Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Disaster warning system using Convolutional Neural Network - Focused on intelligent CCTV

  • Choi, SeungHyeon (Dept. of Computer and Communications Engineering, Kangwon National University) ;
  • Kim, DoHyeon (Dept. of Computer and Communications Engineering, Kangwon National University) ;
  • Kim, HyungHeon (INNODEP INC) ;
  • Kim, Yoon (Dept. of Computer and Communications Engineering, Kangwon National University)
  • Received : 2019.01.08
  • Accepted : 2019.02.08
  • Published : 2019.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an intelligent CCTV technology which is applied to a recent attracted attention real-time object detection technology in a disaster alarm system. Natural disasters are rapidly increasing due to climate change (global warming). Various disaster alarm systems have been developed and operated to solve this problem. In this paper, we detect object through Neuron Network algorithm and test the difference from existing SVM classifier. Experimental results show that the proposed algorithm overcomes the limitations of existing object detection techniques and achieves higher detection performance by about 15%.

Keywords

CPTSCQ_2019_v24n2_25_f0001.png 이미지

Fig. 1. water play safety system(Korea Coast Guard)

CPTSCQ_2019_v24n2_25_f0002.png 이미지

Fig. 2. climber safety system (National Disaster Management Research Institute)

CPTSCQ_2019_v24n2_25_f0003.png 이미지

Fig. 3. KISA intelligent certification process

CPTSCQ_2019_v24n2_25_f0004.png 이미지

Fig. 4. Common Object Detection Algorithm Flowchart

CPTSCQ_2019_v24n2_25_f0005.png 이미지

Fig. 5. HOG Algorithm

CPTSCQ_2019_v24n2_25_f0006.png 이미지

Fig. 6. Proposal Algorithm Flowchart

CPTSCQ_2019_v24n2_25_f0007.png 이미지

Fig. 7. YOLO v2 Network

CPTSCQ_2019_v24n2_25_f0008.png 이미지

Fig. 8. Clustering box dimensions on VOC and COCO

CPTSCQ_2019_v24n2_25_f0009.png 이미지

Fig. 9. Sutherland Hodgman Polygon Clipping

CPTSCQ_2019_v24n2_25_f0010.png 이미지

Fig. 10. Test Level-1 results (KISA Event)

CPTSCQ_2019_v24n2_25_f0011.png 이미지

Fig. 11. First event detection cumulative graph

CPTSCQ_2019_v24n2_25_f0012.png 이미지

Fig. 12. GT detection rate (all test algorithm)

CPTSCQ_2019_v24n2_25_f0013.png 이미지

Fig. 13. Test Level-2 results (GT)

CPTSCQ_2019_v24n2_25_f0014.png 이미지

Fig. 14. IoU Comparison by Test Algorithm 1, 2

Table 1. KISA Intelligent Authentication Evaluation Method and Criteria (Intrusion)

CPTSCQ_2019_v24n2_25_t0001.png 이미지

Table 2. Darknet 19

CPTSCQ_2019_v24n2_25_t0002.png 이미지

Table 3. Detection frameworks on PASCAL VOC 2007

CPTSCQ_2019_v24n2_25_t0003.png 이미지

Table 4. Test Dataset

CPTSCQ_2019_v24n2_25_t0004.png 이미지

Table 5. Test environment

CPTSCQ_2019_v24n2_25_t0005.png 이미지

Table 6. Test Video

CPTSCQ_2019_v24n2_25_t0006.png 이미지

Table 7. Test Level-1 (KISA Event)

CPTSCQ_2019_v24n2_25_t0007.png 이미지

Table 8. Test Level-2 (GT Event)

CPTSCQ_2019_v24n2_25_t0008.png 이미지

Table 9. Test Level-3 (IoU)

CPTSCQ_2019_v24n2_25_t0009.png 이미지

References

  1. Tetra port goes 'Access control', http://www.knn.co.kr/163726.
  2. Park Young Jin, Cho Myeong Heum, Lee Jun Woo, "Development of automatic water level detection alarm system using intelligent CCTV," Korean Society Of Hazard Mitigation Academic Publications, pp. 66-66, 2013.
  3. JungSub Oh, DoHyeon Kim, Yoon Kim, "Loitering and Intrusion Detection Algorithms using Neuron Network," Korean Institute of Information Scientists and Engineers Academic Publications, Vol 2017.12, pp. 2142-2144, 2017.
  4. J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," Computer Vision and Pattern Recognition, arXiv:1612.08242, Dec. 2016.
  5. C. Burges, "A tutorial on support vector machines for pattern recognition. Knowledge Discovery and Data Mining," Vol. 2, Issue 2, pp.121-167, 1998. https://doi.org/10.1023/A:1009715923555
  6. Rappaport. A, "An efficient algorithm for line and polygon clipping," The Visual Computer, Vol. 7, pp. 19-28, Jan. 1991. https://doi.org/10.1007/BF01994114
  7. Sehyuck Wi, Donghyun Kim, Jingchun Piao, Hyunchul Shin, "Night-time Pedestrain Detection Techniques by Using HoG," Korean Institute of Information Scientists and Engineers Academic Publications, Vol. 2014.6, pp. 1797-1799, 2014
  8. N. Dalaland B. Trigg, "Histograms of Oriented Gradients for Human Detection," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp.886-893, 2005.
  9. YuJung Choi, Yoon Kim, "Object Detecting and Tracking Algorithm In The Environment of Complex Beach,"Korean Institute of Information Scientists and Engineers Academic Publications, Vol. 2016, No. 12, pp. 1123-1125, Dec. 2016.
  10. Korea Internet&Security Agency, "Intelligent CCTV Solution Performance Test and Certification Guide," pp. 30, Jan. 2018.
  11. Dasol Hong, Yoon Kim, "Efficient Swimmer Detection Algorithm using CNN-based SVM,"Journal of The Korea Society of Computer and Information, Vol. 22 No. 12, pp. 79-85, Dec. 2017. https://doi.org/10.9708/JKSCI.2017.22.12.079
  12. Jong-Hak Lee, Koo-Rack Park, Dong-Hyun Kim, Yun-Yeol Lee, "Intelligent Monitoring Systems for CCTV for Crime Prevention," The Korea Society of Computer and Information Academic Publications, Vol. 24(2), pp. 105-106, Jun. 2016.
  13. Seung-Hwan Bang, Hyun-Bo Cho, "Learning Method for Real-time Crime Prediction Model Utilizing CCTV," Journal of The Korea Society of Computer and Information, Vol. 21 No. 5, pp. 91-98, May. 2016. https://doi.org/10.9708/jksci.2016.21.5.091
  14. Korea Defense Industry Association, "Defense Technology,"Vol. 468, pp. 17-18, Feb. 2018.
  15. Taewoo Kim, Doyoung Kim, Hyungheon Kim, Pyunggang Kim, "The Design of Intelligent CCTV Video Analytics System utilizing Appearance and Disappearance Points of Objects for False Alarm Mitigation," The Korean Institute of Information Scientists and Engineers Academic Publications, Vol. 2015.06, pp. 769-771, Jun. 2015.