GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure Detection

[Arxiv] [Project Page] [Intro in Chinese]

Abstract

Visual loop closure detection is an important module in visual simultaneous localization and mapping (SLAM), which associates current camera observation with previously visited places. Loop closures correct drifts in trajectory estimation to build a globally consistent map. However, a false loop closure can be fatal, so verification is required as an additional step to ensure robustness by rejecting the false positive loops. Geometric verification has been a well-acknowledged solution that leverages spatial clues provided by local feature matching to find true positives. Existing feature matching methods focus on homography and pose estimation in long-term visual localization, lacking references for geometric verification. To fill the gap, this paper proposes a unified benchmark targeting geometric verification of loop closure detection under long-term conditional variations. Furthermore, we evaluate six representative local feature matching methods (handcrafted and learning-based) under the benchmark, with in-depth analysis for limitations and future directions.

News

:star: Paper is release on arxiv.
:tada: The paper is accepted by IROS 2024!
:rocket: Releasing the visualization of image matching results. (google drive)
:rocket: Releasing the benchmark (easy)! Checkout the image pairs from dataset/gt and images from google drive

Installation

We use part of the HLoc code for feature extraction and matching.

git clone && cd GV-Bench
git submodule init
git submodule update
cd third_party/Hierarchival-Localization
git checkout gvbench # this is a customized fork version
python -m pip install -e .

Replicate Results in Exps

We provide the [output results]() with the format shown below. You can use these results directly.

$seq_$feature_$match.log
$seq_$feature_$match.npy # with following format

np.save(str(export_dir), {
  'prob': num_matches_norm,
  'qImages': qImages,
  'rImages': rImages,
  'gt': labels, 
  'inliers': inliers_list,
  'all_matches': pointMaps,
  'precision': precision, 
  'recall': recall, 
  'TH': TH,
  'average_precision': average_precision,
  'Max Recall': r_recall
  })

Replicate from scratch

To get standard feature detection and matching results, we proposed to use hloc.

Download the dataset sequences from google drive and put it under the dataset/ folder.

Extract and match feature using hloc.

Extract features: SIFT, SuperPoint, and DISK

python third_party/Hierarchical-Localization/gvbench_utils.py config/${seq}.yaml --extraction

Match features: SIFT-NN, SIFT-LightGlue (Not yet implemented), SuperPoint-NN, DISK-NN, SuperPoint-SuperGlue, SuperPoint-LightGlue, DISK-LightGlue, LoFTR
```
# all methods except LoFTR
python third_party/Hierarchical-Localization/gvbench_utils.py config/${seq}.yaml --matching
```

LoFTR is different from above methods thus

python third_party/Hierarchical-Localization/gvbench_utils.py config/${seq}.yaml --matching_loftr


<!-- - We also provide the easy to run scripts
```bash
cd scripts/
bash evaluation.sh ${sequence_name}
``` -->
- Image pairs files
- We prepare pairs (GT) file for matching under `dataset/gt` foler.
- Make sure to use the fork hloc for feature extraction and matching `https://github.com/jarvisyjw/Hierarchical-Localization.git -b gvbench`

Evaluation

We provide out-of-box scripts

cd GV-Bench/scripts
bash ./evaluation <day> # run script with 
#sequence name: day, night, night-hard, season, season-hard, weather

Benchmark Usage

Using customized local features for geometric verification (GV).

TODO

Visualization
- Demos are presented in plot_data.ipynb

Acknowledgement

This work builds upon hloc, thanks for their amazing work.
Contact: jingwen.yu@connect.ust.hk

jarvisyjw / GV-Bench

readme