Port Vessel Monitoring via AI Object Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current port district sea line monitoring systems rely heavily on human personnel to continuously observe radar, AIS receivers, and cameras, leading to potential delays in accident detection due to decreased concentration and high personnel costs, especially for vessels without automatic identification systems.

Innovation Solution

A multiple vessel monitoring system comprising a processing module, storage module, and camera that uses object recognition AI to categorize floating objects as vessels or non-vessels, switching between patrol, monitor, and auxiliary modes to optimize surveillance, with a database of vessel and non-vessel sample data for accurate identification and tracking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If human personnel continuously observe radar, AIS receivers, and cameras to monitor floating objects, then monitoring coverage can be maintained, but personnel costs increase and detection timeliness decreases due to human concentration limitations

Engineering Contradiction:
Improvedetection timelinessVSAvoidpersonnel requirements
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system enables self-service monitoring through automated object recognition technology. The processing module automatically identifies and tracks floating objects using image data from cameras, eliminating the need for continuous human observation. The system performs self-monitoring by comparing detected objects against the vessel identity database and automatically switching between patrol and monitor modes based on detection results.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical human observation system with an automated electronic recognition system. The processing module uses object recognition algorithms to detect and identify floating objects, substituting human visual monitoring with automated image processing and pattern recognition technology.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If AIS signals are used to manage floating object activities, then vessels with AIS can be tracked, but vessels without AIS (especially those under 20 tons) cannot be recognized

Engineering Contradiction:
Improvevessel coverageVSAvoididentification accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system achieves universality by implementing multi-functional monitoring capabilities. It can detect both AIS-equipped vessels and non-AIS vessels through image recognition. The processing module identifies objects regardless of their AIS status, and the system adapts its monitoring strategy based on whether the detected object is a vessel or non-vessel, providing comprehensive coverage for all floating objects.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces image recognition technology as an intermediary method to bridge the gap between AIS-equipped and non-AIS vessels. When AIS signals are unavailable or insufficient, the system uses camera images and object recognition algorithms to identify and track floating objects, providing an alternative identification pathway that expands coverage to include smaller vessels without AIS.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Area of stationary object

If the system monitors all floating objects in large port areas, then comprehensive surveillance is achieved, but the complexity of managing multiple vessels and non-vessels increases

Engineering Contradiction:
Improvemonitoring areaVSAvoidsystem complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The system applies segmentation by dividing the monitoring area into functional zones and categorizing detected objects into distinct groups (vessels and non-vessels). The processing module segments the monitoring task by identifying object types and applying different monitoring strategies to each category, managing complexity through structured classification and zone-based surveillance.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20240177503A1Port district sea line multiple vessel monitoring system and operating method thereof
Publication Date: 2024.05.30 SHIP & OCEAN INDUSTRIES R&D CENTER
  • US20240177503A1 patent drawing
  • US20240177503A1 patent drawing

AI summary

The present invention discloses a port district sea line multiple vessel monitoring system and operating method thereof. Specifically, the port district sea line multiple vessel monitoring system comprises a processing module, a storage module, a camera and a floating object information receiving module. The port district sea line multiple vessel monitoring system may automatically recognize image classification of water surface object, therefore to determine operation of patrol mode, monitor mode or auxiliary recognizing mode for satisfying the needs of monitoring of port district sea line.