Related Experiment Video
Updated: Jul 31, 2025
09:19
Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
Published on: April 18, 2025
664
Underwater image illumination estimation via an evolving extreme learning machine by an improved salp swarm
Summary
This study introduces a new underwater image illumination estimation model, the modified salp swarm algorithm (SSA) extreme learning machine (MSSA-ELM). The MSSA-ELM model achieves high accuracy and stability for underwater image analysis.
Area of Science:
- Computer Vision
- Robotics
- Artificial Intelligence
Background:
- Underwater images suffer from chromatic aberrations and complex scenes, impacting underwater robot navigation.
- Accurate illumination estimation is crucial for reliable underwater image analysis and robotic decision-making.
Purpose of the Study:
- To propose a novel underwater image illumination estimation model.
- To enhance the accuracy and stability of illumination estimation for underwater robotics.
Main Methods:
- Developed a modified salp swarm algorithm (SSA) extreme learning machine (MSSA-ELM) model.
- Utilized Harris hawks optimization and multiverse optimizer algorithms to refine the SSA.
- Optimized extreme learning machine (ELM) weights and biases using the improved SSA.
Main Results:
- The MSSA-ELM model achieved an average accuracy of 0.9209 in underwater image illumination estimation.
- Demonstrated superior accuracy compared to existing models for underwater image illumination estimation.
- Exhibited high stability and significant performance differences compared to other models.
Conclusions:
- The MSSA-ELM model provides a robust and accurate solution for underwater image illumination estimation.
- This advancement can improve the performance and reliability of underwater robots in complex environments.
