Low illumination smog video detection method based on image correlation

Abstract

The invention provides a low illumination smog video detection method based on image correlation; the method comprises the following steps: compressing a recorded video image and converting into a gray scale image, and carrying out four-frame difference operation on the obtained gray scale image, thus extracting a motion object in the video image; selecting a property threshold to convert the interframe difference result into a binary image; carrying out median filtering on the obtained binary image, thus initially reducing image noises; calculating interframe correlation of various connecting zones of the binary image in order, removing non-smog motion areas with small image correlation, and obtaining an accurate smog area image. The method can directly observe the smog developing conditions, thus removing temperature, humidity, air pressure and smell factor influences, improving the smog detection accuracy, and keeping the false alarm rate within 10% under conservative estimation; in addition, the method can replay an extracted smog area developing process, thus accurately positioning the smog source position.

Description

technical field [0001] The invention relates to the field of smoke detection, in particular to a video smoke detection method using a camera with an infrared auxiliary light source under low illumination. Background technique [0002] Video-based fire smoke detection technology has the advantages of being intuitive, fast and reliable, and can meet the needs of early fire detection, and has become a research hotspot in the field of fire detection. Over the years, researchers at home and abroad have proposed many effective smoke detection methods, but these methods are mainly aimed at conditions with sufficient light. The research on smoke detection methods in confined spaces or low-light environments such as night is not enough, but the practical application is very good. need. For example, the commonly used cargo compartment smoke detection system for aircraft currently uses light-scattering smoke detectors. This type of detector is easily affected by factors such as humidi...

AI Technical Summary

Problems solved by technology

Over the years, researchers at home and abroad have proposed many effective smoke detection methods, but these methods are mainly aimed at conditions with sufficient light. The research on smoke detection methods in confined spaces or low-light environments such as night is not enough, but the practical application is very good. need

For example, the cargo compartment smoke detection system commonly used in aircraft currently uses light scattering smoke detectors, which are easily affected by factors such as humidity, dust, strong odors, and oil particles, and have a high false alarm rate.

When receiving a smoke alarm in the cargo compartment, the crew lacks effective means to identify and verify the authenticity of the alarm, which often leads to the return of the aircraft and alternate landing, which increases operating costs and even threatens flight safety

Images