Real-Time Road-Direction Point Detection in Complex Environment

Huimin CAI; Eryun LIU; Hongxia LIU; Shulong WANG

doi:10.1587/transinf.2017EDP7266

Real-Time Road-Direction Point Detection in Complex Environment

Huimin CAI, Eryun LIU, Hongxia LIU, Shulong WANG

Full Text Views

0

Share
Cite this

Summary :

A real-time road-direction point detection model is developed based on convolutional neural network architecture which can adapt to complex environment. Firstly, the concept of road-direction point is defined for either single road or crossroad. For single road, the predicted road-direction point can serve as a guiding point for a self-driving vehicle to go ahead. In the situation of crossroad, multiple road-direction points can also be detected which will help this vehicle to make a choice from possible directions. Meanwhile, different types of road surface can be classified by this model for both paved roads and unpaved roads. This information will be beneficial for a self-driving vehicle to speed up or slow down according to various road conditions. Finally, the performance of this model is evaluated on different platforms including Jetson TX1. The processing speed can reach 12 FPS on this portable embedded system so that it provides an effective and economic solution of road-direction estimation in the applications of autonomous navigation.

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.2 pp.396-404

Publication Date: 2018/02/01

Publicized: 2017/11/13

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017EDP7266

Type of Manuscript: PAPER

Category: Software System

Authors

Huimin CAI
  Xidian University
Eryun LIU
  Zhejiang University
Hongxia LIU
  Xidian University
Shulong WANG
  Xidian University

Keyword

road-direction point, road detection, CNN, autonomous navigation

Cite this

Copy

Huimin CAI, Eryun LIU, Hongxia LIU, Shulong WANG, "Real-Time Road-Direction Point Detection in Complex Environment" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 2, pp. 396-404, February 2018, doi: 10.1587/transinf.2017EDP7266.
Abstract: A real-time road-direction point detection model is developed based on convolutional neural network architecture which can adapt to complex environment. Firstly, the concept of road-direction point is defined for either single road or crossroad. For single road, the predicted road-direction point can serve as a guiding point for a self-driving vehicle to go ahead. In the situation of crossroad, multiple road-direction points can also be detected which will help this vehicle to make a choice from possible directions. Meanwhile, different types of road surface can be classified by this model for both paved roads and unpaved roads. This information will be beneficial for a self-driving vehicle to speed up or slow down according to various road conditions. Finally, the performance of this model is evaluated on different platforms including Jetson TX1. The processing speed can reach 12 FPS on this portable embedded system so that it provides an effective and economic solution of road-direction estimation in the applications of autonomous navigation.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7266/_p

Copy

@ARTICLE{e101-d_2_396,
author={Huimin CAI, Eryun LIU, Hongxia LIU, Shulong WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Real-Time Road-Direction Point Detection in Complex Environment},
year={2018},
volume={E101-D},
number={2},
pages={396-404},
abstract={A real-time road-direction point detection model is developed based on convolutional neural network architecture which can adapt to complex environment. Firstly, the concept of road-direction point is defined for either single road or crossroad. For single road, the predicted road-direction point can serve as a guiding point for a self-driving vehicle to go ahead. In the situation of crossroad, multiple road-direction points can also be detected which will help this vehicle to make a choice from possible directions. Meanwhile, different types of road surface can be classified by this model for both paved roads and unpaved roads. This information will be beneficial for a self-driving vehicle to speed up or slow down according to various road conditions. Finally, the performance of this model is evaluated on different platforms including Jetson TX1. The processing speed can reach 12 FPS on this portable embedded system so that it provides an effective and economic solution of road-direction estimation in the applications of autonomous navigation.},
keywords={},
doi={10.1587/transinf.2017EDP7266},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - Real-Time Road-Direction Point Detection in Complex Environment
T2 - IEICE TRANSACTIONS on Information
SP - 396
EP - 404
AU - Huimin CAI
AU - Eryun LIU
AU - Hongxia LIU
AU - Shulong WANG
PY - 2018
DO - 10.1587/transinf.2017EDP7266
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2018
AB - A real-time road-direction point detection model is developed based on convolutional neural network architecture which can adapt to complex environment. Firstly, the concept of road-direction point is defined for either single road or crossroad. For single road, the predicted road-direction point can serve as a guiding point for a self-driving vehicle to go ahead. In the situation of crossroad, multiple road-direction points can also be detected which will help this vehicle to make a choice from possible directions. Meanwhile, different types of road surface can be classified by this model for both paved roads and unpaved roads. This information will be beneficial for a self-driving vehicle to speed up or slow down according to various road conditions. Finally, the performance of this model is evaluated on different platforms including Jetson TX1. The processing speed can reach 12 FPS on this portable embedded system so that it provides an effective and economic solution of road-direction estimation in the applications of autonomous navigation.
ER -