A Fire Detection Algorithm Based on Tchebichef Moment Invariants and PSO-SVM

Abstract

Automatic fire detection, which can detect and raise the alarm for fire early, is expected to help reduce the loss of life and property as much as possible. Due to its advantages over traditional methods, image processing technology has been applied gradually in fire detection. In this paper, a novel algorithm is proposed to achieve fire image detection, combined with Tchebichef (sometimes referred to as Chebyshev) moment invariants (TMIs) and particle swarm optimization-support vector machine (PSO-SVM). According to the correlation between geometric moments and Tchebichef moments, the translation, rotation, and scaling (TRS) invariants of Tchebichef moments are obtained first. Then, the TMIs of candidate images are calculated to construct feature vectors. To gain the best detection performance, a PSO-SVM model is proposed, where the kernel parameter and penalty factor of support vector machine (SVM) are optimized by particle swarm optimization (PSO). Then, the PSO-SVM model is utilized to identify the fire images. Compared with algorithms based on Hu moment invariants (HMIs) and Zernike moment invariants (ZMIs), the experimental results show that the proposed algorithm can improve the detection accuracy, achieving the highest detection rate of 98.18%. Moreover, it still exhibits the best performance even if the size of the training sample set is small and the images are transformed by TRS.

Visible-Near Infrared Spectroscopy and Chemometric Methods for Wood Density Prediction and Origin/Species Identification

“…The results in our study support their findings (Table 4). However, the parameters of PSO including population size, maximum generation, and number of cross-validation influenced the performance of PSO-SVM models; these parameters were selected by randomized trial or searching many experiments across many studies [47][48][49][50]. Thus, RSM was employed to design the best combined parameters.…”

“…For the preferable optimization results of PSO, the number of initial individuals (population size) and maximum generation should be determined before optimization, the cross-validation number is also critical for the optimization process. Furthermore, these parameters are selected by trial and error or through searching many experiments across a large number of studies [47][48][49][50]. To investigate the relationship between parameters (cross-validation number, maximum generation, and population size) and PSO-SVM model accuracy, the response surface methodology (RSM) with minimum data and resources was employed to design the best combined parameters, and Box-Behnken design with a three-level (lower, equal, and high levels) and a three factor (cross-validation number, maximum generation, and population size) was applied in this study.…”

Forest fire detection on LANDSAT images using support vector machine

“…20 A PSO-SVM model is also given, in which the PSO is applied to optimize the SVM parameters. 15 Thus the proposed algorithm based on Euclidean distance and the SVM-KH model can achieve fire image detection accurately. The effectiveness of the proposed algorithm is also confirmed.…”

“…Step 1: Initialize krill individual and set KH parameters. 15 Generate the initial krill at random, which are composed of the SVM parameters and then, set the particle swarm optimization (PSO) parameters.…”

A Forecast Model of the Number of Containers for Containership Voyage

“…The prediction accuracy of the mixed kernel function SVM is related to the insensitive loss parameter ε, penalty parameter C, polynomial kernel function parameter q, width of the radial basis kernel function σ, and the weight adjustment factor ρ. At present, when the SVM is used for regression fitting prediction, the methods for determining the penalty parameters and kernel parameters mainly include the experimental method [39], grid method [40], ant colony algorithm [41], and particle swarm algorithm [42]. Although the relevant parameters for the experiment can be obtained by a large number of calculations, the efficiency is low and the selected parameters do not necessarily measure up to the global optimum.…”