Maritime Search Hue Segmentation for Survival Equipment Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Maritime patrol aircraft face difficulties in detecting shipwrecked persons and survival equipment due to low contrast and adverse lighting conditions, leading to low probability of timely rescue.
Innovation Solution
A method and device using a camera, computer, and display system that captures images, expresses pixel hues in a colorimetric system, selects and highlights pixels within specific color ranges, and modifies images to enhance visibility, allowing better detection of survival equipment in maritime environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If the patrol aircraft scans large areas from significant distance, then the coverage area increases, but the survivor or survival equipment occupies only a few pixels making detection difficult
Solution Approach 1:
The method segments the image processing task into multiple stages: initial full-image scanning for coverage, followed by hue-based segmentation to isolate potential survivors, and finally highlighted display segmentation to draw operator attention to specific regions of interest
Solution Approach 2:
The patent transforms the detection problem from spatial dimension alone to include color dimension by expressing pixel hues in a colorimetric system, allowing detection based on color characteristics rather than just spatial position and size
2Difficulty of detecting and measuring
If the operator relies on color contrast to identify survivors, then identification capability is improved, but adverse lighting conditions reduce detection probability
Solution Approach 1:
The patent changes the parameter used for detection from intensity-based (affected by lighting) to hue-based (color angle in colorimetric system), which is more invariant to lighting conditions. The hue parameter P represents the angular position in color space, which remains relatively stable under varying illumination
Solution Approach 2:
The method replaces the human operator's visual system (which is sensitive to lighting variations) with a computational color analysis system that calculates hue parameters objectively, substituting biological detection with computational detection that is more robust to environmental conditions
3Length of stationary object
If the survival equipment is viewed from significant distance, then the search radius increases, but the equipment represents only a few pixels reducing detectability
Solution Approach 1:
The patent exploits the color characteristics of survival equipment by expressing pixel hues in a colorimetric system and selecting pixels whose hue parameter P falls within a predetermined range corresponding to typical survival equipment colors, making detection independent of the number of pixels
Solution Approach 2:
The patent introduces an intermediary processing step that converts raw pixel data into hue parameter values, then compares these values against a predetermined range for survival equipment colors. This intermediary color-space transformation acts as a mediator between the raw image data and the detection decision
Data Source
Figure 1~2
Figure 3
AI summary
The invention relates to a method for assisting with the search for an element (E) having a pre-defined hue in an environment, the method comprising the supply of at least one colour image, the or each image comprising pixels, said method being characterised in that it comprises the selection, in the or each image, of the pixels having a hue of which the bijection-associated value of the parameter is comprised between a first and a second value, the first and second values being selected so that the group of hues of which the bijection-associated value of the parameter is comprised between the two selected values comprises the pre-defined hue.