Abstract: Cumulative Wigner-Hough Transform (CWHT) is proposed for parameter estimation of Linear Frequency Modulation Continuous Wave (LFMCW) signal according to the periodic characteristic of LFMCW signal. Firstly, the characteristic of autocorrelation function is analyzed and the modulated period of LFMCW signal is estimated by searching the peaks of autocorrelation function. Then, the LFMCW signal is segmented in several parts based on the modulated period in order to have CWHT. By searching the peak of CWHT and beginning time, the chirp rate and initial frequency of LFMCW signal are estimated eventually. The Signal-to-Noise Ratio (SNR) formula of CWHT is derived theoretically and related calculations about CWHT are analyzed. Not only does the proposed algorithm reduce the impact of time-frequency cross term, but also has low computational complexity. At the same time, the algorithm can get noncoherent integration in several periods, that improves the ability of immunity to noise. The results of simulation verify that the proposed algorithm has a good performance of parameter estimation at a low SNR.