Hierarchical detection of wildfire flame video from pixel level to semantic level. Issue 8 (15th May 2015)

• Record Type: Journal Article
• Authors: Zhao, Yaqin; Tang, Guizhong; Xu, Mingming
• Is Part Of: Expert systems with applications. Volume 42:Issue 8(2015)
• Page Start: 4097
• Page End: 4104
• Publication Date: 2015-05-15
• Subjects: Hierarchical detection -- Wildfire flame video detection -- Sparse representation -- Mathematical model of meaning; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2015.01.018
• Languages: English
• ISSNs: 0957-4174

Abstract

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. Abstract: The importance of flame detection cannot be ignored in a wildfire video surveillance system due to disturbance of heavy fog and challenging of smoke detection. In this paper a novel method for hierarchical detection of wildfire flame video is presented. Specifically, wildfire flame images are gradually recognized from low level visual features of pixel based to high level semantics of video clip based. For all the pixels of one image, the pixels which meet color rules and motion characteristics are labeled as flame colored pixels. The candidate flame region roughly generated by flame-like pixels is divided into non-overlapped image blocks. The sparse representation of the blocks are defined and recognized by learned dictionaries to more accurately segment candidate flame region and exclude some non-flame regions. To reduce the cost of computation, the proposed method detects one F rate ( F rate denotes one frame rate) frames instead of one frame at a time by using a sliding time window. Flicker features and spatiotemporal features extracted from video clips of the size F rate are used to build semantic model of wildfire flame video recognition based on mathematical model of meaning. Experimental results show that the proposed approach can effectively segment flame region and significantly improve the performance of wildfire flame detection.