Towards Global Localization Using Global Descriptors

Charbel Azzi, Daniel Asmar, Adel Fakih, John ZelekJournal of Computational Vision and Imaging Systems 2016 · DOI

Abstract

Image-Based Localization (IBL) is a critical task for robotics and augmented reality, yet it becomes computationally expensive and prone to errors as scene size increases. This paper presents Global Search Space Reduction (GSSR), a system that utilizes global descriptors—specifically GIST—to prune the search space of a 3D map. By reducing the problem to a "small-scale" counterpart, GSSR achieves state-of-the-art accuracy on the Cambridge 5 Scenes dataset with significantly lower computational overhead and processing times under 0.1 seconds.

Introduction

The "Where am I?" problem, or Image-Based Localization (IBL), involves estimating the 6-DOF pose of a camera relative to a 3D representation of a scene. While effective for small environments, matching query images against millions of 3D points in large-scale urban environments leads to two primary issues: high computational cost and increased ambiguity (outliers). Traditional methods like Bag-of-Words often sacrifice accuracy for speed, while deep learning approaches like PoseNet lack the precision needed for high-stakes robotics applications.

The GSSR Methodology

The researchers propose a system called Global Search Space Reduction (GSSR). The core philosophy is to treat large-scale localization as a series of manageable small-scale problems by using the "gist" of a scene to prune away noise.

Figure 1: System architecture of the GSSR localizer, illustrating the offline map preparation and the online query image pipeline.

Workflow Overview

  1. Offline Stage: A 3D map is built using Structure-from-Motion (SfM). For every keyframe in the map, a GIST descriptor is computed. GIST captures the overall spatial structure and orientation of a scene without relying on individual local feature points.
  2. GIST Qualification: For a query image, the system computes its GIST descriptor and identifies a limited set of similar keyframes from the map based on a similarity measure.
  3. Clustering: These candidate keyframes are grouped into clusters, effectively narrowing the search from an entire city down to a few specific candidate locations.
  4. Fine-Grained Matching: Only now does the system perform matching. SIFT features from the query image are matched against the 3D points associated with the qualified keyframe clusters.
  5. Pose Estimation: RANSAC is used to filter remaining outliers, followed by precise 6-DOF pose calculation.

Visualizing Search Space Reduction

The power of GIST lies in its ability to quickly identify relevant portions of a map. By comparing the global descriptor of a query image to the database, the system can ignore the vast majority of the map that is visually dissimilar, preventing the "ambiguity trap" where different locations look alike.

Figure 2: Visualization of the GIST-based search space reduction. The plot shows distances between the query image and map keyframes, with clusters of low-distance (high similarity) images identified for further matching.

Results and Performance

The GSSR system was evaluated on the Cambridge 5 Scenes dataset, a gold standard for outdoor localization including areas like Kings College and St. Mary’s Church.

  • Accuracy: GSSR consistently outperformed industry standards. In the "Kings College" scene, it achieved a median error of 0.213 meters, compared to PoseNet’s 1.992 meters.
  • Efficiency: The system is remarkably fast for a feature-based localizer, with an average processing time of 0.085 seconds, making it suitable for real-time applications.
  • Robustness: By qualifying keyframes via visibility and similarity, the system significantly reduces the number of outliers that typically plague large-scale IBL.

Conclusion

GSSR demonstrates that global context is a powerful tool for large-scale localization. By using the "big picture" to guide fine-grained feature matching, the system achieves a balance of speed and precision that is essential for the next generation of autonomous systems and augmented reality.

Summary updated

Abstract

3D pose of a camera with respect to a 3D representation of thescene. IBL, despite being a trivial problem for small scenes, becomesquite challenging as the size of the scene grows. Aside fromthe computational burden, matching against a very large numberof 3D keypoints spanning a wide variety of viewpoints, illumination,and areas is a very unreliable process that results in a largenumber of outliers and ambiguous situations. In recent years, anumber of approaches have attempted to address the problem usingparadigms such as bag-of-words, features co-occurrence andothers, with varying degrees of success. This paper explores theuse of global descriptors, in particular GIST, to tackle this problem.We present a system that relies on a similarity measure derivedfrom GIST to qualify a limited number of 3D points for the matchingprocess, hence reducing the problem to its small size counterpart.Our results on a standard dataset show that our system canachieve better localization accuracy than the state of the art at afraction of the computational cost, which can used towards globallocalization.
BibTeX
@article{azzi2016towards,
  author = {Charbel Azzi and Daniel Asmar and Adel Fakih and John Zelek},
  title = {{Towards Global Localization Using Global Descriptors}},
  journal = {Journal of Computational Vision and Imaging Systems},
  year = {2016},
  doi = {10.15353/vsnl.v2i1.116},
}
Figure