Hierarchical detection of wildfire flame video from pixel level to semantic level

作者：

Highlights：

• Propose a flame region detection method using sparse representation of flame block.

• Establish a flame recognition model of based on mathematical model of meaning.

• Identify flame video from low-level visual features to high-level semantics.

• Validate higher accuracy of the proposed method with comparable computational time.

摘要

•Propose a flame region detection method using sparse representation of flame block.•Establish a flame recognition model of based on mathematical model of meaning.•Identify flame video from low-level visual features to high-level semantics.•Validate higher accuracy of the proposed method with comparable computational time.

论文关键词：Hierarchical detection,Wildfire flame video detection,Sparse representation,Mathematical model of meaning

论文评审过程：Available online 17 January 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.01.018