Unexpected fall remains the major threat for elderly since it can cause severe consequences. In this paper, an automatic human fall detection approach is proposed using RGB-Depth (RGBD) cameras. Based on the skeleton and joints data, three velocity features and a head-hip height difference feature are extracted within each sliding window. The features are then gradually analyzed and compared to adaptive thresholds by the proposed multi-step fall detection method. We also conducted a series evaluation on the determination of thresholds and the whole approach. The experiments show a good result with a high F1-measure of 0.944.