Extraction of Vehicle Representative Color Regions Using Feature Points and Probability Map 


Vol. 43,  No. 3, pp. 597-602, Mar.  2018
10.7840/kics.2018.43.3.597


PDF
  Abstract

In this paper, we propose a representative color regions extraction method for color recognition of vehicles recorded in CCTV. After detection the license plate in the CCTV image, the vehicle front image is acquired. A Harris corner detection method is applied to the frontal vehicle image to generate a vehicle representative color regions probability map. Finally, the highly reliable region among the candidate regions representing the vehicle representative color information is extracted as the vehicle representative color region. In order to evaluate the performance of the proposed method, we obtained a total of 5,941 images including the vehicles from the real highway CCTV images. In the experiment using this, the vehicle representative color region detection performance of about 94.3% was shown.

  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]

K. Kim, P. Kim, K. Lim, Y. Chung, D. Choi, "Extraction of Vehicle Representative Color Regions Using Feature Points and Probability Map," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 3, pp. 597-602, 2018. DOI: 10.7840/kics.2018.43.3.597.

[ACM Style]

Kwang-Ju Kim, Pyong-Kun Kim, Kil-Taek Lim, Yun-Su Chung, and Doo-Hyun Choi. 2018. Extraction of Vehicle Representative Color Regions Using Feature Points and Probability Map. The Journal of Korean Institute of Communications and Information Sciences, 43, 3, (2018), 597-602. DOI: 10.7840/kics.2018.43.3.597.

[KICS Style]

Kwang-Ju Kim, Pyong-Kun Kim, Kil-Taek Lim, Yun-Su Chung, Doo-Hyun Choi, "Extraction of Vehicle Representative Color Regions Using Feature Points and Probability Map," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 3, pp. 597-602, 3. 2018. (https://doi.org/10.7840/kics.2018.43.3.597)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880