Region of Interest (ROI) extraction is an important component in remote sensing images processing, which is useful for further practical applications such as image compression, image fusion, image segmentation and image registration. Traditional ROI extraction methods are usually prior knowledge-based and depend on a global searching solution which are time consuming and computational complex. Saliency detection which is widely used for ROI extraction from natural scene images in these years can effectively solve the problem of high computation complexity in ROI extraction for remote sensing images as well as retain accuracy. In this paper, a new computational model is proposed to improve the accuracy of ROI extraction in remote sensing images. Considering the characteristics of remote sensing images, we first use lifting wavelet transform based on adaptive direction evaluation (ADE) to obtain multi-scale orientation contrast feature map (MF). Secondly, the features of color are exploited using the information content analysis to provide a color information map (CIM). Thirdly, feature fusion is used to integrate multi-scale orientation contrast features and color information for generating a saliency map. Finally, an adaptive threshold segmentation algorithm is employed to obtain the ROI. Compared with existing models, our method can not only effectively extract detail of the ROIs, but also effectively remove mistaken detection of the inner parts of the ROIs.