Vessel Path Correction Using Grid-Based Obstacle Distance Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned surface vehicles face challenges in accurate route planning due to interference from water surface conditions, such as light reflection and undulation, which affect LiDAR measurement accuracy and image recognition, requiring real-time processing and correction of obstacle distances.
Innovation Solution
An assistance system using a machine-readable grid to determine obstacle distances, combined with sensor data correction, eliminates environmental deviations and provides real-time distance information without relying on LiDAR, suitable for undulating waters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If LiDAR is used for distance detection on water surface, then measurement speed is fast, but measurement accuracy deteriorates due to water surface interference such as light reflection and undulation
Solution Approach 1:
The patent replaces LiDAR (optical system) with image measurement technology (visual system) for distance detection. The processor analyzes image data to calculate distances based on known dimensions of reference objects in the scene, avoiding the water surface interference problems that affect optical LiDAR measurements.
Solution Approach 2:
The patent introduces machine-readable grids and reference objects as intermediaries between the measurement system and the target. These reference objects with known dimensions serve as mediators that enable accurate distance calculation through image analysis, bridging the gap between the camera and the target object.
2Object-affected harmful factors
If image measurement is used for obstacle detection, then environmental resistance is improved, but measurement accuracy deteriorates due to water surface undulation causing obstacle displacement and swinging
Solution Approach 1:
The patent performs preliminary identification and tracking of reference objects in the scene. By pre-establishing the known dimensions and positions of reference objects, the system can compensate for water surface undulations when calculating target distances, maintaining accuracy despite environmental disturbances.
Solution Approach 2:
The system uses reference objects with known dimensions as feedback references. By comparing the apparent size and position of these reference objects in the image against their known dimensions, the processor can calculate and compensate for distortions caused by water surface undulation, thereby maintaining measurement accuracy.
3Ease of operation
If real-time image processing is performed for route monitoring, then route correction capability is improved, but processing speed deteriorates due to the complexity of real-time analysis
Solution Approach 1:
The patent extracts and utilizes only the essential features from image data for distance calculation - specifically focusing on identifying reference objects with known dimensions and calculating distances based on their apparent size. This selective extraction of critical information reduces processing complexity while maintaining real-time capability.
Solution Approach 2:
The system changes the approach from complex full-scene analysis to simplified parameter-based calculation. By using the known dimensions of reference objects as fixed parameters and calculating distances based on simple geometric relationships in the image, the processing becomes computationally efficient enough for real-time operation.
Data Source
AI summary
The assistance system for correcting vessel path comprises a receiver, a memory, at least one sensor, a processor and a display. The processor connects to the receiver, the memory and the at least one sensor, and the display is coupled to the processor. The assistance system based on the processor is able to be utilizing the preset machine-readable grid in determining the distance parameters of obstacles above water, and in which these distance parameters are corrected by using the sensor measurement data acquired by the at least one sensor. Thereby the assistance system could finish the distance measurements of abovementioned obstacles without using Lidar, and even in the case of high-undulating water surface.