Detection of smoke from infrared image frames in the aircraft cargoes

Li Deng,Xiubao Sui,Yuanhua He,Qin Wang,Qian Chen

doi:10.1177/15501477211009808

Abstract

The existing equipment of civil aircraft cargo fire detection mainly uses photoelectric smoke detectors, which has a high false alarm rate. According to Federal Aviation Agency’s statistics, the false alarm rate is as high as 99%. Since, in the cargo of civil aircraft, visible image processing technology cannot be used to detect smoke in the event of a fire due to the closed dark environment, a novel smoke detection method using infrared image processing technology is presented. Experiments were conducted under different environment pressures in the full-size cargo of civil aircraft. The results show that the proposed method can effectively detect smoke at the early stage of fire which is applicable for fire detection in civil aircraft cargoes.

Highlights

Cargo fire detection is an important guarantee for the flight safety of civil aircraft
Given 3000 infrared smoke image blocks and 2000 non-smoke image blocks in the aircraft cargo environment, the discriminate power of the proposed smoke detection method was studied
The results show that the proposed method achieves the best false alarm rate performance at low atmospheric pressures which is the evidence for using variable pressure environment of aircraft cargoes

Summary

Introduction

Cargo fire detection is an important guarantee for the flight safety of civil aircraft. Over-complete dictionaries[11] are used to achieve the sparse representations of smoke component and non-smoke component in one block of the frame which leads to a convex optimization problem To solve this problem, dictionaries learning process for infrared smoke image frames is conducted in an enclosed air cargo under different pressure conditions and trained with real samples to accommodate different image content. The optimal results can be obtained while the difference of the two consecutive iterations is less than a predefined threshold Since both sparse coefficient vectors contain the information of whether the block f has smoke or not, the extracted feature[12,14] from them is bundled together and input into the support vector machine (SVM) classifier.

Experimental results

Method

Conclusion