Target identification method in smoke environment

The invention belongs to the technical field of target detection and identification, and discloses a method for identifying a target in a smoke environment, which comprises the following steps of: collecting a multi-echo waveform superposed by a detection target in the smoke environment; the multi-echo waveform comprises an echo waveform formed by overlapping smoke dust and a detection target; full waveform decomposition is carried out on the collected multi-echo waveform, the echo waveform of the smoke and the echo waveform of the detection target are calculated, and amplitude parameters of the waveforms are extracted from the echo waveforms; extracting polarization information of the smoke and the detection target according to the amplitude parameter of the extracted waveform; and carrying out machine learning by taking the polarization information as a feature, and identifying a detection target and smoke dust. The method has the beneficial effect that the target in the smoke environment can be accurately