Visual and Visual-Inertial SLAM: State of the Art, Classification, and Experimental Benchmarking

Abstract

Simultaneous Localization and Mapping is now widely adopted by many applications, and researchers have produced very dense literature on this topic. With the advent of smart devices, embedding cameras, inertial measurement units, visual SLAM (vSLAM), and visual-inertial SLAM (viSLAM) are enabling novel general public applications. In this context, this paper conducts a review of popular SLAM approaches with a focus on vSLAM/viSLAM, both at fundamental and experimental levels. It starts with a structured overview of existing vSLAM and viSLAM designs and continues with a new classification of a dozen main state-of-the-art methods. A chronological survey of viSLAM’s development highlights the historical milestones and presents more recent methods into a classification. Finally, the performance of vSLAM is experimentally assessed for the use case of pedestrian pose estimation with a handheld device in urban environments. The performance of five open-source methods Vins-Mono, ROVIO, ORB-SLAM2, DSO, and LSD-SLAM is compared using the EuRoC MAV dataset and a new visual-inertial dataset corresponding to urban pedestrian navigation. A detailed analysis of the computation results identifies the strengths and weaknesses for each method. Globally, ORB-SLAM2 appears to be the most promising algorithm to address the challenges of urban pedestrian navigation, tested with two datasets.

Fast Attitude Estimation System for Unmanned Ground Vehicle Based on Vision/Inertial Fusion

“…where [L I , λ I , h I ] is the position of the SINS mechanization in navigation frame. In Equation (11), P is the retraction of:…”

“…Due to its low cost, small size, and rich environmental perception information, it is a very promising scheme in engineering applications. At present, the vision/inertial fusion system can be divided into the method of filtering and optimization [11]. The method based on filtering is to use the visual calculation results to construct the measurement equation and use the inertial mechanization results to construct the state equation.…”

“…Compared with the optimized method, the optimization-based vision/inertial fusion method is the current mainstream, which has the advantages of efficiency, precision, and the possibility of achieving a large range of environments [11]. Forster et al put forward a systematic theory for inertial pre-integration, which cleverly converts the previous inertial continuous mechanization results into incremental results.…”

Mobile 3D scan LiDAR: a literature review

“…Indeed, the application can be extended further when dealing with the smart cities paradigm: to collect information on advertising signals in the city (Chiappini et al 2020), parking monitoring (Bock et al 2015), evaluation of emergency cases for infrastructures such as tunnels (Leingartner et al 2016) and much more. In literature there are already a few cases of comparisons of laser scanner tools, specific to the urban environment ( C. Wang et al 2020;Yanjun Wang et al 2019 ) and more generally reviews by MLS (I Puente et al 2013;Servi eres et al 2021).…”

GNSS Spoofing Identification and Smoothing Localization Method for GNSS/Visual SLAM System

“…However, its signals are publicly available, which makes its localization easy to be spoofed. In recent years, with the improvement of mobile terminal computing performance, the use of camera sensors to obtain visual SLAM data has been widely used [1]. The visual mileage information provided by SLAM can simultaneously match the observed environmental features with the feature map to obtain pose and autonomous localization [2].…”