Abstract
Video flame and smoke-based fire detection usually exhibit large variations in the feature of color, texture, shapes, etc., caused by the complex environment. It is difficult to develop a robust method to detect fire based on single or multiple fire features. Since convolutional neural network (CNN) has reported state-of-the-art performance in a wide range of fields. This study present a method based on SLIC-DBSCAN and convolutional neural network to recognize flame and smoke modes connected to fire stages. First, simple linear iterative clustering (SLIC) is acted as the pre-processing step to over segment images into super-pixels. Then the use of density based spatial clustering of application with noise (DBSCAN) gathered the similar super-pixels into several clusters, which in turn provide better smoke detection accuracy by using CNN. Comparison studies are performed to base on smoke image from publicly available data and self-collected data. The experimental results demonstrated the improved smoke detection capabilities by the present method.
Highlights
Fire in living environment will lead to life, property and economic losses
AUTOMATIC SMOKE DETECTION METHOD In light of the strong feature learning ability of convolutional neural network (CNN), this paper proposed a simple linear iterative clustering (SLIC)- DBSCAN based CNN to automatically detect smokes using images with complex backgrounds
Unlike many other image segmentation methods work with gray scale image that may loss some useful information of the color image, SLIC-DBSCAN could directly cluster sub-images from the color image
Summary
Fire in living environment will lead to life, property and economic losses. Generally, forest fires, civil infrastructure and industrial fires are the main fire losses to take several decades to repair. [36] proposed a video-based smoke detection technique by the combination of Kalman estimator, color analysis, image segmentation, blob labeling, geometrical features analysis, and M of N decisor for early warning in ant-fire surveillance systems. A novel smoke detection method is proposed by integrating SLIC-DBSCAN with convolutional neural networks, which consists of the complex background interference splitter and a robust smoke feature extractor. AUTOMATIC SMOKE DETECTION METHOD In light of the strong feature learning ability of CNN, this paper proposed a SLIC- DBSCAN based CNN to automatically detect smokes using images with complex backgrounds. Step 3: The collected raw images combined with CIELAB color space are segmented using SLIC to generating super-pixel images with spectral feature of smoke areas. Step 6: The testing sample set (images waiting for detection) is treated as unknown images to recognize smoke/fire and non-smoke images
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
