DOI QR코드

DOI QR Code

Modified Canny Edge Detection Algorithm for Detecting Subway Platform Screen Door Invasion

지하철 플랫폼 스크린 도어 침범 인식을 위한 변형된 캐니에지 검출 알고리듬

  • Lee, Ha-Woon (Dept. Electric Railway Convergence Science, Dongyang University)
  • 이하운 (동양대학교 철도전기융합학과)
  • Received : 2019.07.17
  • Accepted : 2019.08.15
  • Published : 2019.08.31

Abstract

The modified Canny edge detection algorithm that can detect the boundary between screen door and platform in the subway is proposed in this paper. Generally, in the subway, the boundary line between the platform and the screen door is darker than the surrounding area. Therefore, an edge image is using the modified bottom-hat transform by considering its characteristics. Double thresholded images with strong edge and weak edge through double thresholding are obtained. An algorithm that detects the boundary invasion between the platform and the screen door is proposed by calculating the length by applying the Hough transform to the double thresholded image and comparing the boundary line length between when there is an object such as a person and when there is no object. In this paper, the results of the proposed modified Canny edge detection algorithm using two different input images according to camera height position are shown by computer simulation.

KCTSAD_2019_v14n4_663_f0001.png 이미지

그림 1. 제안한 알고리듬 순서도 Fig. 1 The proposed algorithm flowchart

KCTSAD_2019_v14n4_663_f0002.png 이미지

그림 2. 직교좌표와 극좌표와의 관계 Fig. 2 The relation between rectangular coordinates and polar coordinates

KCTSAD_2019_v14n4_663_f0003.png 이미지

그림 4. 사람이 없을 때 연속 팽창된 영상 (a) 낮은 카메라 위치 (b) 높은 카메라 위치 (c) 사람 없는 높은 카메라 위치 (d) 사람 있는 높은 카메라 위치 Fig. 4 Cascaded dilated images without person (a) low position camera (b) high position camera (c) high position camera without person (d) high position camera with person

KCTSAD_2019_v14n4_663_f0004.png 이미지

그림 3. 입력영상 (a) 사람 없는 낮은 위치 카메라 영상 (b) 사람 있는 낮은 위치 카메라 영상 (c) 사람 없는 높은 위치 카메라 영상 (d) 사람 있는 높은 위치 카메라 영상 Fig. 3 Input image (a) low position camera image without person (b) low position camera image with person (c) high position camera image without person (d) high position camera image with person

KCTSAD_2019_v14n4_663_f0005.png 이미지

그림 5. 사람이 없을 때 bottom-hat 영상 (a) 낮은 카메라 위치 (b) 높은 카메라 위치 Fig. 5 Bottom-hat transformed images without person (a) low position camera (b) high position camera

KCTSAD_2019_v14n4_663_f0006.png 이미지

그림 6. 이중 문턱화 영상 (a) 낮은 카메라 위치 (b) 높은 카메라 위치 Fig. 6 Double thresholded images without person (a) low position camera (b) high position camera

KCTSAD_2019_v14n4_663_f0007.png 이미지

그림 7. 검출된 경계선 영상 (a) 사람 없는 낮은 카메라 위치 (b) 사람 있는 낮은 카메라 위치 (c) 사람 없는 높은 카메라 위치 (d) 사람 있는 높은 카메라 위치 Fig. 7 The detected boundary images (a) (a) low position camera without person (b) low position camera with person (c) high position camera without person (d) high position camera with person

KCTSAD_2019_v14n4_663_f0008.png 이미지

그림 8. 그림 7(c) 영상에 대한 호프 변환 결과 Fig. 8 Hough transform result for the fig. 7(c)

표 1. 호프 변환에 의해 검출된 경계선의 최대 길이 Table 1. Maximum boundary line length detected by Hough transform

KCTSAD_2019_v14n4_663_t0001.png 이미지

Acknowledgement

Supported by : 동양대학교

References

  1. L. Bin and M. Samiei, "Comparison for image edge detection algorithms," International Organization of Scientific Research Journal of Computer Engineering, vol. 2, issue 6, 2012, pp. 1-4.
  2. R. Muthukrishnan and M. Radha, "Edge detection techniques for image segmentation," International Journal of Computer Science & Information Technology, vol. 3, no. 6, Dec. 2011, pp. 259-267. https://doi.org/10.5121/ijcsit.2011.3620
  3. K. Kim, W. Son, M. Lee, and Y. Park, "The study of parking management system by image processing," J. of the Korea Institute of Electronic Communication Sciences, vol. 12, no. 4, 2017, pp. 651-656. https://doi.org/10.13067/JKIECS.2017.12.4.651
  4. N. Kim and J. Ha, "Performing missions of a small biped walking robot using image processing," J. of the Korea Institute of Electronic Communication Sciences, vol. 11, no. 12, 2016, pp. 1225-1230. https://doi.org/10.13067/JKIECS.2016.11.12.1225
  5. J. Kim and J. Ha, "Performing Missions of a Minicar using a Single Camera," J. of the Korea Institute of Electronic Communication Sciences, vol. 12, no. 1, 2017, pp. 123-128. https://doi.org/10.13067/JKIECS.2017.12.1.123
  6. H. Kim, G. Lee, J. Park, and Y. Yu, "Vehicle detection in tunnel using Gaussian mixture model and mathematical morphological processing," J. of the Korea Institute of Electronic Communication Sciences, vol. 7, no. 5, 2012, pp. 967-974. https://doi.org/10.13067/JKIECS.2012.7.5.967
  7. K. Lee, Y. Woo, J. Min, and C. Choi, "Feature Point Extraction of Sea Cucumbers using Canny Edge Detection," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 6, 2018, pp. 1281-1286. https://doi.org/10.13067/JKIECS.2018.13.6.1281
  8. M. Roushdy, "Comparative study of edge detection algorithms applying on the grayscale noisy image using morphological filter," J. on Graphic, Vision and Image Processing, vol. 6, issue 4, Dec. 2006, pp. 17-23.
  9. N. Senthilkumaran and R. Rajesh, "Edge detection techniques for image segmentation -A survey of soft computing approaches," Int. J. of Recent Trends in Engineering and Technology, vol. 1, no. 2, Nov. 2009, pp. 250-254.
  10. J. Canny, "A computational approach to edge detection", IEEE Trans. Pattern Anal. Mach. Intell. vol. 8, no. 6, 1986, pp. 679-698.
  11. W. Baek and H. Lee, "A modified top-hat and bottom-hat transform for edge detection," J. of the Korea Institute of Electronic Communication Sciences, vol. 11, no. 9, 2016, pp. 901-908. https://doi.org/10.13067/JKIECS.2016.11.9.901
  12. W. Baek and H. Lee, "Algorithm for detecting PSD boundary invasion in subway PSD using image," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 5, 2018, pp. 1051-1058. https://doi.org/10.13067/JKIECS.2018.13.5.1051