Non-Linear Dimensionality Reduction and Gaussian Process Based Classification Method for Smoke Detection

Non-Linear Dimensionality Reduction and Gaussian Process Based Classification Method for Smoke Detection

To improve smoke detection accuracy, we combine local binary pattern (LBP) like features, kernel principal component analysis (KPCA), and Gaussian process regression (GPR) to propose a novel data processing pipeline for smoke detection. The data processing pipeline consists of three steps including...

Full description

Bibliographic Details
Main Authors: Feiniu Yuan, Xue Xia, Jinting Shi, Hongdi Li, Gang Li
Format: Article
Language:English
Published: IEEE 2017-01-01
Series:IEEE Access
Subjects:
Smoke detection
kernel principal component analysis (KPCA)
gaussian process regression (GPR)
classification pipeline
Online Access:https://ieeexplore.ieee.org/document/7911197/

Similar Items

Similar Items