mlsanityData to 14 Oct 2026

SmartScan: An AI-based Interactive Framework for Automated Region Extraction from Satellite Images

arXiv 2504.00200 ↗First posted 31 Mar 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The deployment of a continuous methane monitoring system requires determining the optimal number and placement of fixed sensors. However, planning is labor-intensive, requiring extensive site setup and iteration to meet client restrictions. This challenge is amplified when evaluating multiple sites, limiting scalability. To address this, we introduce SmartScan, an AI framework that automates data extraction for optimal sensor placement. SmartScan identifies subspaces of interest from satellite images using an interactive tool to create facility-specific constraint sets efficiently. SmartScan leverages the Segment Anything Model (SAM), a prompt-based transformer for zero-shot segmentation, enabling subspace extraction without explicit training. It operates in two modes: (1) Data Curation Mode, where satellite images are processed to extract high-quality subspaces using an interactive prompting system for SAM, and (2) Autonomous Mode, where user-curated prompts train a deep learning network to replace manual prompting, fully automating subspace extraction. The interactive tool also serves for quality control, allowing users to refine AI-generated outputs and generate additional constraint sets as needed. With its AI-driven prompting mechanism, SmartScan delivers high-throughput, high-quality subspace extraction with minimal human intervention, enhancing scalability and efficiency. Notably, its adaptable design makes it suitable for extracting regions of interest from ultra-high-resolution satellite imagery across various domains.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 39 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

18 of 39 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023Segment Anythingcited by 8,234
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  8. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  9. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  10. 2019Zero-Shot Semantic Segmentationcited by 245
  11. 2018Comparison of Reinforcement Learning algorithms applied to the Cart Pole problemcited by 13
  12. 2018Learning Dynamics from Kinematics: Estimating 2D Foot Pressure Maps from Video Framescited by 7
6 more
  1. 2022PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarizationcited by 6
  2. 2023Estimating Uncertainty in Landslide Segmentation Modelscited by 3
  3. 2024Thermal Analysis for NVIDIA GTX480 Fermi GPU Architecturecited by 3
  4. 2024SAMIC: Segment Anything with In-Context Spatial Prompt Engineeringcited by 3
  5. 2024Emotion Recognition from the perspective of Activity Recognitioncited by 2
  6. 2023Subspace-Constrained Continuous Methane Leak Monitoring and Optimal Sensor Placementcited by 1

Built on by

Not cited yet.