Length: 3 hours
Intended Audience: The targeted audience are university
students, researchers from academia, researchers and
developers from the industry and also everyone, who
is interested to get to know the different automotive
environment perception and fusion systems used in the
intelligent vehicles sector.
Description: This tutorial is focussed towards the stringent
requirements, foundations, development and testing
of sensor fusion algorithms meant for advanced driver
assistance functions and driverless applications in automotive
vehicle systems. The audience would be provided
with the materials used in the tutorial.
The audience can see the different representations of
the surrounding environment as perceived by the heterogeneous
environment perception sensors e.g. different
radars, stereo camera and lidar. The relevant state
estimation algorithms, sensor fusion frameworks and the
evaluation procedures with reference ground truth are presented
in detail. The audience can get a first ever glimpse
of the data set obtained from a sensor configuration that
would be used in the future Mercedes Benz autonomous
vehicles.
The interesting part of the tutorial is covered on the
different challenging and important practical aspects such
as fusion with incomplete information, data association,
etc. related to fusion and target tracking in automotive
setting. Fusion and management of the different extended
target representations of heterogeneous nature obtained
from sensors with different resolution is presented with
examples. More than one kind of intelligent vehicular
sensor fusion framework dealing with tracked objects
i.e. track level fusion and raw sensor measurements i.e.
measurement level fusion, with results obtained using
several real world data sets that contains various static
and dynamic targets would be presented in this tutorial.
Prerequisites: No special prerequisites are expected from
the audience. The presenters need a conference room
equipped with audio-visual presentation medium and
equipments e.g. projector. If possible availability of flip
charts or a white board would be helpful but it is not
mandatory.
Presenter: Bharanidhar Duraisamy, Ting Yuan, Tilo Schwarz, and Martin Fritzsche
Bharanidhar Duraisamy Bharanidhar Duraisamy
has been with Daimler’s department of environment
perception for the past five years. His work is
in the area of automotive multi-level sensor fusion
with active and passive environment perception
sensors, state estimation and signal processing designed
for automotive intelligent vehicular applications,
classification-fusion of relevant objects, multisensor
data association, target tracking and detection
. He has completed his master studies in robotics
and automation from the Dortmund university of
technology, Germany and he is at present working towards his doctoral degree.
Ting Yuan Dr. Ting Yuan is currently a Senior
Research Scientist at the Mercedes-Benz Research
and Development North America, Inc., Sunnyvale,
CA within the Autonomous Driving Department,
where his fields of endeavor lie in detection, classification
and tracking of moving/static objects using
information from camera, Radar and Lidar systems,
as well as data fusion for the multi-sensor systems.
He received his Ph.D. degree from the Electrical and
Computer Engineering Department at the University
of Connecticut, Storrs, CT in 2013. He is an invited
presenter on Automotive Radar System at 2016 IEEE Radar Conference,
Philadelphia, PA. His research interests include target tracking, data fusion
and multiple-model analysis.
Tilo Schwarz Dr. Tilo Schwarz has received his
Diploma in Physics from the University of Stuttgart
in 1995 and the Doctorate degree in Physics from
the University of Kiel in 2000. He has worked from
1996-1999 as PhD student and from 2000 till today
as a senior research scientist in the Environment
Perception and Sensor Fusion departments of the
Daimler Research and Advanced Engineering in
Ulm. His scientific interests are in the domains of
computer vision, machine learning, signal processing
and sensor fusion with primary applications in
the field of machine vision and driver assistance systems.
Martin Fritzsche Dr. Martin Fritzsche has received
his diploma in Geophysics and his Doctoral degree
in Electrical Engineering both fro the University
of Karlsruhe, Germany. He is with Daimler’s research
and development department for the past two
decades. He has worked on several sensor fusion
focussed active and passive safety oriented in-house
and public funded projects related to intelligent
vehicles. He has held lecture and keynote series in
many conferences and events specific to intelligent
vehicles, automotive safety research and applications.
His core research interests are in the domains of pattern recognition,
signal processing, state estimation, sensor fusion, target detection and tracking.
Previous Conferences
