Deep Learning for Detection of Railway Signs and Signals

Georgios Karagiannis; Søren Ingvor Olsen; Kim Steenstrup Pedersen

Deep Learning for Detection of Railway Signs and Signals

Georgios Karagiannis, Søren Ingvor Olsen, Kim Steenstrup Pedersen

Department of Computer Science

Abstract

Major railway lines need advance management systems based on accurate maps of their infrastructure. Asset detection is an important tool towards automation of processes and improved decision support on such systems. Due to lack of available data, limited research exists investigating railway asset detection, despite the rise of Artificial Neural Networks and the numerous investigations on autonomous driving. Here, we present a novel dataset used in real world projects for mapping railway assets. Also, we implement Faster R-CNN, a state of the art deep learning object detection method, for detection of signs and signals on this dataset. We achieved 79.36% on detection and a 70.9% mAP. The results were compromised by the small size of the objects, the low resolution of the images and the high similarity across classes.

Original language	English
Publication date	24 Apr 2019
Publication status	Published - 24 Apr 2019
Event	Computer Vision Cnference - Vdara hotel, Las Vegas, United States Duration: 25 Apr 2019 → … https://saiconference.com/Conferences/CVC2019

Conference

Conference	Computer Vision Cnference
Location	Vdara hotel
Country/Territory	United States
City	Las Vegas
Period	25/04/2019 → …
Internet address	https://saiconference.com/Conferences/CVC2019

Cite this

@conference{652fa006f12540b796379c032f4425b0,

title = "Deep Learning for Detection of Railway Signs and Signals",

abstract = "Major railway lines need advance management systems based on accurate maps of their infrastructure. Asset detection is an important tool towards automation of processes and improved decision support on such systems. Due to lack of available data, limited research exists investigating railway asset detection, despite the rise of Artificial Neural Networks and the numerous investigations on autonomous driving. Here, we present a novel dataset used in real world projects for mapping railway assets. Also, we implement Faster R-CNN, a state of the art deep learning object detection method, for detection of signs and signals on this dataset. We achieved 79.36% on detection and a 70.9% mAP. The results were compromised by the small size of the objects, the low resolution of the images and the high similarity across classes.",

author = "Georgios Karagiannis and Olsen, {S{\o}ren Ingvor} and Pedersen, {Kim Steenstrup}",

year = "2019",

month = apr,

day = "24",

language = "English",

note = "Computer Vision Cnference, CVC ; Conference date: 25-04-2019",

url = "https://saiconference.com/Conferences/CVC2019",

}

TY - CONF

T1 - Deep Learning for Detection of Railway Signs and Signals

AU - Karagiannis, Georgios

AU - Olsen, Søren Ingvor

AU - Pedersen, Kim Steenstrup

PY - 2019/4/24

Y1 - 2019/4/24

N2 - Major railway lines need advance management systems based on accurate maps of their infrastructure. Asset detection is an important tool towards automation of processes and improved decision support on such systems. Due to lack of available data, limited research exists investigating railway asset detection, despite the rise of Artificial Neural Networks and the numerous investigations on autonomous driving. Here, we present a novel dataset used in real world projects for mapping railway assets. Also, we implement Faster R-CNN, a state of the art deep learning object detection method, for detection of signs and signals on this dataset. We achieved 79.36% on detection and a 70.9% mAP. The results were compromised by the small size of the objects, the low resolution of the images and the high similarity across classes.

AB - Major railway lines need advance management systems based on accurate maps of their infrastructure. Asset detection is an important tool towards automation of processes and improved decision support on such systems. Due to lack of available data, limited research exists investigating railway asset detection, despite the rise of Artificial Neural Networks and the numerous investigations on autonomous driving. Here, we present a novel dataset used in real world projects for mapping railway assets. Also, we implement Faster R-CNN, a state of the art deep learning object detection method, for detection of signs and signals on this dataset. We achieved 79.36% on detection and a 70.9% mAP. The results were compromised by the small size of the objects, the low resolution of the images and the high similarity across classes.

M3 - Paper

T2 - Computer Vision Cnference

Y2 - 25 April 2019

ER -

Deep Learning for Detection of Railway Signs and Signals

Abstract

Conference

Fingerprint

Cite this