An improved FAST feature extraction based on RANSAC method of vision/SINS integrated navigation system in GNSS-denied environments

Abstract

Although Strapdown Inertial Navigation System (SINS) and Global Navigation Satellite System (GNSS) integrated navigation system has been widely used in modern kinematic positioning and navigation due to its numerous advantages, the GNSS signal is easily disturbed or blocked by the surroundings, which will reduce the system accuracy significantly. So some other alternated aiding techniques should be studied on. With the rapid development of the digital imaging sensors and computer techniques, the vision/SINS integrated system is gradually important. Since the feature extraction is the key and basic technique, superior feature extractor can improve the integrated navigation accuracy. In order to improve the robustness and accuracy of the feature extraction, an improved Features from Accelerated Segment Test (FAST) feature extraction based on the Random Sample Consensus (RANSAC) method is proposed to remove the mismatched points in this manuscript. Furthermore, the performance of this new method has been estimated through experiments. And the results have shown that the proposed feature extractor cannot only effectively extract features, but also reduce the positioning error availably, making the proposed FAST feature extraction based on RANSAC feasible and efficient.