Deep spatial-temporal networks for flame detection
- PDF / 2,417,100 Bytes
- 22 Pages / 439.642 x 666.49 pts Page_size
- 20 Downloads / 199 Views
Deep spatial-temporal networks for flame detection Mohammad Shahid1 · I-Feng Chien1 · Wannaporn Sarapugdi1 · Lili Miao1 · Kai-Lung Hua1 Received: 30 April 2020 / Revised: 29 September 2020 / Accepted: 13 October 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Every year, fire accidents cause substantial economic losses and casualties. Being able to detect a fire at the early stage is the only way to avoid notable disasters. Although conventional fire alarm systems (CFAs) that depend on heat and flame sensors are used for a fire safety-catch in our society, they cannot be used effectively for large and open spaces due to performance parameters of the sensors. Recently, most of the state-of-the-art methods for fire detection are evolving based on deep learning (DL) technique. However, it is a difficult task to detect fire from visual scenes due to significant irregularities in the color, size, form, texture and flickering frequency of fire. In the present work, we proposed a two-stage cascaded architecture to improve accuracy. In the first stage, we introduced the Spatio-Temporal network, which efficiently and effectively combines both shape and motion flicker based characteristics to obtain heatmaps of fire regions in the input images. By analyzing the heatmaps with a threshold segmentation method, the candidate of the fire region in the input image can be automatically located. Besides, to minimize false-positive due to some object similar to flame, in the second stage, original image and heatmaps of candidate region are fused for improving abilities of classifier to distinguish whether it is a fire or not. Also, the center loss function is adopted to backpropagate fused features to overcome the impact of intraclass heterogeneity on the representation of features. Furthermore, we tested the proposed method on three different datasets, and the results of our experiments reveal that the proposed method has achieved better performance than the other existing state-of-the-art methods. Keywords Flame detection · Spatial-temporal networks · Deep learning
1 Introduction Fire is one of the common hazards which can suddenly make significant financial and environmental destruction as well as endangering people lives. In 2019, one of the most massive Kai-Lung Hua
[email protected] 1
Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan
Multimedia Tools and Applications
fire disasters in recent world history was in Australia’s New South Wales Province. More than 5.5 million acres of land have been destroyed, as have 2,448 buildings in hundreds of towns and 25 people, including 3 NSW Rural Fire Service volunteers and 3 US firefighters lost their lives. Fire outbreaks in Europe impact 10, 000 km2 of forest areas annually; in Russia and North America, the loss is about 100, 000 km2 . As claimed by the NFPA report in 2018 [9], more than 1.3 million fires have happened in the United States. These caused a loss
Data Loading...
