Visual SLAM: What Are the Current Trends and What to Expect?

Abstract

In recent years, Simultaneous Localization and Mapping (SLAM) systems have shown significant performance, accuracy, and efficiency gain. In this regard, Visual Simultaneous Localization and Mapping (VSLAM) methods refer to the SLAM approaches that employ cameras for pose estimation and map reconstruction and are preferred over Light Detection And Ranging (LiDAR)-based methods due to their lighter weight, lower acquisition costs, and richer environment representation. Hence, several VSLAM approaches have evolved using different camera types (e.g., monocular or stereo), and have been tested on various datasets (e.g., Technische Universität München (TUM) RGB-D or European Robotics Challenge (EuRoC)) and in different conditions (i.e., indoors and outdoors), and employ multiple methodologies to have a better understanding of their surroundings. The mentioned variations have made this topic popular for researchers and have resulted in various methods. In this regard, the primary intent of this paper is to assimilate the wide range of works in VSLAM and present their recent advances, along with discussing the existing challenges and trends. This survey is worthwhile to give a big picture of the current focuses in robotics and VSLAM fields based on the concentrated resolutions and objectives of the state-of-the-art. This paper provides an in-depth literature survey of fifty impactful articles published in the VSLAMs domain. The mentioned manuscripts have been classified by different characteristics, including the novelty domain, objectives, employed algorithms, and semantic level. The paper also discusses the current trends and contemporary directions of VSLAM techniques that may help researchers investigate them.

Research on crowded scene localization method based on visual invariant information

“…In order to ensure the uniqueness of the obtained camera observation position optimization results, the following assumptions are made for the experimental environment: (1) The experimental environment is relatively densely populated. (2) The experimental site has a certain degree of representativeness. (3) No significant difference in the height of the ceiling and the shape of the ground architectural patterns seen by the camera.…”

“…The camera observation position optimization of vision localization should meet the following criteria: (1) The camera observation height reaches the lowest possible value. (2) The pitch angle of the camera should be such that the positioning accuracy meets the demand. (3) Moving pedestrian occlusion information does not have a significant impact on positioning accuracy, i.e., h and  should satisfy: min ( , , ) 0 ( , )…”

“…Autonomous mobile robots move in indoor crowded environments similar to airport terminal building, the robot's accurate self-localization method has been a key concern [1]. The main idea of robot self-positioning using visual perception method is to detect the image of fixed facilities in the environment to achieve [2]. The collection of visual invariant information and the extraction of localization information need to exclude the influence of pedestrian occlusion [3], it is required that the collected visual invariant information is rich enough to ensure the implementation of robot selfpositioning.…”

Image matching algorithm based on improved AKAZE and Gaussian mixture model

“…The resulting autonomous and driverless mobile robots have advanced quickly, and the simultaneous localization and mapping (SLAM) technology that used to locate them has received extensive research in academic circles 1 – 3 There are two types of SLAM: visual SLAM (VSLAM) 4 and laser SLAM 5 . Due to benefits such as inexpensive sensors and richer environmental data, VSLAM is growing quickly.…”

Dense mapping of large outdoor scenes based on Pseudo-LiDAR

“…One of the key technologies supporting the development of autonomous driving navigation is Simultaneous Localization And Mapping (SLAM), which has become a current research hotspot in academia and industry. It is capable of building a map of the environment and localizing in real time with the help of its own sensors 1 .…”