Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

HE-VPR: Height Estimation Enabled Aerial Visual Place Recognition Against Scale Variance

Mengfan He, Xingyu Shao, Chunyu Li, Chao Chen, Liangzheng Sun, Ziyang Meng, Yuanqing Wu

TL;DR

Results indicate that HE-VPR offers a scalable and efficient solution for height-aware aerial VPR, enabling practical deployment in GNSS-denied environments and reduces memory usage by up to 90%.

Abstract

In this work, we propose HE-VPR, a visual place recognition (VPR) framework that incorporates height estimation. Our system decouples height inference from place recognition, allowing both modules to share a frozen DINOv2 backbone. Two lightweight bypass adapter branches are integrated into our system. The first estimates the height partition of the query image via retrieval from a compact height database, and the second performs VPR within the corresponding height-specific sub-database. The adaptation design reduces training cost and significantly decreases the search space of the database. We also adopt a center-weighted masking strategy to further enhance the robustness against scale differences. Experiments on two self-collected challenging multi-altitude datasets demonstrate that HE-VPR achieves up to 6.1\% Recall@1 improvement over state-of-the-art ViT-based baselines and reduces memory usage by up to 90\%. These results indicate that HE-VPR offers a scalable and efficient solution for height-aware aerial VPR, enabling practical deployment in GNSS-denied environments. All the code and datasets for this work have been released on https://github.com/hmf21/HE-VPR.

HE-VPR: Height Estimation Enabled Aerial Visual Place Recognition Against Scale Variance

TL;DR

Results indicate that HE-VPR offers a scalable and efficient solution for height-aware aerial VPR, enabling practical deployment in GNSS-denied environments and reduces memory usage by up to 90%.

Abstract

In this work, we propose HE-VPR, a visual place recognition (VPR) framework that incorporates height estimation. Our system decouples height inference from place recognition, allowing both modules to share a frozen DINOv2 backbone. Two lightweight bypass adapter branches are integrated into our system. The first estimates the height partition of the query image via retrieval from a compact height database, and the second performs VPR within the corresponding height-specific sub-database. The adaptation design reduces training cost and significantly decreases the search space of the database. We also adopt a center-weighted masking strategy to further enhance the robustness against scale differences. Experiments on two self-collected challenging multi-altitude datasets demonstrate that HE-VPR achieves up to 6.1\% Recall@1 improvement over state-of-the-art ViT-based baselines and reduces memory usage by up to 90\%. These results indicate that HE-VPR offers a scalable and efficient solution for height-aware aerial VPR, enabling practical deployment in GNSS-denied environments. All the code and datasets for this work have been released on https://github.com/hmf21/HE-VPR.
Paper Structure (16 sections, 4 equations, 5 figures, 6 tables)

This paper contains 16 sections, 4 equations, 5 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Aerial VPR with Height Variation
  4. Adapters for Vision Transformers
  5. Methodology
  6. Preliminary
  7. Bypass Adapter
  8. Height-Aware Aerial VPR
  9. Masked Feature Enhancement
  10. Experiments
  11. Implementation Details
  12. Evaluation Datasets
  13. HE Evaluation
  14. VPR Evaluation
  15. HE-VPR Evaluation
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Overview of the proposed HE-VPR, an aerial VPR pipeline with height estimation.
  • Figure 2: Illustration of the adapter network in ViT.
  • Figure 3: The proposed HE-VPR pipeline. A height estimation branch is added for sub-database selection such that the proposed pipeline is robust to height variance. It requires only a single forward pass of the model for both parts.
  • Figure 4: Overviews of two evaluation datasets.
  • Figure 5: Qualitative results for height estimation. The top two rows are from GEStudio dataset and the bottom two rows are from MHFlight dataset. The height label for top-5 database image is annotated at the top and all the samples are correctly retrieved at the top-1 candidate.