Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Convergence CCTV camera embedded with Deep Learning SW technology

딥러닝 SW 기술을 이용한 임베디드형 융합 CCTV 카메라

  • Son, Kyong-Sik (Dept. of Computer Science & Engineering, Kongju National University) ;
  • Kim, Jong-Won (Dept. of Computer Science & Engineering, Kongju National University) ;
  • Lim, Jae-Hyun (Dept. of Computer Science & Engineering, Kongju National University)
  • 손경식 (공주대학교 컴퓨터공학부) ;
  • 김종원 (공주대학교 컴퓨터공학부) ;
  • 임재현 (공주대학교 컴퓨터공학부)
  • Received : 2019.10.26
  • Accepted : 2019.12.20
  • Published : 2019.01.28
Download PDF
⟨ Previous Next ⟩

Abstract

License plate recognition camera is dedicated device designed for acquiring images of the target vehicle for recognizing letters and numbers in a license plate. Mostly, it is used as a part of the system combined with server and image analysis module rather than as a single use. However, building a system for vehicle license plate recognition is costly because it is required to construct a facility with a server providing the management and analysis of the captured images and an image analysis module providing the extraction of numbers and characters and recognition of the vehicle's plate. In this study, we would like to develop an embedded type convergent camera (Edge Base) which can expand the function of the camera to not only the license plate recognition but also the security CCTV function together and to perform two functions within the camera. This embedded type convergence camera equipped with a high resolution 4K IP camera for clear image acquisition and fast data transmission extracted license plate area by applying YOLO, a deep learning software for multi object recognition based on open source neural network algorithm and detected number and characters of the plate and verified the detection accuracy and recognition accuracy and confirmed that this camera can perform CCTV security function and vehicle number plate recognition function successfully.

차량 번호판 인식 카메라는 차량 번호판 내 문자와 숫자의 인식을 위하여 대상 차량의 이미지 취득을 목적으로 하는 전용 카메라를 말하며 대부분 단독 사용보다는 서버와 영상 분석 모듈과 결합된 시스템의 일부로 적용된다. 그러나 차량 번호판 인식을 위한 시스템 구축을 위해서는 취득 영상 관리 및 분석 지원을 위한 서버와 문자, 숫자의 추출 및 인식을 위한 영상 분석 모듈을 함께 구성하여야 하므로 구축을 위한 설비가 필요하고 초기 비용이 많이 든다는 문제점이 있다. 이에 본 연구에서는 카메라의 기능을 차량 번호판 인식에만 한정하지 않고 방범 기능을 함께 수행할 수 있도록 확장하고 카메라 단독으로도 두가지 기능 수행이 가능한 Edge Base의 임베디드형 융합 카메라를 개발한다. 임베디드형 융합 카메라는 선명한 영상 취득 및 빠른 데이터 전송을 위해 고해상도 4K IP 카메라를 탑재하고 오픈소스 신경망 알고리즘 기반의 다중 객체 인식을 위한 딥러닝 SW인 YOLO를 적용하여 차량 번호판 영역을 추출한 후 차량 번호판 내의 문자와 숫자를 검출하고 검출 정확도와 인식 정확도를 검증하여 CCTV 방범 기능과 차량 번호 인식 기능이 가능한지를 확인 하였다.

Keywords

OHHGBW_2019_v10n1_103_f0001.png 이미지

Fig. 1. Conventional vehicle's parking management system configuration

OHHGBW_2019_v10n1_103_f0002.png 이미지

Fig. 2. Conventional vehicle's parking management system block diagram

OHHGBW_2019_v10n1_103_f0003.png 이미지

Fig. 3. Conventional LPR camera system configuration

OHHGBW_2019_v10n1_103_f0004.png 이미지

Fig. 4. Edge base convergence CCTV camera block diagram

OHHGBW_2019_v10n1_103_f0005.png 이미지

Fig. 5. Vehicle number plate‘s characters and numbers extraction process utilizing deep learning SW

OHHGBW_2019_v10n1_103_f0006.png 이미지

Fig. 6. Camera setting drawing

OHHGBW_2019_v10n1_103_f0007.png 이미지

Fig. 7. Live video for vehicle's entering and exiting

OHHGBW_2019_v10n1_103_f0008.png 이미지

Fig. 8. Number plate recognition web viewer

OHHGBW_2019_v10n1_103_f0009.png 이미지

Fig. 9. Extraction and recognition for entering vehicle's license plate

OHHGBW_2019_v10n1_103_f0010.png 이미지

Fig. 10. Extraction and recognition for exitingvehicle's license plate

Table 1. Performance objectives

OHHGBW_2019_v10n1_103_t0001.png 이미지

Table 2. Measurement method

OHHGBW_2019_v10n1_103_t0002.png 이미지

Table 3. Assessment of data extraction

OHHGBW_2019_v10n1_103_t0003.png 이미지

Table 4. Number plate extraction assessment by time

OHHGBW_2019_v10n1_103_t0004.png 이미지

Table 6. Number plate recognition assessment by time

OHHGBW_2019_v10n1_103_t0005.png 이미지

Table 5. Accuracy of number plate recognition

OHHGBW_2019_v10n1_103_t0006.png 이미지

References

  1. J. H. Yoon. (2017). A study on extraction algorithm of multi-license plate recognition for ITS applications. Doctoral dissertation, Hanyang University, 1-118.
  2. M. A. Ko. (2004). Effective license plate character recognition based on geometric invariant features. Doctoral dissertation, Kyungpook National University, 1-105.
  3. D. J. Kim. (2018). Implementation of Parking Management System using Cloud based License Plate Recognition Service. Journal of Digital Contents Society, 19(1), 173-179. DOI : 10.9728/dcs.2018.19.1.173
  4. H. W. Kang. (2011). License Plate Recognition for Speed and Red Light Enforcement System Based on Character Circumscribed Quadrilateral. Journal of Korean institute of information technology, 9(3), 67-76. http://www.riss.kr/ link?id=A82575539
  5. E. Polders, et al. (2015). Drivers' Behavioral Responses to Combined Speed and Red Light Cameras. Accident Analysis & Prevention, Vol.81, 153-166. DOI : 10.1016/j.aap.2015.05.006
  6. B. S. Lee, et al. (2011, Apr). The Recognition of License Plate Characters Using Regional Adaptive Binarization. Proceedings of the Korea Information Processing Society Conference. (pp. 437-440). Seoul : Korea Information Processing Society. http://www.ndsl.kr/ndsl/search/detail/ article/article SearchResultDetail.do?cn=NPAP09711248
  7. J. H. Kim. (2013). Malaysian Vehicle License Plate Recognition in Low Illumination Images. The Journal of the Korea Contents Association, 13(10), 19-26. DOI : 10.5392/JKCA.2013.13.10.019
  8. T. Natio, et al. (1999, Oct). License Plate Recognition Method for Inclined Plates Outdoors. International Conference on Information Intelligence and Systems. (pp. 304-312). Bethesda, MD : IEEE Computer society. DOI : 10.1109/ICIIS.1999.810281
  9. D. Bissessar & D.O. Gorodnichy. (2011, May). Integrating LPR with CCTV systems: problems and solutions. In Automatic Target Recognition XXI (Vol.8049, p.80490T). Orlando, FL : International Society for Optics and Photonics. DOI : 10.1117/12.883540
  10. B. J. Kim, D. H. Kim & J. H. Lee. (2016). An Improved License Plate Recognition Technique in Outdoor Image. Journal of Korean institute of intelligent systems, 26(5), 423-431. DOI : 10.5391/JKIIS.2016.26.5.423
  11. B. C. Kim. (2013). An intelligent video security system for the tracking of multiple moving objects. The Journal of digital policy & management, 11(10), 359-366. DOI : 10.14400/JDPM.2013.11.10.359
  12. H. C. Kwon. (2015). A Study on Efficient Vehicle Tracking System using Dynamic Programming Method. Journal of Digital Convergence, 13(12), 209-215. DOI : 10.14400/JDC.2015.13.12.209
  13. C. J. Seo. (2014). Artificial Vision System using Human Visual Information Processing. Journal of Digital Convergence, 12(11), 349-355. DOI : 10.14400/JDC.2014.12.11.349
  14. K. H. Kim, et al. (2003, May). Car Plate Extraction and Recognition System Using DSP Board. Proceedings of the Korea Information Processing Society Conference. (pp. 627-630). Seoul : Korea Information Processing Society. http://www.ndsl.kr/ndsl/search/detail/article/articleSearchResultDetail.do?cn=NPAP08040394
  15. M. J. Kang, H. M. Kang, Y. W. Woo & K. B. Kim. (2008). Intelligent Recognition System of Car License Plate. Proceedings of the Korean Institute of Information and Commucation Sciences Conference. (pp. 337-342). Busan : The Korea Institute of Information and Commucation Engineering. http://www.ndsl.kr/ndsl/search/detail/article/articleSearchResultDetail.do?cn=NPAP08297842