Journal of the Korean Society of Marine Environment & Safety (해양환경안전학회지)

The Korean Society of Marine Environment and safety (해양환경안전학회)
권호 표지
DOI QR코드

DOI QR Code

Vehicle Detection and Ship Stability Calculation using Image Processing Technique

영상처리기법을 활용한 차량 검출 및 선박복원성 계산

  • Kim, Deug-Bong (Division of Navigation Information System, Mokpo National Maritime University) ;
  • Heo, Jun-Hyeog (College of Maritime Sciences, Mokpo National Maritime University) ;
  • Kim, Ga-Lam (College of Maritime Sciences, Mokpo National Maritime University) ;
  • Seo, Chang-Beom (College of Maritime Sciences, Mokpo National Maritime University) ;
  • Lee, Woo-Jun (College of Maritime Sciences, Mokpo National Maritime University)
  • 김득봉 (목포해양대학교 항해정보시스템학부) ;
  • 허준혁 (목포해양대학교 해사대학) ;
  • 김가람 (목포해양대학교 해사대학) ;
  • 서창범 (목포해양대학교 해사대학) ;
  • 이우준 (목포해양대학교 해사대학)
  • Received : 2021.12.03
  • Accepted : 2021.12.28
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

After the occurrence of several passenger ship accidents in Korea, various systems are being developed for passenger ship safety management. A total of 162 passenger ships operate along the coast of Korea, of which 105 (65 %) are car-ferries with open vehicle decks. The car-ferry has a navigation pattern that passes through 2 to 4 islands. Safety inspections at the departure point(home port) are carried out by the crew, the operation supervisor of the operation management office, and the maritime safety supervisor. In some cases, self-inspections are carried out for safety inspections at layovers. As with any system, there are institutional and practical limitations. To this end, this study was conducted to suggest a method of detecting a vehicle using image processing and linking it to the calculations for ship stability. For vehicle detection, a method using a difference image and one using machine learning were used. However, a limitation was observed in these methods that the vehicle could not be identified due to strong background lighting from the pier and the ship in the cases where the camera was backlit such as during sunset or at night. It appears necessary to secure sufficient image data and upgrade the program for stable image processing.

우리나라는 여러 건의 여객선 사고를 겪으면서, 여객선 안전관리를 위해 다양한 제도를 운영하고 있다. 2021년 기준 우리나라 연안을 운항하는 여객선 162척 중, 차량갑판이 개방된 형태의 차도선이 105척(65 %)을 차지하고 있다. 차도선은 2~4개의 섬을 경유하는 운항 패턴을 가지고 있다. 출항지(모항)에서 안전점검은 선원과 운항관리실의 운항감독관, 해사안전감독관에 의해 실시된다. 경유지에서의 안전점검은 자체점검이 실시되는 경우가 있다. 여느 제도와 마찬가지로 제도적, 현실적 한계 등이 있다. 이를 위해 영상처리기법을 활용하여 차량을 검출하고 이를 선박 복원성 계산과 연동하는 방안을 제안하고자 본 연구를 수행하였다. 차량 검출을 위해 차영상을 이용하는 방법과 기계학습을 이용하는 방법을 사용하였다. 검출된 데이터를 선박 복원성 계산에 활용하였다. 기계학습을 통해 차량을 검출하는 경우, 차영상에 의한 차량 검출 방법보다 차량 식별에 안정적임을 알 수 있었다. 다만, 카메라가 일몰과 같은 상황에서 역광을 받는 경우와 야간과 같은 상황에서 부두와 선박 내부의 강한 조명에 의해 차량이 식별되지 않는 한계가 있었다. 안정적인 영상처리를 위해 충분한 영상 데이터 확보와 프로그램 고도화가 필요해 보인다.

Keywords

Acknowledgement

이 논문은 목포해양대학교 LINC+사업단의 '산학공동기술 개발과제' 연구비 지원을 받아 수행되었음.

References

  1. Eunseong Shipyard(2020), Final trim and stability booklet, Approved 08th Dec. 2020.
  2. Kang, B. S., C. H. Jung, and D. B. Kim(2020), A Study on Lashing Standards for Car Ferry Ships Sailing in Smooth Sea Areas, Journal of the Korean Society of Marine Environment & Safety, Vol. 26, No. 1, pp. 1-7. https://doi.org/10.7837/kosomes.2020.26.1.001
  3. Kim, H. B., Y. H. Lee, Y. S. Park, and G. Y. Kong(2018), A Study on Real Ship Experiments to Estimate the Heeling Angle of Passenger Type Ship when Turning, Journal of the Korean Society of Marine Environment & Safety, Vol. 24, No. 5, pp. 497-503. https://doi.org/10.7837/kosomes.2018.24.5.497
  4. Kim, H. S.(2014), A Study on Vehicle Detection using Image Processing, Sangji University, pp. 12-21.
  5. KMST(2011), General Cargo Ship 'Hangroferry two' Capsizing Accident, MPMST 2011-022.
  6. KMST(2017a), Korea Maritime Safety White Paper, Korea Maritime Safety Tribunal, pp. 200-315.
  7. KMST(2017b), Korea Maritime Safety White Paper, Korea Maritime Safety Tribunal, pp. 340-391.
  8. KMST(2021), Marine Accident Statistics, www.kmst.go.kr (accessed 4h Dec. 2021).
  9. KOMSA(2021), Coastal Passenger Ship Companies 2021 year, www.komsa.or.kr (Accessed 4th Dec. 2021).
  10. Lee, C. Y. and N. H. Kim(2015), A Study on Edge Detection using Pixel Brightness Transfer Function in Low Light Level Environments, The Journal of the Koera Institute of Informatio and Comnuication Engineering, Vol. 19, No. 7, pp. 1681-1685.
  11. Lee, Y. H. and Y. S. Kim(2020), Comparison of CNN and YOLO for Object Detection, Journal of the Semiconductor and Display Technology, Vol. 19, No. 1, pp. 85-91.
  12. MOF(2021), Intensive Management of Marine Accidents that Cause Large Casualties, Press Release (15th Feb. 2021).
  13. Redmon, J. and A. Farhadi(2017), YOLO9000: Better, Faster, Stronger, IEEE Conference on Computer Vision and Pattern Recognition, pp. 6517-6525.
  14. Redmon, J., S. Divvala, R. Girshick, and A. Farhadi(2015), You Only Look Once: Unified, Real-time Object Detection, IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788.
  15. Yang, S. G. and S. G. Kim(2007), Ship Loading and Stability, Haein Publisher, pp. 199-207.