The invention discloses an
infrared small target detection method for multi-scale spatio-temporal union filtering under a complex background. The method concretely comprises the following steps: 1, inhibiting a ghost effect, improving the
image identification degree, establishing a multi-scale bilateral time-domain high-pass filtering nonuniformity correction model, and obtaining an
infrared nonuniformity correction image; 2, enhancing the local contrast of a
small target, establishing an image airspace complexity weighted-information
entropy model by adopting the airspace complexity factors of the
infrared nonuniformity correction image, and protruding the information entropy of a
small target region; 3, improving the
detection rate of the infrared small target, reducing the
false alarm rate, establishing a multi-scale spatio-temporal union filtering model, and self-adaptively detecting small targets with different scales. The method is an infrared small target detection
algorithm for multi-scale spatio-temporal union filtering under the complex background, and enriches the detection technology for the small targets with different scales.