基于Multilinear PCA的烟雾图像识别算法

为了提高火灾烟雾图像识别正确率,更好地预防火灾,提出一种基于multilinear PCA的火灾烟雾图像识别算法。在提取烟雾疑似区域的基础上,首先分别提取烟雾的静态和动态特征,然后采用multilinear PCA对特征进行融合,消除其中冗余特征,并根据选择特征进行训练样本构造,最后将训练样本输入支持向量机建立烟雾图像分类器,并对测试样本进行识别。仿真结果表明,相对于其他烟雾图像识别算法,提出的算法不仅提高了烟雾图像识别正确率和识别效率,而且具有良好的抗干扰能力,可以满足不同环境下烟雾图像识别要求。

Smoke image detection algorithm based on multi-linear principal component analysis

In order to improve the fire smoke image recognition accuracy and prevent fire, a fire smoke image recognition algorithm based on multiple linear principal component analysis was proposed. Firstly, the static and dynamic features of the smoke suspected area was extracted respectively, and then multiple linear principal component analysis was used to eliminate the redundant features, and training sample was built according to the features, and finally the training samples were input support vector machine (SVM) to build the smoke image classifier, and the test samples were used to identified the performance. Compared to other smoke image recognition algorithm, the simulation results show that our algorithm has improved the recognition efficiency and accuracy recognition of the smoke image, and has good anti-interference ability, and it can meet the requirements of the smoke image recognition under different environment.