Learning to Predict Repeatability of Interest Points

TL;DR

This paper introduces a method to predict the lifespan of interest points in robotics environments, improving visual localization by selecting more repeatable points over time.

Contribution

It presents a novel repeatability predictor trained on long-term interest point data, enabling better interest point selection for robust localization.

Findings

The predictor accurately estimates interest point repeatability over time.

Using the predictor improves localization accuracy in map summarization.

The approach effectively mitigates localization degradation due to environmental changes.

Abstract

Many robotics applications require interest points that are highly repeatable under varying viewpoints and lighting conditions. However, this requirement is very challenging as the environment changes continuously and indefinitely, leading to appearance changes of interest points with respect to time. This paper proposes to predict the repeatability of an interest point as a function of time, which can tell us the lifespan of the interest point considering daily or seasonal variation. The repeatability predictor (RP) is formulated as a regressor trained on repeated interest points from multiple viewpoints over a long period of time. Through comprehensive experiments, we demonstrate that our RP can estimate when a new interest point is repeated, and also highlight an insightful analysis about this problem. For further comparison, we apply our RP to the map summarization under visual localization framework, which builds a compact representation of the full context map given the query time. The experimental result shows a careful selection of potentially repeatable interest points predicted by our RP can significantly mitigate the degeneration of localization accuracy from map summarization.