Millimeter wave image strong noise spatial domain elimination method

The invention discloses a millimeter wave image strong noise spatial domain elimination method, which comprises the following steps of: firstly, preprocessing a millimeter wave image, and performing binary segmentation on the millimeter wave image by using an OTSU method to obtain a binary mask without a weak noise region; and determining a strong noise space domain range, calculating the maximum circumscribed rectangle of the strong noise connected domain, and obtaining the specific coordinate value of the maximum circumscribed rectangle of each strong noise connected domain in the binary mask. And finally, eliminating all strong noise connected domains in the binary mask. Aiming at the problem of serious false alarm caused by the serious influence of the strong noise of the human body millimeter wave image, especially the strong noise between two legs on the detection, the noise can be effectively removed and the false alarm rate can be reduced according to the structural characteristics of the human body m