ORB-YOLO: An Indoor IMU-aided Visual-Inertial SLAM System for Dynamic Environment

Abstract

Visual Simultaneous Localization and Mapping (Visual SLAM) is a methodology that empowers a robot to construct a map of an unfamiliar environment and determine its own position within the map solely based on visual data. However, Visual SLAM faces many challenges in indoor scenarios, such as low lighting, dynamic objects, textureless surfaces, and motion blur. To overcome these difficulties, we propose an indoor Visual SLAM system that combines ORB_SLAM3 with YOLOv8 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> to achieve high accuracy while maintaining robust performance in dynamic environments. Besides, the proposed system also uses the Inertial Measurement Unit (IMU) to aid the SLAM process. The IMU provides complementary information to the camera, such as orientation, acceleration, and angular velocity, which can improve the robustness and accuracy of the Visual SLAM system. Our system undergoes evaluation on two public datasets, as well as in real-world scenarios. To assess its performance, we compare it against alternative Dynamic SLAM approaches. The outcomes demonstrate that our system effectively handles intricate dynamic scenes that involve multiple moving objects, yielding state-of-the-art (SOTA) results. We have released our code on: https://github.com/SimonWXW/ORB-YOLO.