Comparing machine learning and neural network-based approaches for sign detection and classification in autonomous vehicles

Sphurti More; Jeremy Bos

doi:10.1117/12.2558966

18 May 2020 Comparing machine learning and neural network-based approaches for sign detection and classification in autonomous vehicles

Sphurti More, Jeremy Bos

Author Affiliations +

Proceedings Volume 11415, Autonomous Systems: Sensors, Processing, and Security for Vehicles and Infrastructure 2020; 114150H (2020) https://doi.org/10.1117/12.2558966
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

Abstract

We compare two algorithms, Histogram of Oriented Gradient (HOG) with linear Support Vector Machine (SVM) and You Look Only Once (YOLO), to the task of sign detection and classification from imagery from the LISA dataset. Comparisons are made in terms of execution time, accuracy, and readiness for use on GPU or FPGA hardware for acceleration. We find the neural network-based approaches like YOLO have superior accuracy but run slower on general purpose CPUs without acceleration. On the other hand, while less accurate the SVM-based are faster without acceleration.

Conference Presentation

Citation Download Citation

Sphurti More and Jeremy Bos "Comparing machine learning and neural network-based approaches for sign detection and classification in autonomous vehicles", Proc. SPIE 11415, Autonomous Systems: Sensors, Processing, and Security for Vehicles and Infrastructure 2020, 114150H (18 May 2020); https://doi.org/10.1117/12.2558966

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available