A Lightweight Visual Simultaneous Localization and Mapping Method with a High Precision in Dynamic Scenes

Abstract

Currently, in most traditional VSLAM (visual SLAM) systems, static assumptions result in a low accuracy in dynamic environments, or result in a new and higher level of accuracy but at the cost of sacrificing the real–time property. In highly dynamic scenes, balancing a high accuracy and a low computational cost has become a pivotal requirement for VSLAM systems. This paper proposes a new VSLAM system, balancing the competitive demands between positioning accuracy and computational complexity and thereby further improving the overall system properties. From the perspective of accuracy, the system applies an improved lightweight target detection network to quickly detect dynamic feature points while extracting feature points at the front end of the system, and only feature points of static targets are applied for frame matching. Meanwhile, the attention mechanism is integrated into the target detection network to continuously and accurately capture dynamic factors to cope with more complex dynamic environments. From the perspective of computational expense, the lightweight network Ghostnet module is applied as the backbone network of the target detection network YOLOv5s, significantly reducing the number of model parameters and improving the overall inference speed of the algorithm. Experimental results on the TUM dynamic dataset indicate that in contrast with the ORB–SLAM3 system, the pose estimation accuracy of the system improved by 84.04%. In contrast with dynamic SLAM systems such as DS–SLAM and DVO SLAM, the system has a significantly improved positioning accuracy. In contrast with other VSLAM algorithms based on deep learning, the system has superior real–time properties while maintaining a similar accuracy index.

SEG-SLAM: Dynamic Indoor RGB-D Visual SLAM Integrating Geometric and YOLOv5-Based Semantic Information

“…In 2023, Zhang et al [32] introduced a visual SLAM system that utilizes the YOLOv5s CNN and Ghostnet backbone network to detect dynamic objects in a scene and integrates the coordinate attention mechanism to improve the small-target recognition accuracy. However, the method used to reject dynamic objects is relatively simple and it rejects all the points within the detection box without fully considering the background points within the detection box.…”

A Comparative Review on Enhancing Visual Simultaneous Localization and Mapping with Deep Semantic Segmentation

“…The map representation constituted another crucial component in VSLAM systems. Traditional maps typically consisted of geometric representations that primarily encoded low-level metric or topological information [ 95 , 96 ]. In contrast, semantic maps, which incorporated high-level context, provided a more comprehensive understanding of the environment, thereby enhancing intelligent interactions and decision-making capabilities.…”