Wavelet based outlier correction for power controlled turning point detection in surveillance systems

► We present a power controlled turning point detection method in surveillance. ► This method is based on the theory of the likelihood ratio test. ► We next show how the outliers will influence the detecting performance. ► We present a wavelet multiresolution (MRA) approach to correct the outlier problem. ► It is on-line correcting and can alleviate the false alarm problem from outliers.