STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation

Shingeon Kim; Hyeyoon Lee; Dain Kwon; Kanghyun Choi; Sunjong Park; Mi-Ryang Kim; Jeong-Eun Lee; Jinho Lee

cs.CVAug 29, 2026

STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation

Authors: Shingeon Kim, Hyeyoon Lee, Dain Kwon, Kanghyun Choi, Sunjong Park, Mi-Ryang Kim, Jeong-Eun Lee, Jinho Lee

Organizations: Department of Electrical and Computer Engineering, Seoul National University · Department of Physics and Astronomy, Seoul National University

Abstract

The rapid expansion of low Earth orbit satellites such as Starlink is increasingly contaminating astronomical surveys. In practice, contaminated images are often identified through inspection. However, modern surveys generate terabytes of data each night, making manual screening infeasible and necessitating reliable automated methods for satellite trail removal. Unfortunately, existing general-domain line detection methods fail to generalize to astronomical images due to domain mismatch, which are mostly grayscale with sparse bright stars and have a low signal-to-noise ratio. Moreover, training new models from scratch is impractical due to the lack of large-scale annotated astronomical datasets. To address these challenges, we introduce STARLINC, the first ML-based framework for satellite trail removal without requiring tedious pixel-level annotation of astronomical images. STARLINC combines synthetic satellite trail generation for training, inter-frame differential maps from temporally adjacent exposures to highlight transient trails, and heatmaps to provide additional localization cues for pixel-level segmentation. Extensive experiments on real-world data demonstrate substantial improvements over baselines, establishing STARLINC as a scalable solution for next-generation astronomical surveys. Code is available at https://github.com/starioKim/STARLINC.

Figures & tables

Figure 1: An example of contaminated images.

Figure 2: Motivational study of the impact of satellite contamination. (a) A satellite trail intersecting a star perturbs its measured brightness (magnitude). (b) The resulting bias leads to errors in derived stellar properties (e.g., age and mass).

Figure 3: (a) Visualization of SNR distribution per dataset. The astronomical images consists of very low SNR, compared to general domain datasets. (b) Line detection performance under varying signal-to-noise ratios (SNR) of images. Deep learning detectors degrade rapidly in the low-SNR region. The metric is structural Average Precision (sAP), which measures the accuracy of predicted lines against the ground truth. @5, @10, and @15 denote the pixel tolerance for matching prediction and ground-truth.

Figure 4: Overall framework of STARLINC. The pipeline consists of three stages. Synthetic data generation (§ 4.1 ): Artificial satellite trails are injected into non-trail images to generate image-label pairs for segmentation model training. Inter-frame differential map (§ 4.2 ): Leveraging repeated exposures of the same sky region, STARLINC suppresses static celestial structures and emphasizes transient satellite trails using locally aggregated temporal differences. Pseudo-localization via heatmaps (§ 4.3 ): We convert an image-level trail classifier into a spatial cue by extracting Grad-CAM activation heatmaps, which provide coarse pseudo-localization of the trail and guide the downstream segmentation network without pixel-level annotations.

Category	Method	Metrics
Category	Method	mIoU	Dice	Prec.	Recall	ROC AUC	PR AUC
Classical	Hough [ 11 ]	0.142	0.202	0.785	0.293	0.692	0.741
	Radon [ 29 ]	0.000	0.001	0.653	0.001	0.670	0.696
	LSD [ 37 ]	0.074	0.126	0.077	0.517	0.776	0.714
Learning-based	DeepLSD [ 28 ]	0.116	0.192	0.120	0.642	0.867	0.827
Learning-based	DT-LSD [ 16 ]	0.240	0.332	0.663	0.507	0.769	0.838

Table 1: Segmentation performance comparison.

Figure 5: Performance evaluation for segmentation model using (a) ROC curve and (b) PR curve showing performance across different decision thresholds.

Figure 6: Qualitative examples of satellite trail masking. Each row shows a different astronomical image containing a satellite trail. From left to right, the original observation, and trail masks predicted by Hough [ 11 ] , DT-LSD [ 16 ] , MaxiMask [ 27 ] , and STARLINC, where detected trail locations are overlaid in red. If the model fails to detect the line, the output remains identical to the original image.

Dataset	Metric	Method
Dataset	Metric	Hough	Radon	LSD	DeepLSD †	DT-LSD †	ASTA †	MaxiMask †	UnetLSD †	STARLINC
ZTF	mIoU	0.166	0.029	0.288	0.321	0.019	0.067	0.365	0.163	0.469
ZTF	Dice	0.285	0.057	0.447	0.486	0.038	0.126	0.535	0.280	0.639
NGC	mIoU	0.115	0.001	0.050	0.199	0.011	0.020	0.008	0.120	0.471
NGC	Dice	0.206	0.002	0.095	0.331	0.021	0.040	0.015	0.215	0.640

Table 2: Cross-dataset evaluation on ZTF and NGC-region observations.

Table 9

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 7: Visualization of the three input modalities used for segmentation over time: the original image, the mean inter-frame differential map (§ 4.2 ), and the heatmap (§ 4.3 ). Trail-containing frames (e.g., $t_{1}$ , $t_{3}$ , and $t_{4}$ ) show strong responses in both the differential map and the heatmap, while the trail-free frame ( $t_{2}$ ) shows minimal activation.

Figure 8: Performance evaluation for classification model using (a) ROC curve and (b) PR curve showing performance across different decision thresholds.

Category	Method	Metrics
Category	Method	Acc	Pre	Recall	F1	ROC-AUC	PR-AUC
Classical	Hough [ 11 ]	0.875	0.913	0.429	0.583	0.692	0.756
	Radon [ 29 ]	0.863	0.944	0.347	0.507	0.671	0.708
	LSD [ 37 ]	0.204	0.204	1.000	0.339	0.777	0.723
Learning-based	DeepLSD [ 28 ]	0.204	0.204	1.000	0.339	0.868	0.834
Learning-based	DT-LSD [ 16 ]	0.917	1.000	0.592	0.744	0.796	0.838

Appendix

Table 6: Classification performance comparison.

Synthetic ratio (%)	Number of data
Synthetic ratio (%)	150	300	450	600	750	900
30	0.651	0.863	0.835	0.863	0.882	0.865
50	0.515	0.653	0.662	0.756	0.824	0.959
70	0.626	0.626	0.492	0.364	0.492	0.545
90	0.371	0.339	0.345	0.344	0.344	0.375

Appendix

Table 7: Sensitivity analysis for classification performance.

Method		Metrics
§ 4.1	§ 4.2	F1	Acc	Pre	Recall
✗	✗	0.314	0.708	0.302	0.327
✓	✗	0.381	0.783	0.457	0.327
✗	✓	0.779	0.913	0.804	0.755
✓	✓	0.959	0.983	0.959	0.959

Appendix

Table 8: Ablation results of the classification task.

Synthetic fraction (%)	57.3	65.1	70.0	75.1	80.0	85.1	90.0	95.1
mIoU	$0.485$ $\pm 0.012$	$\mathbf{0.521}$ $\boldsymbol{\pm}\mathbf{0.018}$	$0.493$ $\pm 0.014$	$0.492$ $\pm 0.008$	$0.504$ $\pm 0.010$	$0.506$ $\pm 0.017$	$0.472$ $\pm 0.012$	$0.504$ $\pm 0.008$

Appendix

Table 9: Sensitivity to the synthetic fraction among trail-containing training images.

Method	mIoU	Dice	Precision	Recall
DeepLSD †	0.269	0.380	0.293	0.628
DT-LSD †	0.381	0.474	0.482	0.477
ASTA †	0.285	0.394	0.360	0.506
MaxiMask †	0.220	0.289	0.734	0.180

Appendix

Table 10: Results of fine-tuned learning-based baselines on the 7DT dataset.

# Params(M)	3.67	4.67	5.94	6.82	7.76 (Ours)	8.96	10.97	20.61
mIoU	0.475	0.480	0.480	0.488	0.485	0.480	0.483	0.473

Appendix

Table 11: U-Net size sensitivity analysis.

Setting	mIoU	Dice	Precision	Recall
STARLINC-8bit(ours)	0.485	0.653	0.815	0.545
STARLINC-16bit	0.450	0.621	0.816	0.501

Appendix

Table 12: Effect of input bit depth.

Figure 9: Applying STARLINC to other astronomical datasets (Serpens and Messier 81). The predicted masks accurately localize satellite trails while preserving surrounding celestial structures.

Figure 10: Additional qualitative comparison of satellite trail detection and removal results across different methods.

Figure 11: Additional qualitative comparison of satellite trail detection and removal results across different methods (continued).

Figure 12: Comparison of different distance metrics for inter-frame differential map computation. Given a target image and another comparison image from the same observation group, we compute difference maps using MAE, RMSE, SSIM.

Panel of Figure 13 — Figure 13: Example predictions of DeepLSD [ 28 ] on the Wireframe dataset [ 15 ] under different SNR levels, compared with ground-truth.

Image Restoration

Image restoration uses computational methods to recover useful visual content from noisy, blurred, low-resolution, or otherwise degraded images.

See all 375 papers

StreakMind: AI detection and analysis of satellite streaks in astronomical images with automated database integration
May 5, 2026Rafael Carrillo Navarro, René Duffard, Pablo García-Martín +3Object Detection
Real Instituto y Observatorio de la Armada (ROA), Plaza de las Marinas s/n, 11100 San Fernando (Cádiz), Spain · Instituto de Astrofísica de Andalucía – CSIC, Apdo. 3004, 18080 Granada, Spain · Safran, 171 Bd de Valmy, 92700 Colombes, France +2
AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data
Apr 18, 2026Omid Vaheb, Sebastien Fabbro, Stark DraperSelf-Supervised Image Denoising Noise Robustness
Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, 10 King’s College Road, Toronto, ON M5S 3G4, Canada · National Research Council Herzberg Astronomy an Astrophysics Research Centre, 5071 West Saanich Road, Victoria, BC V9E 2E7, Canada · Department of Computer Science, University of British Columbia, Vancouver, BC, V6T 1Z4, Canada
Co-addition and Subtraction of Undersampled Images
Jul 20, 2026Matan Schlanger, Barak ZackayImage Reconstruction Astrophysics
Department of Particle Physics and Astrophysics Weizmann Institute of Science 76100 Rehovot, Israel

May 5, 2026J/K move · Enter open · S save

StreakMind: AI detection and analysis of satellite streaks in astronomical images with automated database integration

Rafael Carrillo Navarro, René Duffard, Pablo García-Martín, Javier Romero+2

Real Instituto y Observatorio de la Armada (ROA), Plaza de las Marinas s/n, 11100 San Fernando (Cádiz), Spain · Instituto de Astrofísica de Andalucía – CSIC, Apdo. 3004, 18080 Granada, Spain · Safran, 171 Bd de Valmy, 92700 Colombes, France+2

Object Detection

Open paper AskPDF arXiv

Artificial satellites and space debris increasingly contaminate astronomical images, affecting scientific surveys and producing large volumes of streaked exposures. Manual inspection is no longer feasible at scale, and reliable detection and characterisation of streaks has become essential for both data-quality control and the monitoring of objects in Earth orbit. We present StreakMind, an automated pipeline designed to detect Near-Earth Objects and satellite streaks in astronomical images, characterise their geometry, and cross-identify them with known orbital objects. The system integrates all inference results into a structured database suitable for large surveys. A YOLO OBB model was trained on a hybrid dataset of 2335 images and applied to processed FITS frames. Geometric refinement, inter-frame association, satellite cross-identification, and Gaussian-based confidence scoring were then used to produce final identifications stored in a relational database. Observations from La Sagra Observatory were used to develop and test the method. On the test set, the model achieved a precision of 94 percent and a recall of 97 percent. It reliably detected faint streaks, delivered consistent geometric reconstructions, and performed robust satellite cross-identification. StreakMind demonstrates strong potential for large-scale automated analysis of linear streaks produced by both Near-Earth Objects and artificial satellites, contributing to space situational awareness.

Abstract

Image Restoration

Explore similar work

StreakMind: AI detection and analysis of satellite streaks in astronomical images with automated database integration

AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data

Co-addition and Subtraction of Undersampled Images