Extracting Foreground Based on Codebook for Early Forest Smoke Video
Dong Mei Wu, Xin Zhou · Advanced materials research · 2014
Shaking leaves has been the biggest interference for early forest smoke video detection. Moving average method, Gaussian mixture method and its improved methods are often used to update background, but the performance is not good through background subtraction. Codebook algorithm is applied to extract foreground for early forest smoke detection, quantization techniques are used to obtain background model from time series, then getting foreground image through background subtraction. Through multiple video tests, the experimental results that the filtering performance, anti-noise performance and accuracy are better than other methods above.