文献类型：期刊文献

英文题名：Preferred vector machine for forest fire detection

作者：Yang, Xubing[1] Hua, Zhichun[1] Zhang, Li[1] Fan, Xijian[1] Zhang, Fuquan[1] Ye, Qiaolin[2] Fu, Liyong[3]

第一作者：Yang, Xubing

通信作者：Yang, XB[1];Fu, LY[2]

机构：[1]Nanjing Forestry Univ, Coll Informat Sci & Technol, Nanjing 210037, Peoples R China;[2]Nanjing Forestry Univ, Coll Informat Sci & Technol, Coinnovat Ctr Sustainable Forestry Southern China, Key Lab Tree Genet & Biotechnol,Educ Dept China,St, Nanjing 210037, Peoples R China;[3]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China

年份：2023

卷号：143

外文期刊名：PATTERN RECOGNITION

收录：;EI(收录号：20232714342274);Scopus(收录号：2-s2.0-85163704202);WOS:【SCI-EXPANDED(收录号:WOS:001024530900001)】；

基金：This research was supported in part by Fundamental Research Funds for the Central Non-profit Research Institution of CAF under Grant. CAFYBB2022ZB002, and in part by the National Science Foundation of China under Grant 62072246 .

语种：英文

外文关键词：Forest fire detection; Fire detection rate; Error warning rate; SVM; Dual representation

摘要：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 L 0 norm constraint is introduced to the fire class. Computationally, instead of the traditional L 1 re-weighted techniques in L 0 norm approximation, this L 0 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 L 1 norm PreVM ( L 1 -PreVM). Theoretically, we firstly prove the existence of dual representation for the general L p ( p & GE;1) norm regularization problems in RKHS (Reproducing Kernel Hilbert Space). Then, we provide a mathematical evidence for L 1 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 L 1 -PreVM is also superior in real-time detection. & COPY; 2023 Elsevier Ltd. All rights reserved.