and used as a generic object detector through a convolution neural network, using the sensory network’s
video streams. Blind spot sensors on the lateral sides of the vehicle provided sensory data transmitted
to the smartphone through Bluetooth.
IVWSNs are complex environments with many reflective materials that may impede communication.
The network in a vehicle environment should be reliable. The network’s performance was analysed to
ensure that the network could carry out detection in real-time, which would be essential for the driver’s
safety. General ADAS systems use wired harnessing for communication and, therefore, the practicality
of a novel wireless ADAS solution was tested.
It was found that a low-cost advanced driver-assistance system alternative can be conceptualised by
using object detection techniques being processed on a smartphone from multiple streams, sourced
from an IVWSN, composed of camera sensors. A low-cost CMOS camera sensors network with a
smartphone found an application, using Wi-Fi Direct to create an intra-vehicle wireless network as a
low-cost advanced driver-assistance system.
