Automated Augmentation with Reinforcement Learning and GANs for Robust Identification of Traffic Signs using Front Camera Images
Paper i proceeding, 2019

Traffic sign identification using camera images from vehicles plays a critical role in autonomous driving and path planning. However, the front camera images can be distorted due to blurriness, lighting variations and vandalism which can lead to degradation of detection performances. As a solution, machine learning models must be trained with data from multiple domains, and collecting and labeling more data in each new domain is time consuming and expensive. In this work, we present an end-to-end framework to augment traffic sign training data using optimal reinforcement learning policies and a variety of Generative Adversarial Network (GAN) models, that can then be used to train traffic sign detector modules. Our automated augmenter enables learning from transformed nightime, poor lighting, and varying degrees of occlusions using the LISA Traffic Sign and BDD-Nexar dataset. The proposed method enables mapping training data from one domain to another, thereby improving traffic sign detection precision/recall from 0.70/0.66 to 0.83/0.71 for nighttime images.

Författare

Sohini Roy Chowdhury

Volvo Cars

Lars Tornberg

Volvo Cars

Robin Halvfordsson

Chalmers

Jonatan Nordh

Chalmers

Adam Suhren Gustafsson

Chalmers

Joel Wall

Chalmers

Mattias Westerberg

Chalmers

Adam Wirehed

Chalmers

Louis Tilloy

University of California at Berkeley

Hu Zhanying

University of California at Berkeley

Haoyuan Tan

University of California at Berkeley

Meng Pan

University of California at Berkeley

Jonas Sjöberg

Chalmers, Elektroteknik, System- och reglerteknik, Mekatronik

Conference Record - Asilomar Conference on Signals, Systems and Computers

10586393 (ISSN)

IEEE Asilomar SSC 2019
Asilomar , USA,

WASP - Security for Autonomous Systems

Knut och Alice Wallenbergs Stiftelse, 2016-03-01 -- 2021-02-28.

Ämneskategorier

Annan data- och informationsvetenskap

Transportteknik och logistik

Datorseende och robotik (autonoma system)

Styrkeområden

Transport

Mer information

Skapat

2020-01-10