ADS-SLAM: a semantic SLAM based on adaptive motion compensation and semantic information for dynamic environments

Abstract Static environment assumption are the prerequisite for simultaneous localization and mapping (SLAM), while interference from dynamic objects in the environment can seriously impair the system’s localization accuracy. Recently, many works usually combine deep learning and geometric constraints to attenuate the interference of dynamic objects, however poor real-time performance and low accuracy in high dynamic scenes still exist. In this paper, we proposed a semantic SLAM algorithm for complex dynamic scenes named ADS-SLAM. Our system combines the advantages of semantic information and motion constraints to remove dynamic points during tracking and localization. First, an adaptive dynamic point detection method based on epipolar constraint between adjacent frames is designed to adapt the changes of object motion states, and a motion area detection method based on Gaussian Mixture Model (GMM) and Kalman Filter (KF) is utilized to effectively compensate the missed motion areas. Second, the object detection network with improved inference in the backend is utilized to extract prior object semantics. Lastly, the multi-level information is integrated in order to comprehensively screen all dynamic points in the environment and utilize only static points for pose estimation and optimization. Extensive evaluations on challenging public datasets and outdoor dynamic environment demonstrate that our algorithm achieves high localization accuracy in almost all dynamic scenarios compared to the current state-of-the-art SLAM algorithms, especially the highest accuracy in high dynamic scenarios, and shows real-time performance for practical applications.