Related Experiment Video
Updated: Jun 30, 2026
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.7K
Aerial image segmentation using multilevel thresholding based on multi strategy Osprey optimization algorithm
Mohamed Abd Elaziz1,2, Mohammed Azmi Al-Betar3,4, Ahmed A Ewees5
1Department of Mathematics, Faculty of Science, Zagazig University, Zagazig , 14459, Egypt. abd_el_aziz_m@yahoo.com.
Scientific Reports
|March 17, 2026
Summary
This study introduces a modified Osprey Optimization Algorithm (MOOA) for aerial image segmentation. The MOOA enhances image segmentation quality by optimizing multilevel thresholding, improving accuracy in remote sensing applications.
Area of Science:
- Computer Vision
- Remote Sensing
- Image Processing
Background:
- Aerial image segmentation is crucial for diverse applications including urban planning, environmental monitoring, and disaster management.
- Accurate segmentation relies on effective thresholding techniques to extract meaningful information from aerial imagery.
- Existing optimization algorithms may suffer from premature convergence, limiting segmentation performance.
Purpose of the Study:
- To develop an advanced multilevel thresholding technique for aerial image segmentation.
- To enhance the Osprey Optimization Algorithm (OOA) using a multi-strategy mechanism for improved performance.
- To evaluate the efficacy of the proposed Modified Osprey Optimization Algorithm (MOOA) in segmenting aerial images.
Main Methods:
- A modified Osprey Optimization Algorithm (MOOA) was developed incorporating double attractors for enhanced exploration and a dynamic random search for improved exploitation.
- The multi-strategy mechanism in MOOA aims to prevent premature convergence and boost overall performance.
- MOOA was applied to multilevel thresholding for aerial image segmentation and validated using sixteen aerial images.
Main Results:
- The MOOA demonstrated a high capability in determining optimal threshold values, significantly improving segmented image quality.
- Performance metrics such as Peak Signal-to-Noise Ratio (PSNR), Feature Similarity Index Measure (FSIM), and Structural Similarity Index Measure (SSIM) showed substantial improvements.
- Comparative analysis against established multilevel thresholding methods confirmed the superiority of the MOOA.
Conclusions:
- The proposed MOOA effectively addresses the limitations of standard OOA, offering superior performance in aerial image segmentation.
- The developed technique provides a robust solution for accurate information extraction from aerial imagery.
- MOOA represents a promising advancement for computer vision and remote sensing tasks requiring precise image segmentation.
Related Concept Videos
00:56Extraction: Advanced Methods
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is formed in...
01:28Methods of Medium Optimization
Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...