# Efficient Feature Description for Small Body Relative Navigation using Binary Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2304.04985 · HTML: https://mlsanity.com/paper/2304.04985/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 52 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm](https://mlsanity.com/paper/1808.00278/) (2018)
- [Forward and Backward Information Retention for Accurate Binary Neural Networks](https://mlsanity.com/paper/1909.10788/) (2019)
- [SOSNet: Second Order Similarity Regularization for Local Descriptor Learning](https://mlsanity.com/paper/1904.05019/) (2019)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [XNOR-Net++: Improved Binary Neural Networks](https://mlsanity.com/paper/1909.13863/) (2019)
- [TILDE: A Temporally Invariant Learned DEtector](https://mlsanity.com/paper/1411.4568/) (2014)
- [WRPN: Wide Reduced-Precision Networks](https://mlsanity.com/paper/1709.01134/) (2017)
- [Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks](https://mlsanity.com/paper/1911.09737/) (2019)
- [Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap](https://mlsanity.com/paper/2203.04275/) (2022)
- [Beyond Cartesian Representations for Local Descriptors](https://mlsanity.com/paper/1908.05547/) (2019)
- [daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices](https://mlsanity.com/paper/1908.05858/) (2019)
- [Learning to Assign Orientations to Feature Points](https://mlsanity.com/paper/1511.04273/) (2015)
- [Neural Outlier Rejection for Self-Supervised Keypoint Learning](https://mlsanity.com/paper/1912.10615/) (2019)
- [ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization](https://mlsanity.com/paper/2203.03610/) (2022)
- [AstroVision: Towards Autonomous Feature Detection and Description for Missions to Small Bodies Using Deep Learning](https://mlsanity.com/paper/2208.02053/) (2022)
- [AstroSLAM: Autonomous Monocular Navigation in the Vicinity of a Celestial Small Body -- Theory and Experiments](https://mlsanity.com/paper/2212.00350/) (2022)
- [Bayesian Deep Learning for Segmentation for Autonomous Safe Planetary Landing](https://mlsanity.com/paper/2102.10545/) (2021)

## Abstract (arXiv)

Missions to small celestial bodies rely heavily on optical feature tracking for characterization of and relative navigation around the target body. While techniques for feature tracking based on deep learning are a promising alternative to current human-in-the-loop processes, designing deep architectures that can operate onboard spacecraft is challenging due to onboard computational and memory constraints. This paper introduces a novel deep local feature description architecture that leverages binary convolutional neural network layers to significantly reduce computational and memory requirements. We train and test our models on real images of small bodies from legacy and ongoing missions and demonstrate increased performance relative to traditional handcrafted methods. Moreover, we implement our models onboard a surrogate for the next-generation spacecraft processor and demonstrate feasible runtimes for online feature tracking.