Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 2, 2025T-CommOpen Access

Multi-scale image segmentation in solving problems of oil spill detection on the basis of convolutional neural networks

View Full Paper
Ask AI
Bookmark
Share

Authors

DVD. V. VasilievaSDSergey DvornikovСДС. С. Дворников

Discussion

Loading...

Member takes

Overview

Proposed approach enhances oil spill detection reliability in ocean monitoring, suggesting better neural network performance.

Key Points

  • The proposed model reduces the computational load by approximately six times compared to canonical approaches.
  • Detection results coincided with visual analysis data in 67% of cases, significantly improving reliability.
  • Using multi-scale image segmentation with the K-means algorithm enhances detection in areas with high water surface variability.
  • This solution allows for effective processing of large images, vital for ecological monitoring of seas and oceans.

Cite This Study

Vasilieva et al. (2025) studied this question.

synapsesocial.com/papers/68de79595b556a9128e1a232https://doi.org/10.36724/2072-8735-2025-19-6-16-24
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Developing a Comprehensive Oil Spill Detection Model for Marine Environments2024 · 25 citations
  2. 2A Systematic Evaluation of CNN Configurations for Multiclass Oil Spill Classification in Hyperspectral Images2026
  3. 3A Novel Multi-Scale Feature Map Fusion for Oil Spill Detection of SAR Remote Sensing2024 · 26 citations
  4. 4Adaptive oil spill detection network for scene-based PolSAR data using dynamic convolution and boundary constraints2024 · 18 citations
  5. 5Using Convolutional Neural Network for the Detection of Offshore and Onshore Oil Spills2025