Smoke detection method based on support vector machine and device

Abstract

The invention provides a smoke detection method based on a support vector machine. The method comprises the following steps of: (101) establishing background images: partitioning a continuous frame image into W*H blocks and then establishing background image for each subblock; (102) acquiring a foreground detection area; (103) calculating the characteristics of the foreground detection area; and (104) recognizing smoke areas according to the characteristics by adopting the support vector machine. The invention also provides a smoke detection device based on the support vector machine. The smoke detection method and the device based on the support vector machine can effectively detect smoke which slowly changes so as to solve the practical problem of recognition difficulty of smoke slowly changed in large indoor scenes, such as warehouses, large laboratories, and the like.

Description

technical field [0001] The invention relates to a smoke detection method, in particular to a smoke detection method based on a support vector machine. Background technique [0002] According to the law of fire occurrence, the appearance of fire smoke is earlier than that of open flame, so smoke detection technology is widely used in early warning of fire. Among smoke detection technologies, video-based smoke detection has become a research hotspot due to its advantages of non-contact and low cost. [0003] US patent application US 2007 / 0019071A1 discloses a smoke detection method that uses background estimation to extract smoke regions in an image. The Chinese patent application with publication number CN101059435A discloses a forest fire smoke detection method based on color CCD image analysis. The method uses wavelet analysis and multi-feature fusion algorithm to detect smoke on the image. The above smoke detection methods all simply use background segmentation without c...

AI Technical Summary

Problems solved by technology

The above smoke detection methods are all for dynamic smoke detection, and cannot effectively detect slowly changing smoke

Therefore, in large indoor scenes such as warehouses and large laboratories, slowly changing smoke cannot be effectively detected, and false positives are prone to occur.

Images