Adapted learning for polarization-based car detection

Rachel Blin; Samia Ainouz; Stéphane Canu; Fabrice Meriaudeau

doi:10.1117/12.2523388

16 July 2019 Adapted learning for polarization-based car detection

Rachel Blin, Samia Ainouz, Stéphane Canu, Fabrice Meriaudeau

Proceedings Volume 11172, Fourteenth International Conference on Quality Control by Artificial Vision; 1117218 (2019) https://doi.org/10.1117/12.2523388
Event: Fourteenth International Conference on Quality Control by Artificial Vision, 2019, Mulhouse, France

Abstract

Object detection in road scenes is an unavoidable task to develop autonomous vehicles and driving assistance systems. Deep neural networks have shown great performances using conventional imaging in ideal cases but they fail to properly detect objects in case of unstable scenes such as high reflections, occluded objects or small objects. Next to that, Polarized imaging, characterizing the light wave, can describe an object not only by its shape or color but also by its reflection properties. That feature is a reliable indicator of the physical nature of the object even under poor illumination or strong reflections. In this paper, we show how polarimetric images, combined with deep neural networks, contribute to enhance object detection in road scenes. Experimental results illustrate the effectiveness of the proposed framework at the end of this paper.

Citation Download Citation

Rachel Blin, Samia Ainouz, Stéphane Canu, and Fabrice Meriaudeau "Adapted learning for polarization-based car detection", Proc. SPIE 11172, Fourteenth International Conference on Quality Control by Artificial Vision, 1117218 (16 July 2019); https://doi.org/10.1117/12.2523388

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