ML and DL in ADAS
➢ After the advancement of Machine Learning and Deep Learning, the way of algorithm development from
classic rule based approach is changed.
➢ Now, AI based algorithms are created with totally different approach by training the models and also by
making learning themselves during the real time use.
➢ The reasearch and development in the area of AI for ADAS and AD (Autonomous Driving) is slowly getting
blurry.
➢ When AI algorithm is developed for vehicle, it is both useful for ADAS and AD.
➢ Example: Traffic sign recognition system using front camera
➢ Earlier, classical methods of computer vision using feature extraction were in use,
➢ Then came Machine Learning algorithms like SVM (Support Vector Machine), etc.
➢ Then now came Deep Learning CNN based networks, which has revolutionised the overall
process with high accurate results.
© Copyright content
ML and DL in ADAS
Perception Processing and
Environment Sensors Actuation
(Information extraction decision making
(Outside or inside vehicle)
from sensor data)
➢ High Amount of data
from one sensor
➢ More sensors on one
vehicle
➢ The Perception process of sensors
like Radar, Camera, Lidar is using
more ML / DL algorithms for
Environemnt Perception (Object
detection, classification, tracking)
➢ Advanced Automotive Platforms with AI
➢ Sensor Data fusion is using a lot of computing features
ML / DL algorithms ➢ AI algorithms are getting their place in desicion
making also
➢ Directly using them
© Copyright content ➢ Parallel to rule based algorithms to
increase the confidence of output
ML and DL in ADAS
Perception Processing and
Environment Sensors Actuation
(Information extraction decision making
(Outside or inside vehicle)
from sensor data)
➢ High Amount of data
from one sensor
➢ More sensors on one
vehicle
© Copyright content
High amount of Data output from Advance sensors – for ADAS and AD
➢ The Puck LITE provides high definition 3-dimensional information about the surrounding environment.
➢ High Resolution Radar from Astyx provides more than 1000 detections per scan.
© Copyright content
https://velodynelidar.com/products/puck-lite/#downloads; https://www.astyx.net/entwicklung/astyx-hires2019-datensatz.html
Multiple camera setup on vehicle – from Mobileye
© Copyright content
https://www.mobileye.com/super-vision/
Multiple sensors setup on vehicle – from Tesla & Ford
•
© Copyright content •
•
Sonar means Ultrasonic sensors
SR – Short Range
LR – Long Range
https://www.youtube.com/watch?v=V8LA0_bb9LI&t=290s (at 6:06 sec)
Thank you
