A Flame Detection Algorithm Based on Bag-of-Features In The YUV Color Space

Computer vision-based fire detection involves flame detection and smoke detection. This paper proposes a new flame detection algorithm, which is based on a Bag-of-Features technique in the YUV color space. Inspired by that the color of flame in image and video will fall in certain regions in the color space, models of flame pixels and non-flame pixels are established based on code book in the training phase in our proposal. In the testing phase, the input image is split into some NxN blocks and each block is classified respectively. In each NxN block, the pixels values in the YUV color space are extracted as features, just as in the training phase. According to the experimental results, our proposed method can reduce the number of false alarms greatly compared with an alternative algorithm, while it also ensures the accurate classification of positive samples. The classification performance of our proposed method is better than that of alternative algorithms.