DOI QR코드

DOI QR Code

Development of A Uniform And Casual Clothing Recognition System For Patient Care In Nursing Hospitals

  • Yun, Ye-Chan (Dept. of Information Technology & Engineering, Jeonbuk National University) ;
  • Kwak, Young-Tae (Dept. of Information Technology & Engineering, Jeonbuk National University)
  • Received : 2020.10.12
  • Accepted : 2020.12.09
  • Published : 2020.12.31

Abstract

The purpose of this paper is to reduce the ratio of the patient accidents that may occur in nursing hospitals. In other words, it determines whether the person approaching the dangerous area is a elderly (patient uniform) group or a practitioner(Casual Clothing) group, based on the clothing displayed by CCTV. We collected the basic learning data from web crawling techniques and nursing hospitals. Then model training data was created with Image Generator and Labeling program. Due to the limited performance of CCTV, it is difficult to create a good model with both high accuracy and speed. Therefore, we implemented the ResNet model with relatively excellent accuracy and the YOLO3 model with relatively excellent speed. Then we wanted to allow nursing hospitals to choose a model that they wanted. As a result of the study, we implemented a model that can distinguish patient and casual clothes with appropriate accuracy. Therefore, it is believed that it will contribute to the reduction of safety accidents in nursing hospitals by preventing the elderly from accessing the danger zone.

본 연구의 목적은 요양병원에서 발생할 수 있는 노인안전사고 발생률을 감소시키는 것이다. 즉, 위험지역으로 접근하는 인물이 노인(환자복) 그룹인지 실무자(평상복) 그룹인지를 CCTV에 나타나는 의복을 기준으로 구별하는 것이다. Web Crawling기법과 요양병원으로부터 지원을 받아 기초 데이터를 수집하였다. 이후 Image Generator와 Labeling으로 모델 학습 데이터를 만들었다. CCTV의 제한된 성능 때문에 높은 정확도와 속도를 모두 갖춘 모델을 만드는 것은 어려웠다. 그러므로 정확성이 상대적으로 우수한 ResNet 모델, 속도에서 상대적으로 우수한 YOLO3 모델을 각각 구현했다. 그리고 요양병원이 자신의 실정에 맞는 모델을 고를 수 있게 하고자 했다. 연구 결과 환자복과 평상복을 적절한 정확도로 구별할 수 있는 모델을 구현하였다. 따라서 실제 사용처에서 노인들이 위험구역에 접근하지 못하도록 하여 요양병원 안전사고 감소에 이바지 할 것으로 평가된다.

Keywords

References

  1. C. H. Song, South Korea enters 'aged society' over 14% over 65 years of age, https://www.donga.com/news/Society/article/all/20180828/91705793/1.
  2. M. H. Choi, Korea enters an aging society, changes in the menopausal market, http://www.businesskorea.co.kr/news/articleView.html?idxno=40925.
  3. M. S. Yun. and J. Y. Moon, "Need to Analyze Demand Considering Active Areas and Living Population when Expanding Social Service Facilities Due to the Increase in the Elderly Population", Seoul Institute Policy Project Research Report, pp. 1-19, 2018.
  4. D. Y. Park, Nursing hospitals and nursing homes increased by 15% compared to the previous year, a total of 6833 in 2017, https://www.dailymedi.com/detail.php?number=835542&thread=22r14.
  5. D. H. Kim, "Trend of Increase in the Number of Patients and Days of Hospitalization Due to the Increase in the Number of Sickbeds in Nursing Hospitals", HIRA policy trends, Vol. 7, No. 3, pp. 53-61, 2013.
  6. E. H. Ha. and G. S. Park, "Factors Influencing Cognitive Impairment in Elders with Dementia Living at Home", Journal of Basic Nursing, Vol. 18, No. 3, pp. 317-327, 2011.
  7. M.. S. Lee. and B. S. Lee, "A Conversation Analysis of Communication between Patients with Dementia and Their Professional Nurses", Journal of Korean Academy of Nursing, Vol. 36, No. 7, pp. 1,253-1,264, 2006. https://doi.org/10.4040/jkan.2006.36.7.1253
  8. U. K. Choi, "The Effects of Perceived Medical Service Quality on Patient Satisfaction, Hospital's Reputation and Loyalty", Journal of The Korea Society of Computer and Information, Vol. 25, No. 1, pp 177-185, 2020, DOI: https://doi.org/10.9708/jksci.2020.25.01.177.
  9. J. M. Song and A. R. Park and S. B. Lee, "Trend of Technology in Video Surveillance System", Journal of The Korea Society of Computer and Information, Vol. 25 No. 6, pp. 57-64, 2020, DOI: https://doi.org/10.9708/jksci.2020.25.06.057.
  10. H. Y. Kim, "A Tracking Algorithm to Certain People Using Recognition of Face and Cloth Color and Motion Analysis with Moving Energy in CCTV", Journal of Korean Society of Costume, Vol. 50, No. 2, pp. 81-95, 2000, DOI:10.3745/KIPSTB.2008.15-B.3.197.
  11. H. J. Lee. and S. J. Lee and M. H. Choi and S. Y. Kim and I. Y. Moon, "Fashion Image Searching Website based on Deep Learning Image Classification",Journal of Practical Engineering Education, Vol. 11, No. 2, pp. 175-180, 2019, DOI: 10.14702/JPEE.2019.175.
  12. Matiur Rahman Minar. and Thai Thanh Tuan. and H. J. Ahn, "An Improved VTON(Virtual-Try-On) Algorithm using a Pair of Cloth and Human Image", Journal of Korea Industrial Information Systems Research, Vol. 25, No. 2, pp. 11-18, 2020, DOI: http://dx.doi.org./10.9723/jksiis.2020.25.2.011.
  13. S. M. Lee and S. C. Oh and C. H. Jung and C. I. Kim, "Visual Fashion Analysis Using Deep Learning: A Survey", The Journal of Korean Institute of Communications and Information Science, Vol. 45, No. 7, pp. 1,174-1,182, 2020, DOI: https://doi.org/10.7840/kics.2020.45.7.1174.
  14. Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, "Deep Residual Learning for Image Recognition", In CVPR, 2015, DOI:10.1109/CVPR.2016.90.