Page 36 - TTG-Taiwan Transportation Equipment Guide (TTG)-2021-09 Edition

34
Feature Topic

AI based V
AI based Vehicle Vision Perception ehicle Vision Perception

System tr
System trains datasets for suppliersains datasets for suppliers

Training a self-driving vehicles’ AI platform
requires datasets, however, not all companies have
the means to create such datasets themselves. This
is where the “AI based Vehicle Vision Perception
System,” developed by the Institute for Information
Industry (III) comes in.

Hsu Ting, a senior planner at the III Smart
System Institute Emerging Markets and Planning
Service Centre, told CENS during an interview
at the Taipei AMPA show that the datasets they
use are primarily a fusion of images and LiDAR
point clouds. Regarded as Taiwan’s fi rst “Formosa worked with a local supplier to design an automatic
Database” for autonomous driving development, braking system should the driver maintain course
Hsu said the team at III designed the platform into driving into a scooter rider or pedestrian in the
and enabled the use of a semi-automatic labeling blind spot.
system once they had manually labeled the images
and LiDAR point clouds. The efforts can relieve However, in order to transfer data from high-
clients from needing to direct resources and time resolution images without any latency, which can
into training their own AI systems. be fatal for vehicle-oriented AI if the system cannot
keep up, the system requires hardware that can
To properly train an AI, such datasets could sustain high-speed network and data transfers.
be designed according to the local region, Hsu Hsu said they worked with local suppliers and
said. III had incorporated the semi-automatic turned the Nvidia chip they were using to adhere to
labeling system to allow companies to change specifi cations for automotive use. The automotive-
and adjust labels according to localized culture or spec hardware, designed with ADLINK, is featured
environmental factors. For instance, the Formosa in its IPC model and was launched in June.
Datasets would refl ect more scooters on the roads
in Taiwan than in some European countries, or lack
data for snowy road conditions, as Taiwan is mostly
in a subtropical climate. Having collected data
for over two years, Hsu said the AI could identify
diverse road objects in complex environments for
FCW, PCW, BSD, and LDW development.

News of pedestrians or scooters getting caught
under a bus or large-sized trucks is unfortunately
common in Taiwan, which Hsu attributes to a
higher population and traffic density. The III-
designed system is used conjunctively with four
high-resolution cameras stuck to four points on
the vehicle, locations that can assist the driver to
avoid scooters or pedestrians caught in the blind
spots when turning or driving. The possibilities are
numerous with the system: Hsu says they have also