Related Experiment Video
Updated: Jul 18, 2025
11:24
Evaporation-reducing Culture Condition Increases the Reproducibility of Multicellular Spheroid Formation in Microtiter Plates
Published on: March 7, 2017
7.0K
Multi-threshold image segmentation of 2D OTSU inland ships based on improved genetic algorithm
Zhongbo Peng1, Lumeng Wang1, Liang Tong1
1School of shipping and naval architecture, Chongqing Jiaotong University, Chongqing, China.
Plos One
|August 25, 2023
Summary
This study introduces an improved genetic algorithm for ship image segmentation in waterways, enhancing accuracy and speed for navigational safety. The method efficiently extracts ship information from complex scenes, aiding waterway management.
Area of Science:
- Computer Vision
- Image Processing
- Artificial Intelligence
Background:
- Waterway transportation relies on navigational safety, requiring efficient ship monitoring.
- Supervisors need rapid extraction of ship information from complex waterway images.
- Current methods face challenges in complex inland navigation environments and data acquisition.
Purpose of the Study:
- To develop a precise and efficient algorithm for segmenting inland ship images.
- To improve the accuracy and speed of ship detection in complex waterway scenes.
- To address limitations in acquiring target datasets for inland navigation.
Main Methods:
- Proposed a two-dimensional OTSU (Otsu's method) multi-threshold image segmentation algorithm.
- Utilized an improved genetic algorithm to enhance search accuracy and efficiency.
- Implemented the algorithm for real-time segmentation of complex inland ship images.
Main Results:
- The improved algorithm demonstrated enhanced search accuracy and efficiency.
- Achieved superior image thresholding accuracy and reduced algorithm time complexity.
- Experimental verification confirmed excellent evaluation indexes and real-time segmentation capabilities.
Conclusions:
- The developed algorithm effectively addresses challenges in complex inland navigation environments.
- The method facilitates quick acquisition of relevant ship information for waterway management.
- The approach has potential applications in other optimization problems using metaheuristic algorithms.
