Application of Wavelet Neural Networks to Lidar Signal De-noising
【摘要】：正The Lidar is an efficient tool for remote monitoring, but the effective range is often limited by signal-to-noise ratio. The reason is that noises or fluctuations always strongly affect the measured results. In this paper we present a new method of the signal acquisition by using wavelet neural network (WNN) to de-noise Lidar signals for increasing the effective range of Lidar measurements. And in order to enhance the robustness, the WNN is trained by least trimmed square method, which is famous robust estimator. The performance of the WNN is investigated by detecting the simulating and real signals in white noise. To contrast, the results of Butterworth filter and FIR filter are also demonstrated. Finally, the experiment results show that our approach is superior to the traditional methods.