Translational Motion Compensation of Space Micromotion Targets Using Regression Network

Abstract

The high-speed translational motion of space targets will cause the micro-Doppler to shift, tilt, and fold, which brings great difficulty to the extraction of micromotion features. Translational motion must be compensated in advance to extract the authentic characteristics of micro-Doppler curves. To solve the problem of translational motion compensation, an estimation method of translational parameters based on deep learning theory is proposed. A polynomial model describing translational motion is constructed firstly by analyzing its dynamic principle. Meanwhile, the parametric characterization of micromotion signal is deduced by taking the cone target as an example. On this basis, two regression networks that can estimate acceleration and velocity respectively from the time-frequency graph are built using transfer learning. The translational motion compensation is accomplished with high accuracy and low computation complexity. The proposed method can also achieve satisfactory results in the presence of high intensity noise and discontinuous scattering points. Finally, the effectiveness and robustness of the proposed method are validated by simulations.

Sparse time‐frequency analysis for aircraft target classification with low sampling rate and short observation time

“…Similarly, in ref. [15], an algorithm based on deep learning is designed for the estimation of translational parameters, so that the algorithm is exploited to compensate micro‐Doppler shift in space targets for micro‐Doppler features extraction. In addition to all of this, the micro‐Doppler frequency of the rotating target also can be extracted from high‐resolution range profiles (HRRPs), such as, 16 where the micro‐Doppler frequency is estimated accurately from circular correlation (CC) coefficients and circular average magnitude difference (CAMD) coefficients.…”

Detection and Identification of Low-Slow-Small Rotor Unmanned Aerial Vehicle Using Micro-Doppler Information

“…In (12) , ψ d and the other three parameters in the vector S (see (9)) are unknown fixed value and need to be Then the estimated value of the four parameters could be expressed as…”

“…At present, many scholars have studied the RCS characteristics of "low-slow-small" targets represented by various UAVs. The research is focused on the difference of echo power or RCS characteristics caused by the difference of motion characteristics between UAV main body translation and its rotor rotation for the detection of "low-slow-small" targets [9]. The echo of rotor UAV mainly includes two kinds of components [10]: one is the translational component generated by the motion of UAV itself, which can be modeled by polynomial phase signal (PPS) ; the other is the micro-Doppler component, which is generated by the rotation of rotor, whose echo is a typical sine frequency modulation (SFM) signal.…”