Preferred vector machine for forest fire detection

Machine learning-based fire detection/recognition is very popular in forest-monitoring systems. However, without considering the prior knowledge, e.g., equal attention on both classes of the fire and non-fire samples, fire miss-detected phenomena frequently appeared in the current methods. In this work, considering model’s interpretability and the limited data for model-training, we propose a novel pixel-precision method, termed as PreVM (Preferred Vector Machine). To guarantee high fire detection rate under precise control, a new L0 norm constraint is introduced to the fire class. Computationally, instead of the traditional L1 re-weighted techniques in L0 norm approximation, this L0 constraint can be converted into linear inequality and incorporated into the process of parameter selection. To further speed up model-training and reduce error warning rate, we also present a kernel-based L1 norm PreVM (L1-PreVM). Theoretically, we firstly prove the existence of dual representation for the general Lp (p≥1) norm regularization problems in RKHS (Reproducing Kernel Hilbert Space). Then, we provide a mathematical evidence for L1 norm kernelization to conquer the case when feature samples do not appear in pairs. The work also includes an extensive experimentation on the real forest fire images and videos. Compared with the-state-of-art methods, the results show that our PreVM is capable of simultaneously achieving higher fire detection rates and lower error warning rates, and L1-PreVM is also superior in real-time detection.