DarkVesselNet: Multi-Modal Remote Sensing and Trajectory Reasoning for Dark Vessel Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Sharma, Arun
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916068978589696
author Sharma, Arun
author_facet Sharma, Arun
contents Dark vessel detection requires fusing what vessels report through AIS with what satellites observe through radar and optical sensors. DarkVesselNet is a multi-modal remote sensing stack that combines Sentinel-1 SAR, Sentinel-2 optical imagery, geospatial foundation model backbones, AIS trajectory reasoning, TGARD-style gap detection, and a Pi-DPM-inspired anomaly head. The repository exposes the system as a tested Python package and a public Hugging Face Space. The paper presents the sensor stack, backbone abstraction, fusion path, anomaly head, and current validation. The evidence currently available is software-grounded: tests for SAR speckle filtering, optical band ratios, Haversine distance, TGARD gap emission, sensor coregistration, backbone token shapes, and differentiable anomaly scoring.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00445
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DarkVesselNet: Multi-Modal Remote Sensing and Trajectory Reasoning for Dark Vessel Detection
Sharma, Arun
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Dark vessel detection requires fusing what vessels report through AIS with what satellites observe through radar and optical sensors. DarkVesselNet is a multi-modal remote sensing stack that combines Sentinel-1 SAR, Sentinel-2 optical imagery, geospatial foundation model backbones, AIS trajectory reasoning, TGARD-style gap detection, and a Pi-DPM-inspired anomaly head. The repository exposes the system as a tested Python package and a public Hugging Face Space. The paper presents the sensor stack, backbone abstraction, fusion path, anomaly head, and current validation. The evidence currently available is software-grounded: tests for SAR speckle filtering, optical band ratios, Haversine distance, TGARD gap emission, sensor coregistration, backbone token shapes, and differentiable anomaly scoring.
title DarkVesselNet: Multi-Modal Remote Sensing and Trajectory Reasoning for Dark Vessel Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2606.00445