General object detection method by on-board computer vision with Artificial Neural Networks

Jittima Varagul, Toshio Ito

Research output: Contribution to journalArticle

Abstract

The objective of this paper is to find object based solutions for a collision avoidance system. In this paper, the authors present an algorithm for obstacle detection, from the actual video images taken by an on-board camera. The proposed technique is based on Histograms of Oriented Gradient (HOG) to extract features of the objects and classify the obstacles by the Time Delay Neural Network (TDNN). The experimental results showed that it can detect general objects, and is not restricted to vehicles, objects or pedestrians. It has provided good results along with high accuracy and reliability.

Original languageEnglish
Pages (from-to)149-156
Number of pages8
JournalInternational Journal of Automotive Engineering
Volume8
Issue number4
DOIs
Publication statusPublished - 2017 Jan 1

Fingerprint

Collision avoidance
neural network
Computer vision
Time delay
Cameras
Neural networks
pedestrian
video
Object detection

Keywords

  • Automatic collision notification
  • Image processing / neural networks
  • Object detection [C1]
  • Safety

ASJC Scopus subject areas

  • Human Factors and Ergonomics
  • Automotive Engineering
  • Safety, Risk, Reliability and Quality
  • Fluid Flow and Transfer Processes

Cite this

General object detection method by on-board computer vision with Artificial Neural Networks. / Varagul, Jittima; Ito, Toshio.

In: International Journal of Automotive Engineering, Vol. 8, No. 4, 01.01.2017, p. 149-156.

Research output: Contribution to journalArticle

@article{90f06734643347288c0b32ad65d1eb45,
title = "General object detection method by on-board computer vision with Artificial Neural Networks",
abstract = "The objective of this paper is to find object based solutions for a collision avoidance system. In this paper, the authors present an algorithm for obstacle detection, from the actual video images taken by an on-board camera. The proposed technique is based on Histograms of Oriented Gradient (HOG) to extract features of the objects and classify the obstacles by the Time Delay Neural Network (TDNN). The experimental results showed that it can detect general objects, and is not restricted to vehicles, objects or pedestrians. It has provided good results along with high accuracy and reliability.",
keywords = "Automatic collision notification, Image processing / neural networks, Object detection [C1], Safety",
author = "Jittima Varagul and Toshio Ito",
year = "2017",
month = "1",
day = "1",
doi = "10.20485/jsaeijae.8.4_149",
language = "English",
volume = "8",
pages = "149--156",
journal = "International Journal of Automotive Engineering",
issn = "2185-0984",
publisher = "Society of Automotive Engineers of Japan Inc",
number = "4",

}

TY - JOUR

T1 - General object detection method by on-board computer vision with Artificial Neural Networks

AU - Varagul, Jittima

AU - Ito, Toshio

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The objective of this paper is to find object based solutions for a collision avoidance system. In this paper, the authors present an algorithm for obstacle detection, from the actual video images taken by an on-board camera. The proposed technique is based on Histograms of Oriented Gradient (HOG) to extract features of the objects and classify the obstacles by the Time Delay Neural Network (TDNN). The experimental results showed that it can detect general objects, and is not restricted to vehicles, objects or pedestrians. It has provided good results along with high accuracy and reliability.

AB - The objective of this paper is to find object based solutions for a collision avoidance system. In this paper, the authors present an algorithm for obstacle detection, from the actual video images taken by an on-board camera. The proposed technique is based on Histograms of Oriented Gradient (HOG) to extract features of the objects and classify the obstacles by the Time Delay Neural Network (TDNN). The experimental results showed that it can detect general objects, and is not restricted to vehicles, objects or pedestrians. It has provided good results along with high accuracy and reliability.

KW - Automatic collision notification

KW - Image processing / neural networks

KW - Object detection [C1]

KW - Safety

UR - http://www.scopus.com/inward/record.url?scp=85039151067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039151067&partnerID=8YFLogxK

U2 - 10.20485/jsaeijae.8.4_149

DO - 10.20485/jsaeijae.8.4_149

M3 - Article

VL - 8

SP - 149

EP - 156

JO - International Journal of Automotive Engineering

JF - International Journal of Automotive Engineering

SN - 2185-0984

IS - 4

ER -