A saliency-based target detection method for forward looking infrared (FLIR) image is proposed. Firstly, saliency map is computed using scale-space representation and separated into dark saliency map (DSM) and bright saliency map (BSM). Secondly, dark and bright regions of interest (ROI) are detected by respective type of saliency map using marker-based maximally stable extremal regions (MSER) detection algorithm. Finally, shape matching algorithm is applied after grouping of the two types of ROI for object detection. Experimental results show that this work provides a promising way to solve the problems caused by salient dark parts of target.