The week's pick
Random Articles
Reseach Article
Fire Detection System
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 185 - Number 24 |
| Year of Publication: 2023 |
| Authors: Shridevi Soma, Meghana Suryan, Nandini Jattur, Amruta Rasalkar |
10.5120/ijca2023922993
|
Shridevi Soma, Meghana Suryan, Nandini Jattur, Amruta Rasalkar . Fire Detection System. International Journal of Computer Applications. 185, 24 ( Jul 2023), 22-26. DOI=10.5120/ijca2023922993
Abstract
Fire plays a major role in providing light but it is dangerous as it spreads rapidly. This paper deals with the monitoring of fire using drones and cameras by applying image processing. Image processing is a type of processing in which input images are transformed into another image as output with certain techniques applied to it. The drone camera records the video and the recorded video is uploaded and fire is detected. This is done by using the HAAR cascade classifier algorithm. The HAAR cascade classifier, a popular object detection algorithm, is employed to identify flames in drone footage. OpenCV, a powerful open-source computer vision library, is utilized for image processing and analysis. The captured footage is then processed, and the HAAR classifier is applied to detect fire and smoke regions within the frames. To enhance the system's efficiency, various image processing techniques are implemented, such as image filtering, thresholding, and region of interest (ROI) extraction. Additionally, measures are taken to handle challenges like dynamic lighting conditions and false positive detections. The system generates alerts and notifications whenever a fire is detected, enabling prompt action by authorities or firefighting teams. Once a fire is detected the system could send an alarm and send a notification to the user’s mobile device via GSM.
References
- Punam Patel and Shamik Tiwari (2016) proposed a paper entitled Flame Detection using Image Processing Techniques in the International Journal of Computer Applications Volume 58– No.18.
- Jareerat Seebamrungsat, Suphachai Praising, and Panomkhawn Riyamongkol (2014)proposed a paper entitled Fire Detection in the Buildings Using Image Processing in Third ICT International Journal of IEEE Access in the Department of Electrical and Computer Engineering. Volume 09 issue 5 april 2020 edition.
- Khan Muhammad and Jamil Ahmad (2018) proposed a paper entitled Efficient Deep CNN based fire detection system and localization in video surveillance system at IEEE Transactions on Systems, Man, and Cybernetics System.
- Abdulaziz and Young Im CHO (2018) proposed a paper entitled An Efficient Deep Learning Algorithm for Fire and Smoke Detection with Limited Data in IEEE Explore Advances in Electrical and Computer Engineering.
- Qingjie Zhang, Jiaolong Xu, Liang Xu, and Haifeng Guo ([2016) proposed a paper entitled Deep Convolutional Neural Networks for Forest Fire Detection in International Forum on Management, Education and Information Technology Application by Aviation University of Air Force, Changchun.
- Sebastien Frizzi1, Rabeb Kaabi, Moez Bouchouicha, and Jean-Marc Ginoux (2017) proposed a paper entitled Convolutional Neural Network for Video Fire and Smoke Detection in IEEE Transactions.
- Surapong Surit, Watchara Chatwiriya , “Forest FireSmoke Detection in Video Based on Digital Image Processing Approach with Static and Dynamic Characteristic Analysis”, in IEEE First ACIS/JNUInternational Conference on Computers, Networks, Systems and Industrial Engineering, pp.35-39, 2011.
- P. Piccinini, S. Calderara and R. Cucchiara, “Reliable smoke detection in the domains of image energy and color”, in IEEE International Conference on Image Processing (ICIP), pp. 1376– 1379, October 2008.
- Rafael C. Gonzalez and Richard E. Woods. Digital Image Processing. Pearson publication, Third Edition
- Osman Gunay and Habiboglu proposed a system based on Covariance Descriptors, Color Models, and SVM Classifier. Osman Gunay, A. Enis C ， Etin, Yusuf Hakan, Habiboglu. Flame Detection method in video using Covariance descriptors, IEEE transactions, 1817-1820.
- K. Dimitropoulos, P. Barmpoutis, and N. Grammalidis, "Spatio-temporal flame modeling and dynamic texture analysis for automatic video-based fire detection," IEEE transactions on circuits and systems for video technology, vol. 25, pp. 339- 351, 2015.
- Hamed Adab, Kasturi Devi Kanniah, Karim Solaimani. Modeling forest fire risk in the northeast of Iran using remote sensing and GIS techniques, Springer Science Business Media Dordrecht 2012.
- Akshata Patil, Varsha Bhosale (2014). Survey of Local Binary Pattern for fire & smoke using Wavelet Decomposition. International Journal of Research in Engineering and Technology
- T. Celik, H. Demirel, H. Ozkaramanli, and M. Uyguroglu, "Fire detection using statistical color model in video sequences," Journal of Visual Communication and Image Representation, vol. 18, pp. 176-185, 2007.
- CHENG Caixia, SUN Fuchun, ZHOU Xinquan (2011). One Fire Detection Method Using Neural Networks, Tsinghua Science and Technology, ISSN 1007-0214 05/17 31-35 Volume 16, Number 1.
Index Terms
Keywords