Fire Detection Based on Image Learning by Collaborating CNN-SVM with Enhanced Recall
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensingmethod for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step,fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with differentparameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increasedthe recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. Thisis a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In ourexperiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.
Abstract
Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensingmethod for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step,fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with differentparameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increasedthe recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. Thisis a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In ourexperiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.
참고문헌 (13)
- S. Geetha, "Machine vision based fire detection techniques : A survey", Fire Technol., 57(2), pp.591~623 (2021)
- F. Bu, "Intelligent and vision-based fire detection systems : A survey", Image Vis. Comput., 91, pp.103803~ (2019)
- X. Hao, "Video flame detection using convolutional neural networks", Proc. IEEE 4th Int. Conf. on Image, Vision and Comput. (ICIVC), pp.539~543 (2019)
- Z. Zhong, "A convolutional neural network-based flame detection method in video sequence", Signal Image Video Process., 12, pp.1619~1627 (2018)
- M. Balipa, "Arecanut disease detection using CNN and SVM algorithms", Proc. Int. Conf. on Artif. Intell. and Data Eng. (AIDE), pp.01~04 (2022)
- K. Myagila, "A comparative study on performance of SVM and CNN in Tanzania sign language translation using image recognition", Appl. Artif. Intell., 36(1), pp.e2005297(1)~e2005297(16) (2022)
- C. M. Bishop, "Pattern Recognition, and Machine Learning" (2006), Springer
- A. Hertzmann, "Machine Learning and Data Mining Lecture Notes", Dept. of Computer and Mathematical Sciences, Univ. of Toronto, ~ (2015)
- P. Kumar, "Classification of imbalanced data: Review of methods and applications", IOP Conf. Ser. Mater. Sci. Eng., 1099(1), pp.012077(1)~012077(9) (2021)
- A. M. Fernandes, "Automatic early detection of wildfire smoke with visible-light cameras and EfficientDet", J. Fire Sci., 41(4), pp.122~135 (2023)