Image selection method, self-propelled device, and computer storage medium
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Sweepers lack the ability to visually recognize obstacles and provide accurate images of them, leading to poor user experience.
Innovation Solution
An image selection method for self-propelled apparatuses that involves collecting images, scoring them based on parameters like angular velocity, distance, obstacle size, position, and fill light, and selecting the image with the highest score for display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If multiple cameras are arranged in a matrix to capture images of a conveyee, then the coverage area and measurement precision are improved, but the device complexity and number of image processing combinations increase exponentially
Solution Approach 1:
The patent divides the conveyee into multiple regions of interest (ROIs), each captured by a specific camera. Instead of processing all camera combinations, the system segments the image processing task by assigning specific ROIs to specific cameras based on their spatial positions, thereby reducing the complexity while maintaining comprehensive coverage.
Solution Approach 2:
The patent performs preliminary determination of the conveyee's position and orientation before selecting which camera images to use. By pre-calculating the conveyee's spatial parameters and determining the relevant ROI in advance, the system avoids the need to process all possible camera combinations, thus reducing computational complexity while ensuring accurate measurement.
2Measurement precision
If all camera images are used to determine conveyee position and orientation, then measurement precision is improved, but processing time and computational load increase
Solution Approach 1:
The patent applies partial action by selecting only the necessary subset of camera images required to determine the conveyee's position and orientation within a specific ROI. Instead of using all camera images, the system identifies and processes only those cameras whose fields of view intersect with the conveyee's ROI, thereby maintaining measurement precision while significantly reducing processing time.
Solution Approach 2:
The patent segments the image processing task by dividing the conveyee into multiple ROIs and assigning specific cameras to capture and process each ROI. This segmentation allows parallel processing of different ROIs and eliminates the need to process all camera images comprehensively, thus reducing overall processing time while maintaining precision through focused analysis of relevant regions.
3Area of stationary object
If the field of view of each camera is made larger to cover more area, then the coverage is improved, but the measurement precision of position and orientation deteriorates
Solution Approach 1:
The patent segments the overall measurement task into multiple ROIs, each captured by a camera with an optimized field of view. By dividing the conveyee into smaller ROIs rather than attempting to capture the entire conveyee in a single wide field of view, the system maintains high measurement precision for each segment while achieving comprehensive coverage through the combination of multiple segmented views.
Data Source
Figure 1~2
AI summary
An image selection method, a self-propelled device, and a computer readable storage medium. The method comprises: when travelling, a self-propelled device first performs image acquisition on the surrounding environment by means of an image acquisition apparatus (101); then, when an acquired image contains an identifiable obstacle, the image is given a score according to a scoring rule, the score being for indicating the imaging quality of the identifiable obstacle in the image (102); and finally, after receiving a command requesting to view an image of the identifiable obstacle, the image that contains the identifiable obstacle and that has the highest score is selected as an image to be displayed (103).