View management for lifelong visual maps
This addresses the issue of computational and memory constraints in SLAM systems for robotics or autonomous navigation, though it is incremental as it builds on existing graph-based visual SLAM frameworks.
The paper tackles the problem of view management in lifelong visual SLAM systems, where the accumulation of views over time degrades speed and accuracy, and proposes a pruning method to remove low-quality or rarely observed views, resulting in improved performance for long-term use.
The time complexity of making observations and loop closures in a graph-based visual SLAM system is a function of the number of views stored. Clever algorithms, such as approximate nearest neighbor search, can make this function sub-linear. Despite this, over time the number of views can still grow to a point at which the speed and/or accuracy of the system becomes unacceptable, especially in computation- and memory-constrained SLAM systems. However, not all views are created equal. Some views are rarely observed, because they have been created in an unusual lighting condition, or from low quality images, or in a location whose appearance has changed. These views can be removed to improve the overall performance of a SLAM system. In this paper, we propose a method for pruning views in a visual SLAM system to maintain its speed and accuracy for long term use.