The invention relates to a sparse coding and visual saliency-based method for detecting an airport through an infrared remote sensing image. The method comprises the following steps of: firstly, down-sampling an original remote sensing image, linearly detecting the down-sampled remote sensing image via using an LSD (Least Significant Difference) algorithm, calculating the saliency of the image via using an FT algorithm; then detecting the airport by utilizing a sliding window target detector, judging whether a linear section exists in the sliding window, if not, sliding the window continuously, if so, carrying out the sparse coding on the window by utilizing a dictionary constructed by an airport target image of the remote sensing image, and screening sparse codes in a way of combining the sparse codes with salient values of the window, so as to obtain sparse expression characteristics of the window; finally, discriminating the sparse code characteristics of the sliding window via an SVM (Support Vector Machine) binary classifier, judging whether the airport exists in the window, and realizing the detection of an airport target ultimately. Compared with other invented technologies, the method has the advantages of high airport detection accuracy and low false alarm rate.