Water Area Object Detection Map With Near-Range Coverage Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing water area and surrounding object detection systems inaccurately indicate objects near the imager due to excessive reduction in probability distribution ranges caused by distance measurement errors, leading to gaps between adjacent ranges and potential collisions.
Innovation Solution
A system that includes an imager on a hull to capture images, with a controller that sets a lower limit for object presence ranges near the imager and adjusts range sizes based on distance measurement errors, ensuring overlap and accurate representation of objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the probability distribution range is reduced according to distance measurement error, then measurement precision is improved, but reliability deteriorates because gaps occur between adjacent ranges causing collision risks
Solution Approach 1:
The patent changes the parameter of probability distribution range size from being purely error-proportional to having a distance-dependent formulation. Specifically, it sets the range radius to a fixed value for distances within a threshold, and to an error-proportional value for distances beyond the threshold. This parameter change resolves the contradiction by ensuring adequate coverage for near objects while maintaining precision for far objects.
2Reliability
If the probability distribution range is increased to ensure coverage, then reliability is improved, but device complexity increases due to additional processing requirements
Solution Approach 1:
The patent applies local quality by making the probability distribution range size adaptive to local conditions (distance to object). Instead of using a uniform range size throughout the environment map, it locally adjusts the range radius based on the distance to each detected object, using a fixed radius for near objects and an error-proportional radius for far objects. This resolves the contradiction by providing enhanced reliability only where needed (for near objects) without unnecessarily increasing overall system complexity.
Data Source
AI summary
A water area object detection system includes an imager to capture an image around a hull, and a controller configured or programmed to perform a control to detect a feature point corresponding to an object in the image together with a distance to the feature point based on the image captured by the imager to create a water area map in which an object presence range including a likelihood that the object is present is set around the feature point. The controller is configured or programmed to reduce the object presence range as the distance from the imager to the feature point decreases, and set a size of the object presence range to a lower limit when the distance from the imager to the feature point is equal to or less than a predetermined distance.