Smog detecting method and apparatus

Abstract

The invention provides a method and a device for detecting smog. The method comprises the following steps: a plurality of images are captured, if a moving object appears in at least one image, the image with the moving object therein is determined to be the image to be analyzed; a chroma change of the image to be analyzed is analyzed, and at least one of an edge ambiguity and a flicker frequency of the image to be analyzed is analyzed; at least one analysis result of the steps and a preset characteristic are compared, if at least one analysis result accords with the preset characteristic, the moving objected is judged to be smog.

Description

technical field [0001] The present invention relates to a method and device for detecting smoke, and more particularly, to a method and device for detecting smoke using image analysis. Background technique [0002] In many fires, smoke occurs first, and even in some fire situations, such as smoldering, the combustion of substances only produces smoke but not flames. Therefore, smoke detection can be said to be one of fire prevention and fire rescue. A very important topic, the use of smoke detection systems can notify the fire when it first occurs, and carry out early fire fighting actions to greatly reduce the loss of life and property. [0003] Generally, traditional smoke detection devices, such as photoelectric smoke detectors, air sampling smoke detectors, etc., use the physical characteristics derived from the increase of smoke particles as the basis for fire judgment. If there are smoke particles in the air, it will scatter the light and cause the change of brightnes...

AI Technical Summary

Problems solved by technology

[0003] Generally, traditional smoke detection devices, such as photoelectric smoke detectors, air sampling smoke detectors, etc., use the physical characteristics derived from the increase of smoke particles as the basis for fire judgment. Among them, the photoelectric smoke detector uses the emitted light source, If there are smoke particles in the air, they will scatter the light and cause the light to change, thereby detecting the occurrence of a fire. However, due to the limitation of the emission of the light source, the smoke detector set up in this way must have a limited detection range. , the detection effect for a large-scale space is bound to be insufficient; another type of air sampling smoke detector is to use the air distributed in the detection space to sample, and then analyze the sampled air composition to determine the occurrence of a fire , the sensor used in this kind of air sampling smoke detector itself is relatively expensive, and in order to sample air, it must be connected through pipes to facilitate detection

[0004] Therefore, the use of traditional sensors to detect smoke has the following disadvantages: 1. For spaces with high floors and large areas, such as factories, gymnasiums, shopping centers, etc., it is not easy to detect smoke and miss the golden period of early rescue; 2. It is impossible to accurately judge whether the smoke is related to the fire, resulting in misjudgment, resulting in a high false alarm rate (false alarms); 3. It is necessary to install a large number of smoke detectors, pipelines and central control systems, thus increasing the cost of the building

However, the above-mentioned patent document does not mention the accuracy of its detection method and device, nor does it apply other condition parameters and analysis techniques, such as chromaticity change analysis

Images