Image Analysis Using S-V Deviation for Non-Working Region Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image analysis technologies in intelligent devices, such as lawn mowers, struggle to accurately distinguish between working and non-working regions, leading to reduced efficiency and potential damage from collisions with obstacles.
Innovation Solution
An image analysis method that involves obtaining saturation and value channel images, calculating a relative deviation value image, extracting contours, and determining target parameter values to identify non-working regions based on specific conditions, using formulas and thresholds to enhance recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing image analysis technology is used to recognize lawn regions, then the intelligent device can operate autonomously, but the non-lawn regions cannot be effectively recognized leading to collisions and reduced efficiency
Solution Approach 1:
The patent segments the image analysis process into multiple independent modules: HSV color space conversion, saturation-channel/value-channel difference calculation, contour extraction, and regional recognition. Each module processes specific features independently, allowing the system to distinguish lawn regions from non-lawn regions through combined analysis of multiple features rather than relying on a single recognition method.
Solution Approach 2:
The patent transforms the image from RGB color space to HSV color space, then extracts specific parameters (saturation channel S and value channel V) to calculate their difference. By changing the parameter representation from standard RGB to HSV and then to S-V difference, the system enhances the distinguishability between lawn and non-lawn regions, improving recognition accuracy and preventing collisions.
2Measurement precision
If traditional image analysis methods are applied, then the processing is simple, but the recognition of non-lawn regions is inaccurate
Solution Approach 1:
The patent extracts only the necessary features from the image for region differentiation: the saturation channel S and value channel V from HSV color space. By taking out and focusing on these specific channels and their difference, the system achieves accurate lawn/non-lawn region differentiation without processing all image data, balancing precision with computational efficiency.
Solution Approach 2:
The patent transitions from analyzing images in the standard RGB three-dimensional color space to the HSV color space, and further to a two-dimensional feature space defined by the saturation and value channels. This dimensional transformation creates a new perspective for region differentiation, enhancing the separation between lawn and non-lawn regions while managing processing complexity.
Data Source
AI summary
An image analysis method includes the steps of obtaining a saturation channel image and a value channel image according to an original image; obtaining a relative deviation value image based on the saturation channel image and the value channel image, wherein the relative deviation value image represents relative deviations between saturation and value; extracting several contours from the relative deviation value image; determining target parameter values corresponding to each contour; and Determining according to analysis results of the target parameter values corresponding to each contour whether there is a non-working region in the original image. A related image analysis apparatus, computer device, and computer readable storage medium are also disclosed.