Video smoke detection is a promising fire detection method especially in open or lager spaces and outdoor environments. However, there is still room for improvement of the recognition rate. In recent years, great success in the field of image recognition has been achieved by deep learning, which relies on large scale training data. Unfortunately, due to the occasionality of fire accidents, it is difficult and expensive to obtain a large number of fire smoke video samples used to train the deep neural networks.

Our completed work and in progress work will be presented in this poster accepted by 12th IAFSS symposium. The Symposium will be held on June 12-16,2017 at Lund University, Sweden.

In this paper, a deep domain adaptation based method for video smoke detection is proposed to extract a powerful feature representation of smoke. Due to the smoke image samples limited in scale and diversity for deep CNN training, we systematically produced adequate synthetic smoke images with a wide variation in the smoke shape, background and lighting conditions. Considering that the appearance gap (dataset bias) between synthetic and real smoke images degrades significantly the performance of the trained model on the test set composed fully of real images, we build deep architectures based on domain adaptation to confuse the distributions of features extracted from synthetic and real smoke images. This approach expands the domain-invariant feature space for smoke image samples. With their approximate feature distribution off non-smoke images, the recognition rate of the trained model is improved significantly compared to the model trained directly on mixed dataset of synthetic and real images. Experimentally, several deep architectures with different design choices are applied to the smoke detector. The ultimate framework can get a satisfactory result on the test set. We believe that our approach is a start in the direction of utilizing deep neural networks enhanced with synthetic smoke images for video smoke detection.

In this paper, a video based smoke detection method using dynamic texture feature extraction with volume local binary patterns is studied. Block based method was used to distinguish smoke frames in high definition videos obtained by experiments firstly. Then we propose a method that directly extracts dynamic texture features based on irregular motion regions to reduce adverse impacts of block size and motion area ratio threshold. Several general volume local binary patterns were used to extract dynamic texture, including LBPTOP, VLBP, CLBPTOP and CVLBP, to study the effect of the number of sample points, frame interval and modes of the operator on smoke detection. Support vector machine was used as the classifier for dynamic texture features. The results show that dynamic texture is a reliable clue for video based smoke detection. It is generally conducive to reducing the false alarm rate by increasing the dimension of the feature vector. However, it does not always contribute to the improvement of the detection rate. Additionally, it is found that the feature computing time is not directly related to the vector dimension in our experiments, which is important for the realization of real-time detection.

The research is financially supported by the Anhui Provincial Key R&D Program (1704a0902030) and the Fundamental Research Funds for the Central Universities (WK6030000029).

The research is aimed to design a video fire detection system based on simultaneously processing of thermal infrared and visible images.