TY - GEN
T1 - Deep Learning of OpenStreetMap Images Labeled Using Road Traffic Accident Data
AU - Arase, Kaito
AU - Wu, Zhijian
AU - Migita, Tsuyoshi
AU - Takahashi, Norikazu
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Number JP21H03510. 1https://www8.cao.go.jp/koutu/kihon/keikaku11/pdf/11th kettei.pdf
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Identifying potentially high-risk areas is an important task for preventing road traffic accidents. In this paper, we present an attempt to train deep Convolutional Neural Networks (CNNs) on OpenStreetMap (OSM) images, each of which is labeled 'high-risk' or 'low-risk' using the data of road traffic accidents occurred in Okayama Prefecture, Japan from 2010 to 2021. It is shown that the trained CNNs can correctly predict whether a prescribed area is high-risk or low-risk only from the corresponding OSM image with a high probability. We also present some results of applications of Grad-CAM to the trained CNNs in order to visualize their decision making process.
AB - Identifying potentially high-risk areas is an important task for preventing road traffic accidents. In this paper, we present an attempt to train deep Convolutional Neural Networks (CNNs) on OpenStreetMap (OSM) images, each of which is labeled 'high-risk' or 'low-risk' using the data of road traffic accidents occurred in Okayama Prefecture, Japan from 2010 to 2021. It is shown that the trained CNNs can correctly predict whether a prescribed area is high-risk or low-risk only from the corresponding OSM image with a high probability. We also present some results of applications of Grad-CAM to the trained CNNs in order to visualize their decision making process.
KW - deep learning
KW - Grad-CAM
KW - OpenStreetMap
KW - traffic accident data
UR - http://www.scopus.com/inward/record.url?scp=85145662792&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85145662792&partnerID=8YFLogxK
U2 - 10.1109/TENCON55691.2022.9977529
DO - 10.1109/TENCON55691.2022.9977529
M3 - Conference contribution
AN - SCOPUS:85145662792
T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON
BT - Proceedings of 2022 IEEE Region 10 International Conference, TENCON 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE Region 10 International Conference, TENCON 2022
Y2 - 1 November 2022 through 4 November 2022
ER -
