Research on a Key Method for the Optimization of Port Vessel Detection Based on an Improved Multi-Structural Morphology Approach
Preprint
- 24 September 2024
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Some vessels do not comply with maritime rules, particularly in port and safety zones; they must be detected to avoid incidents. Due to background noise and congestion interference at the sea surface, it is difficult to accurately detect these vessels when it is getting dark, especially smaller ones. For these reasons, this paper proposes and develops an improved multi-structural mor-phology (IMSM) approach to eliminate all this noise and interference. The vessel target is sepa-rated from the sea surface backdrop using weighted morphological filtering of many groups of structural components. Then, the neighborhood-based adaptive fast median filtering is used to filter out impulse noise. Finally, the characteristic morphological model of the vessel target is established using the connected domain; this permits eliminating the sea surface congestion and locating vessels movement in real-time. Multiple tests were carried out in a small and discon-tinuous area of the vessel’s inter-frame motion. The results of many groups of data collected show that the proposed approach can effectively eliminate the background noise and congestion in-terference in the monitoring video. The detection accuracy rate and the processing time have increased by approximately 3.91% and 1.14s, respectively.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- A sea clutter suppression algorithm for over-the-horizon radar based on dictionary learning and subspace estimationDigital Signal Processing, 2023
- Seabird surveillance: combining CCTV and artificial intelligence for monitoring and researchRemote Sensing in Ecology and Conservation, 2023
- Multi-level contour combination features for shape recognitionComputer Vision and Image Understanding, 2023
- Deep Hough Transform for Semantic Line Detection2020
- Exploring AIS data for intelligent maritime routes extractionApplied Ocean Research, 2020
- Using Three-Frame Difference Algorithm to Detect Moving Objects2019
- Median Filtering: A New InsightJournal of Mathematical Imaging and Vision, 2016
- Contour Based Shape Matching for Object Recognition2016
- An improved simple morphological filter for the terrain classification of airborne LIDAR dataISPRS Journal of Photogrammetry and Remote Sensing, 2013
- The design of Top-Hat morphological filter and application to infrared target detectionInfrared Physics & Technology, 2006