@article{ART002712277},
author={Park Yeonji and Jeong Yoojin and Chae-Bong Sohn},
title={Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling},
journal={Journal of Advances in Military Studies},
issn={2635-5531},
year={2021},
volume={4},
number={1},
pages={43-59},
doi={10.37944/jams.v4i1.78}
TY - JOUR
AU - Park Yeonji
AU - Jeong Yoojin
AU - Chae-Bong Sohn
TI - Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling
JO - Journal of Advances in Military Studies
PY - 2021
VL - 4
IS - 1
PB - Institute of Defense Acquisition Program
SP - 43
EP - 59
SN - 2635-5531
AB - The purpose of this study is to reinforce the defense and security system by recognizing the behaviors of suspicious person both inside and outside the military using deep learning. Surveillance cameras help detect criminals and people who are acting unusual. However, it is inefficient in that the administrator must monitor all the images transmitted from the camera. It incurs a large cost and is vulnerable to human error. Therefore, in this study, we propose a method to find a person who should be watched carefully only with surveillance camera images. For this purpose, the video data of doubtful behaviors were collected. In addition, after applying a algorithm that generalizes different heights and motions for each person in the input images, we trained through a model combining CNN, bidirectional LSTM, and DNN. As a result, the accuracy of the behavior recognition of suspicious behaviors was improved. Therefore, if deep learning is applied to existing surveillance cameras, it is expected that it will be possible to find the dubious person efficiently.
KW - defense and security technology;surveillance camera;suspicious person;behavior recognition;OpenPose
DO - 10.37944/jams.v4i1.78
ER -
Park Yeonji, Jeong Yoojin and Chae-Bong Sohn. (2021). Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling. Journal of Advances in Military Studies, 4(1), 43-59.
Park Yeonji, Jeong Yoojin and Chae-Bong Sohn. 2021, "Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling", Journal of Advances in Military Studies, vol.4, no.1 pp.43-59. Available from: doi:10.37944/jams.v4i1.78
Park Yeonji, Jeong Yoojin, Chae-Bong Sohn "Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling" Journal of Advances in Military Studies 4.1 pp.43-59 (2021) : 43.
Park Yeonji, Jeong Yoojin, Chae-Bong Sohn. Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling. 2021; 4(1), 43-59. Available from: doi:10.37944/jams.v4i1.78
Park Yeonji, Jeong Yoojin and Chae-Bong Sohn. "Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling" Journal of Advances in Military Studies 4, no.1 (2021) : 43-59.doi: 10.37944/jams.v4i1.78
Park Yeonji; Jeong Yoojin; Chae-Bong Sohn. Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling. Journal of Advances in Military Studies, 4(1), 43-59. doi: 10.37944/jams.v4i1.78
Park Yeonji; Jeong Yoojin; Chae-Bong Sohn. Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling. Journal of Advances in Military Studies. 2021; 4(1) 43-59. doi: 10.37944/jams.v4i1.78
Park Yeonji, Jeong Yoojin, Chae-Bong Sohn. Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling. 2021; 4(1), 43-59. Available from: doi:10.37944/jams.v4i1.78
Park Yeonji, Jeong Yoojin and Chae-Bong Sohn. "Suspicious behavior recognition using deep learning: Focusing on keypoint 2D scaling" Journal of Advances in Military Studies 4, no.1 (2021) : 43-59.doi: 10.37944/jams.v4i1.78
1
