Vehicle Detection Algorithm for VDS by Using Décalcomanie Matching Based on Histogram 


Vol. 42,  No. 6, pp. 1225-1232, Jun.  2017
10.7840/kics.2017.42.6.1225


PDF
  Abstract

In this paper, we propose a histogram-based decalcomania matching algorithm to overcome the problem that conventional vehicle recognition methods for VDS (Vehicle Detection System) are difficult to be processed in real time due to high computational complexity. When we look at a vehicle from the front and divide it into exactly half, both halfs are symmetrical. This paper focuses on this point. The whole algorithm consists of four steps: setup of ROI (Region of Interest), object detection through background subtraction, morphology, and histogram-based decalcomania matching. The devised algorithm is implemented by OpenCV programming and executed on a small mini-PC platform. The performance evaluation results show that the proposed algorithm has run-time performance of 25fps@720p, vehicle recognition rate of 97.2% on average, and center coordinate error rate of average 9.58% or less under good weather.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

S. Jo and J. Lee, "Vehicle Detection Algorithm for VDS by Using Décalcomanie Matching Based on Histogram," The Journal of Korean Institute of Communications and Information Sciences, vol. 42, no. 6, pp. 1225-1232, 2017. DOI: 10.7840/kics.2017.42.6.1225.

[ACM Style]

Sang-Il Jo and Jaesung Lee. 2017. Vehicle Detection Algorithm for VDS by Using Décalcomanie Matching Based on Histogram. The Journal of Korean Institute of Communications and Information Sciences, 42, 6, (2017), 1225-1232. DOI: 10.7840/kics.2017.42.6.1225.

[KICS Style]

Sang-Il Jo and Jaesung Lee, "Vehicle Detection Algorithm for VDS by Using Décalcomanie Matching Based on Histogram," The Journal of Korean Institute of Communications and Information Sciences, vol. 42, no. 6, pp. 1225-1232, 6. 2017. (https://doi.org/10.7840/kics.2017.42.6.1225)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880