# View management for lifelong visual maps

## TL;DR

This paper proposes a view pruning method for visual SLAM systems to maintain efficiency and accuracy over long-term operation by removing less useful views.

## Contribution

It introduces a novel approach to selectively prune views in visual SLAM, addressing the growth of stored views and improving long-term system performance.

## Key findings

- View pruning improves SLAM speed and accuracy.
- The method effectively removes rarely observed or low-quality views.
- Enhanced long-term robustness of visual SLAM systems.

## Abstract

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.