Vehicle Detection System Using Sensor Fusion 


Vol. 42,  No. 8, pp. 1599-1610, Aug.  2017
10.7840/kics.2017.42.8.1599


PDF
  Abstract

This paper deals with the construction of a sensor fusion system for vehicle detection. radar sensor and vision sensor has its advantages and disadvantages. First, the radar sensor has a high detection rate and is resistant to environmental changes such as light, rain, and snow. However, the price is expensive, the index is not intuitive, and erroneous detection due to diffuse reflection sometimes occurs. Vision sensors, on the other hand, are sensitive to environmental changes such as light, rain, and snow, but they are cheap, intuitive to detect, and easy to install and manage. Therefore, this paper deals with a system that overcomes the problems of each sensor and fuses two sensors for higher vehicle detection. The radar sensor uses the Kalman filter to increase the detection rate. The vision sensor detects the vehicle using the gradient - based histogram model. In this case, the detection results of the two sensors are significantly better than those of the conventional sensor alone. Recall was increase from 0.63 for radar sensor and 0.69 for vision sensor to 0.78 for two sensor, Precision was increased from 0.66 for radasr sensor and 0.84 vision sensor to 0.92 for two sensor. In addition it can be seen by comparing FPS that the speed is improved by about 22% compared with the case of using the Gaussian Mixture Model.

  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. Kim, I. Won, J. Kwon, "Vehicle Detection System Using Sensor Fusion," The Journal of Korean Institute of Communications and Information Sciences, vol. 42, no. 8, pp. 1599-1610, 2017. DOI: 10.7840/kics.2017.42.8.1599.

[ACM Style]

Se-jin Kim, In-su Won, and Jang-woo Kwon. 2017. Vehicle Detection System Using Sensor Fusion. The Journal of Korean Institute of Communications and Information Sciences, 42, 8, (2017), 1599-1610. DOI: 10.7840/kics.2017.42.8.1599.

[KICS Style]

Se-jin Kim, In-su Won, Jang-woo Kwon, "Vehicle Detection System Using Sensor Fusion," The Journal of Korean Institute of Communications and Information Sciences, vol. 42, no. 8, pp. 1599-1610, 8. 2017. (https://doi.org/10.7840/kics.2017.42.8.1599)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880