A visual SLAM method assisted by IMU and deep learning in indoor dynamic blurred scenes

Abstract

Dynamic targets in the environment can seriously affect the accuracy of SLAM systems. This article proposes a novel dynamic visual SLAM method with IMU and deep learning for indoor dynamic blurred scenes, which improves the front end of ORB-SLAM2, combining deep learning with geometric constraint to make the dynamic feature points elimination more reasonable and robust. First, a multi-directional superposition blur augmentation algorithm is added to the YOLOv5s network to compensate for errors caused by fast-moving targets, camera shake and camera focus. Then, the fine-tuned YOLOv5s model is used to detect potential dynamic regions. Afterward, IMU measurements are introduced for rotation compensation to calculate the feature point velocity and estimate the motion speed of the camera, in order to estimate the real motion state of potential dynamic targets. Finally, real dynamic points will be removed and potential dynamic points will be reserved for subsequent pose estimation. Experiments are conducted on TUM dynamic dataset and in the real world. The results demonstrate that the proposed method has significant improvement compared with ORB-SLAM2, and has a more robust performance over some other state-of-the-art dynamic visual SLAM systems.

2DLIW-SLAM:2D LiDAR-inertial-wheel odometry with real-time loop closure

“…In recent times, propelled by advancements in visual SLAM [6] and 3D LiDAR SLAM [7], multi-sensor fusion for motion and pose estimation has found extensive utility. Given that indoor robots generally move at slow speeds with frequent stops and starts, the performance of IMU under such conditions may not be ideal, whereas wheel odometry demonstrates superior performance, especially when the robot is stationary and there is no error accumulation.…”