Deep-Learning Based Real-time Fire Detection Using Object Tracking Algorithm (객체 추적 알고리즘을 활용한 딥러닝 기반 실시간 화재 탐지 시스템)

JongHyuk Park (박종혁); Dohyun Park (박도현); Dong-hwan Hyun (현동환); You-min Na (나유민); Soo-Hong Lee (이수홍)

doi:10.9708/jksci.2022.27.01.001

Deep-Learning Based Real-time Fire Detection Using Object Tracking Algorithm

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2022, 27(1), pp.1-8
DOI : 10.9708/jksci.2022.27.01.001
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : November 16, 2021
Accepted : January 17, 2022
Published : January 28, 2022

JongHyuk Park ¹, Dohyun Park ¹, Dong-hwan Hyun ¹, You-min Na ¹, Soo-Hong Lee ¹

¹연세대학교

Accredited

ABSTRACT

In this paper, we propose a fire detection system based on CCTV images using an object tracking technology with YOLOv4 model capable of real-time object detection and a DeepSORT algorithm. The fire detection model was learned from 10800 pieces of learning data and verified through 1,000 separate test sets. Subsequently, the fire detection rate in a single image and fire detection maintenance performance in the image were increased by tracking the detected fire area through the DeepSORT algorithm. It is verified that a fire detection rate for one frame in video data or single image could be detected in real time within 0.1 second. In this paper, our AI fire detection system is more stable and faster than the existing fire accident detection system.

KEYWORDS

Fire Detection, DeepSORT, Tracking Algorithm, Real-time, YOLOv4

Citation status

* References for papers published after 2023 are currently being built.

[other] BOCHKOVSKIY, Alexey / 2020 / Yolov4: Optimal speed and accuracy of object detection

[journal] VEERAMANI, Balaji / 2018 / DeepSort: deep convolutional networks for sorting haploid maize seeds / BMC bioinformatics 19(9) : 1~9

[confproc] FELZENSZWALB, Pedro / 2008 / A discriminatively trained, multiscale, deformable part model / 2008 IEEE conference on computer vision and pattern recognition / Ieee : 1~8

[confproc] XIONG, Huan / 2020 / On the number of linear regions of convolutional neural networks / International Conference on Machine Learning / PMLR : 10514~10523

[confproc] ALBAWI, Saad / 2017 / Understanding of a convolutional neural network / 2017International Conference on Engineering and Technology (ICET) / Ieee : 1~6

[other] WELCH, Greg / 1995 / An introduction to the Kalman filter

[journal] MCLACHLAN, Goeffrey J. / 1999 / Mahalanobis distance / Resonance 4(6) : 20~26

[report] MILLS-TETTEY, G. Ayorkor / 2007 / The dynamic hungarian algorithm for the assignment problem with changing costs / Robotics Institute

[other] MILAN, Anton / 2016 / MOT16: A benchmark for multi-object tracking

[confproc] REZATOFIGHI, Hamid / 2019 / Generalized intersection over union: A metric and a loss for bounding box regression / Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 658~666

[confproc] ZHENG, Liang / 2015 / Scalable person re-identification: A benchmark / Proceedings of the IEEE international conference on computer vision : 1116~1124

[confproc] PANG, Jiahao / 2017 / Cascade residual learning: A two-stage convolutional neural network for stereo matching / Proceedings of the IEEE International Conference on Computer Vision Workshops : 887~895

[journal] SENOUSSAOUI, Mohammed / 2013 / A study of the cosine distance-based mean shift for telephone speech diarization / IEEE/ACM Transactions on Audio, Speech, and Language Processing 22(1) : 217~227

[journal] RONQUIST, Fredrik / 1998 / Three-dimensional cost-matrix optimization and maximum cospeciation / Cladistics 14(2) : 167~172

[journal] 박경민 / 2019 / A Study on Fire Detection in Ship Engine Rooms Using Convolutional Neural Network / 해양환경안전학회지 / 해양환경안전학회 25(4) : 476~481

[journal] 김정수 / 2020 / Development of Fire Detection Model for Underground Utility Facilities Using Deep Learning : Training Data Supplement and Bias Optimization / 한국산학기술학회논문지 / 한국산학기술학회 21(12) : 320~330

[journal] 유시영 / 2021 / A Study on a Video-Based Deep Learning Fusion Algorithm for Fire Detection Systems / 한국통신학회논문지 / 한국통신학회 46(9) : 1487~1496

This paper was written with support from the National Research Foundation of Korea.

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Deep-Learning Based Real-time Fire Detection Using Object Tracking Algorithm

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Deep-Learning Based Real-time Fire Detection Using Object Tracking Algorithm

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (2)

REFERENCES (17) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.