An algorithm to estimate speed by colour-based object detection

Aghil Shavalipour, Sallehuddin Mohamed Haris

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper describes a method to determine the travelling speed of a moving object from a sequence of captured video image frames. Using a new method for the detection of objects in colour images, the target moving object is identified and located in each video frame. The object detection process is performed by a colour segmentation method and a labelling algorithm. By defining a rectangular bounding box around it in every frame, the detected object image is isolated from other moving objects in the video, and tracked. The velocity can then be determined by calculating the distance through which the bounding box centroid moves over a sequence of frames with respect to the frame rate of the video recording.

Original languageEnglish
Pages (from-to)203-210
Number of pages8
JournalInternational Journal of Signal and Imaging Systems Engineering
Volume7
Issue number4
DOIs
Publication statusPublished - 1 Dec 2014

Fingerprint

Color
Video recording
Labeling
Object detection

Keywords

  • Bounding box
  • Moving centre
  • Object colour detection
  • Speed estimation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

An algorithm to estimate speed by colour-based object detection. / Shavalipour, Aghil; Mohamed Haris, Sallehuddin.

In: International Journal of Signal and Imaging Systems Engineering, Vol. 7, No. 4, 01.12.2014, p. 203-210.

Research output: Contribution to journalArticle

@article{816668cc87004dcfb3e0f73632730ce2,
title = "An algorithm to estimate speed by colour-based object detection",
abstract = "This paper describes a method to determine the travelling speed of a moving object from a sequence of captured video image frames. Using a new method for the detection of objects in colour images, the target moving object is identified and located in each video frame. The object detection process is performed by a colour segmentation method and a labelling algorithm. By defining a rectangular bounding box around it in every frame, the detected object image is isolated from other moving objects in the video, and tracked. The velocity can then be determined by calculating the distance through which the bounding box centroid moves over a sequence of frames with respect to the frame rate of the video recording.",
keywords = "Bounding box, Moving centre, Object colour detection, Speed estimation",
author = "Aghil Shavalipour and {Mohamed Haris}, Sallehuddin",
year = "2014",
month = "12",
day = "1",
doi = "10.1504/IJSISE.2014.066599",
language = "English",
volume = "7",
pages = "203--210",
journal = "International Journal of Signal and Imaging Systems Engineering",
issn = "1748-0698",
publisher = "Inderscience Enterprises Ltd",
number = "4",

}

TY - JOUR

T1 - An algorithm to estimate speed by colour-based object detection

AU - Shavalipour, Aghil

AU - Mohamed Haris, Sallehuddin

PY - 2014/12/1

Y1 - 2014/12/1

N2 - This paper describes a method to determine the travelling speed of a moving object from a sequence of captured video image frames. Using a new method for the detection of objects in colour images, the target moving object is identified and located in each video frame. The object detection process is performed by a colour segmentation method and a labelling algorithm. By defining a rectangular bounding box around it in every frame, the detected object image is isolated from other moving objects in the video, and tracked. The velocity can then be determined by calculating the distance through which the bounding box centroid moves over a sequence of frames with respect to the frame rate of the video recording.

AB - This paper describes a method to determine the travelling speed of a moving object from a sequence of captured video image frames. Using a new method for the detection of objects in colour images, the target moving object is identified and located in each video frame. The object detection process is performed by a colour segmentation method and a labelling algorithm. By defining a rectangular bounding box around it in every frame, the detected object image is isolated from other moving objects in the video, and tracked. The velocity can then be determined by calculating the distance through which the bounding box centroid moves over a sequence of frames with respect to the frame rate of the video recording.

KW - Bounding box

KW - Moving centre

KW - Object colour detection

KW - Speed estimation

UR - http://www.scopus.com/inward/record.url?scp=84920087691&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920087691&partnerID=8YFLogxK

U2 - 10.1504/IJSISE.2014.066599

DO - 10.1504/IJSISE.2014.066599

M3 - Article

AN - SCOPUS:84920087691

VL - 7

SP - 203

EP - 210

JO - International Journal of Signal and Imaging Systems Engineering

JF - International Journal of Signal and Imaging Systems Engineering

SN - 1748-0698

IS - 4

ER -