Evaluation of the Robustness of Visual SLAM Methods in Different Environments
This work addresses the need for reliable SLAM performance in varied environments, particularly for embedded vision applications, but is incremental as it focuses on benchmarking existing methods.
This paper compares the robustness of open-source visual SLAM algorithms across different environments using public datasets, finding performance variations based on environmental conditions, as part of a larger goal to test them in off-road scenarios.
Determining the position and orientation of a sensor vis-a-vis its surrounding, while simultaneously mapping the environment around that sensor or simultaneous localization and mapping is quickly becoming an important advancement in embedded vision with a large number of different possible applications. This paper presents a comprehensive comparison of the latest open-source SLAM algorithms with the main focus being their performance in different environmental surroundings. The chosen algorithms are evaluated on common publicly available datasets and the results reasoned with respect to the datasets' environment. This is the first stage of our main target of testing the methods in off-road scenarios.