Traditional pavement crack detection methods can not cope well with the complexity and diversity of noises in large image area. To solve this problem, we propose a novel unsupervised crack detection approach based on saliency and statistical features. The saliency is initially represented by a conspicuity map built from the intensity rarity and local contrast of image regions. Then spatial continuity of candidate crack pixels is measured based on the statistical features extracted in their neighborhood. This is followed by a Bayesian model to automatically update the saliency map. Finally, cracks are extracted after adaptive saliency map binarization. Experiments show that proposed method has generated consistent results as those by human visual inspection. The results have also proved the effectiveness of the proposed method in suppressing noises compared with several alternative methods.