# Deep Vehicle Detection in Satellite Video

arXiv: https://arxiv.org/abs/2204.06828 · HTML: https://mlsanity.com/paper/2204.06828/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 69 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [Gaussian Temporal Awareness Networks for Action Localization](https://mlsanity.com/paper/1909.03877/) (2019)
- [MAGSAC: marginalizing sample consensus](https://mlsanity.com/paper/1803.07469/) (2018)
- [A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning](https://mlsanity.com/paper/1609.04453/) (2016)
- [Clustered Object Detection in Aerial Images](https://mlsanity.com/paper/1904.08008/) (2019)
- [Grouped Spatial-Temporal Aggregation for Efficient Action Recognition](https://mlsanity.com/paper/1909.13130/) (2019)
- [Vehicle Detection in Aerial Images](https://mlsanity.com/paper/1801.07339/) (2018)
- [Error Bounded Foreground and Background Modeling for Moving Object Detection in Satellite Videos](https://mlsanity.com/paper/1908.09539/) (2019)
- [Online Structured Sparsity-based Moving Object Detection from Satellite Videos](https://mlsanity.com/paper/1911.12989/) (2019)
- [On Learning Vehicle Detection in Satellite Video](https://mlsanity.com/paper/2001.10900/) (2020)
- [Detecting Tiny Moving Vehicles in Satellite Videos](https://mlsanity.com/paper/1807.01864/) (2018)
- [Multi-Cue Vehicle Detection for Semantic Video Compression In Georegistered Aerial Videos](https://mlsanity.com/paper/1907.01176/) (2019)

## Built on by (most cited first, 1 of 1)

- [A Scoping Review of Earth Observation and Machine Learning for Causal Inference: Implications for the Geography of Poverty](https://mlsanity.com/paper/2406.02584/) (2024)

## Abstract (arXiv)

This work presents a deep learning approach for vehicle detection in satellite video. Vehicle detection is perhaps impossible in single EO satellite images due to the tininess of vehicles (4-10 pixel) and their similarity to the background. Instead, we consider satellite video which overcomes the lack of spatial information by temporal consistency of vehicle movement. A new spatiotemporal model of a compact 3 × 3 convolutional, neural network is proposed which neglects pooling layers and uses leaky ReLUs. Then we use a reformulation of the output heatmap including Non-Maximum-Suppression (NMS) for the final segmentation. Empirical results on two new annotated satellite videos reconfirm the applicability of this approach for vehicle detection. They more importantly indicate that pre-training on WAMI data and then fine-tuning on few annotated video frames for a new video is sufficient. In our experiment only five annotated images yield a F1 score of 0.81 on a new video showing more complex traffic patterns than the Las Vegas video. Our best result on Las Vegas is a F1 score of 0.87 which makes the proposed approach a leading method for this benchmark.