Earticle

초록

영어

Background/Objectives: In this study, we intend to extract a characteristic study of the raining situation based on the GMM (Gaussian mix model) within the raining image and perform the raining phenomenon in real time. Methods/Statistical analysis: Since the Gaussian Mixture Model is a good model for expressing natural phenomena, the Gaussian Mixture Model was used in many fields. In this study, an OpenCV library provided by a Python program was used to analyze rain video using CV2 library. Findings: A test video image object was created, and the frame size was set to create a gray scale image and an image for accumulating color frames. A video frame was acquired, and an average image was calculated using the accumulated images for color image frames and gray scale images, and displayed in a window. An error rate occurs during the initial image analysis, but the accuracy increases over time. By analyzing the raining image, the motion of the rain was detected using the findObjectAndDraw() function to remove the noise. In the image of the detected rain, it was marked with a red bounding rectangle to confirm the rain. Improvements/Application s: In this study, a Gaussian mixture model was used, but the K-NN model was applied to make a more accurate analysis through comparison between various models.

목차

Abstract
I. INTRODUCTION
II. THEORETICAL BACKGROUND
A. GMM(Gaussian mixture model)
B. Mixed model background
III. RESEARCH ANALYSIS
A. Analysis Method
B. Analysis Tools
C. Analysis Library
D. Analysis Result
IV. CONCLUSION AND SUGGESTIONS
REFERENCES

키워드

저자

• Jeongwon Lee [ Student, Department of Information Communication and Engineering, Hanbat National University, Daejoen, 34158, Republic of Korea ]
• Choong Ho Lee [ Professor, Department of Information Communication and Engineering, Hanbat National University, Daejoen, 34158, Republic of Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  IJASC

• 간기

  계간

• pISSN

  2619-8150

• 수록기간

  2019~2024

• 십진분류

  KDC 327 DDC 332