Handheld Laser Rangefinder-Based Location Estimation via Regularity of Fractionally Integrated Signals

This paper proposes to estimate the location of an object via computing the regularity of the fractionally integrated signals. The features are extracted from the regularity and the random forest is employed for performing the regression. More precisely, the acquired signal is first denoised via a linear phase filter. Second, the fractional ordered integration of the denoised signal is computed. Here, the fractional orders are chosen as 0.4 and 0.5. Then, the regularity of the fractionally integrated signal is computed. Next, the features related to the location of the objects are extracted. Finally, the random forest is employed for estimating the location of the objects. The computer numerical simulation results indicate that the relative errors of our proposed method are 0.0029, 0.0125 and 0.0125 when the target is placed at distances of 3001m to 3500m, 3501m to 4000m as well as 4001m to 4500m from the acquisition device, respectively. In addition, other indicators such as the Pearson correlation coefficient (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\rho $ </tex-math></inline-formula>), the mean absolute relative distortion (MARD), the mean absolute error (MAE), the mean squares error (MSE) and the root MSE (RMSE) yielded by our proposed method are superior to those of existing methods. This demonstrates the effectiveness of our proposed method.