Deep Convolutional Generative Adversarial Networks Based Flame Detection in Video
This work addresses flame detection for video surveillance systems, offering an incremental improvement by incorporating temporal information into existing DCGAN-based methods.
The paper tackles the problem of real-time flame detection in video surveillance by proposing a two-stage training method using Deep Convolutional Generative Adversarial Networks (DCGANs) that exploit spatio-temporal flame evolution, resulting in effective flame detection with negligible false positive rates in real-time.
Real-time flame detection is crucial in video based surveillance systems. We propose a vision-based method to detect flames using Deep Convolutional Generative Adversarial Neural Networks (DCGANs). Many existing supervised learning approaches using convolutional neural networks do not take temporal information into account and require substantial amount of labeled data. In order to have a robust representation of sequences with and without flame, we propose a two-stage training of a DCGAN exploiting spatio-temporal flame evolution. Our training framework includes the regular training of a DCGAN with real spatio-temporal images, namely, temporal slice images, and noise vectors, and training the discriminator separately using the temporal flame images without the generator. Experimental results show that the proposed method effectively detects flame in video with negligible false positive rates in real-time.