Marine Vessel Vision Docking for Available Berth Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying available docking positions for a marine vessel is challenging due to the difficulty in distinguishing docks from other long, straight structures like barges or retaining walls, and ensuring sufficient open water for docking.
Innovation Solution
A system using a combination of image segmentation and object detection models to identify docks and assess adjacent water availability, enabling automatic maneuvering to a suitable docking position without user intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If object detection models are used to identify docks, then docking position identification is enabled, but difficulty in distinguishing docks from other long straight structures persists
Solution Approach 1:
The system segments the dock identification task into multiple components: first detecting long straight structures, then classifying them as docks or other structures using additional image data and machine learning models. This multi-stage segmentation approach resolves the contradiction by breaking down the difficult detection task into manageable steps that improve both detection capability and identification accuracy.
Solution Approach 2:
The system introduces intermediary elements including multiple imaging devices capturing different views, machine learning models for classification, and a graphical user interface as an intermediary between detection and final identification. These intermediaries enable the system to overcome the difficulty of directly distinguishing docks from similar structures by adding layers of analysis and verification.
2Extent of automation
If automatic docking identification system is implemented, then user intervention is reduced, but system complexity increases
Solution Approach 1:
The vision system is designed with multi-functionality, using the same imaging devices and processing infrastructure for both dock identification and maneuvering guidance. By making the system universal rather than specialized for single functions, the patent reduces overall complexity while maintaining high automation capability across multiple tasks.
Solution Approach 2:
The system incorporates self-service mechanisms where the graphical user interface automatically presents dock options to the user and the propulsion system automatically executes maneuvering based on user selection. This self-service approach maximizes automation while minimizing the complexity of user interaction, as the system handles most operations autonomously.
3Measurement precision
If multiple imaging devices are used to capture marine environment, then docking position identification accuracy is improved, but device complexity increases
Solution Approach 1:
The system merges data from multiple imaging devices through a unified processing pipeline that combines images and generates composite views. By merging the functionality of multiple devices into a coordinated system rather than treating them as separate independent units, the patent achieves improved identification accuracy while managing device complexity through integrated control and processing.
Data Source
AI summary
A system for automatically identifying available docking positions using a vision system of a marine vessel is provided, the system comprising: an imaging device, wherein the imaging device is configured to be mounted to the marine vessel with an associated field of view of an environment of the marine vessel; and one or more hardware processors configured to: identify, based on image data captured using the imaging device, a dock instance; determine, based on the image data, whether the dock instance is available for docking; indicate that the dock instance is an available docking position; and cause the marine vessel to maneuver to the available docking position.