Return
Agent-Based Optimal Control for Image Processing
DOI:10.1016/j.apm.2026.116967.png)
Abstract
En 中文
• An agent-based mathematical model for image colour segmentation and quantization. • Optimal control problem for agent interactions, preserving image structures. • Total variation regularization enhances edge preservation and reduces noise. • Efficient primal-dual ADMM algorithm with GPU implementation for scalability. • Numerical validation on real images demonstrating accurate dynamic clustering.
Keywords:
Multi-agent systems
Image processing
Unsupervised learning
Augmented Lagrangian
Primal-dual splitting
Method of multipliers
CUDA implementation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.1
Papers:
1.1K
Citations:
2.8W
Organization
No organization information available

