# Unsupervised Learning for Target Tracking and Background Subtraction in Satellite Imagery

arXiv: https://arxiv.org/abs/2109.00885 · HTML: https://mlsanity.com/paper/2109.00885/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 13 Aug 2021.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Unsupervised Deep Tracking](https://mlsanity.com/paper/1904.01828/) (2019)
- [W-Net: A Deep Model for Fully Unsupervised Image Segmentation](https://mlsanity.com/paper/1711.08506/) (2017)
- [Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections](https://mlsanity.com/paper/1606.08921/) (2016)
- [DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensing](https://mlsanity.com/paper/1607.03343/) (2016)
- [FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics](https://mlsanity.com/paper/1612.05360/) (2016)
- [Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation](https://mlsanity.com/paper/1809.01125/) (2018)
- [Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs](https://mlsanity.com/paper/1608.05186/) (2016)
- [Unsupervised Motion Artifact Detection in Wrist-Measured Electrodermal Activity Data](https://mlsanity.com/paper/1707.08287/) (2017)

## Abstract (arXiv)

This paper describes an unsupervised machine learning methodology capable of target tracking and background suppression via a novel dual-model approach. ``Jekyll`` produces a video bit-mask describing an estimate of the locations of moving objects, and ``Hyde`` outputs a pseudo-background frame to subtract from the original input image sequence. These models were trained with a custom-modified version of Cross Entropy Loss. Simulated data were used to compare the performance of Jekyll and Hyde against a more traditional supervised Machine Learning approach. The results from these comparisons show that the unsupervised methods developed are competitive in output quality with supervised techniques, without the associated cost of acquiring labeled training data.