Self-Propelled Robot Image Scoring for Obstacle Recognition Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sweeping robots lack the ability to visually recognize obstacles they avoid, leading to poor user experience due to the inability to accurately identify and view obstacles during navigation.
Innovation Solution
An image selection method for self-propelled apparatuses that collects images, scores them based on parameters like angular velocity, distance, obstacle size, position, and fill light status, and selects the highest-scoring images for display to improve obstacle recognition and user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the sweeper uses a sensor to detect obstacles and automatically turns to avoid them, then the sweeper can navigate around obstacles, but the sweeper cannot visually view or accurately recognize the obstacles it avoids
Solution Approach 1:
The patent introduces an image collection device (camera) as an intermediary to capture visual information of obstacles. The camera works alongside the sensor to provide visual documentation of obstacles, allowing the system to both detect and visually record obstacle information for user viewing through the mobile terminal.
Solution Approach 2:
The patent creates a visual copy of the obstacle by capturing images with the camera. These image copies are then transmitted to the user's mobile terminal, allowing the user to view and recognize obstacles remotely, thus preserving visual information that would otherwise be lost.
2Quantity of substance
If the sweeper collects multiple images of obstacles during navigation, then more obstacle information is captured, but it becomes difficult to determine which image to display to the user
Solution Approach 1:
The patent implements a feedback mechanism where the system evaluates multiple captured images against a set of scoring rules and selects the optimal image for display. The scoring rules consider factors like image quality, obstacle visibility, and capture conditions, providing automated feedback to determine the best representation of the obstacle.
Solution Approach 2:
The patent changes the parameter of image selection by introducing multiple scoring criteria (image quality, obstacle area ratio, capture distance, etc.) to evaluate and rank different images. This transforms the selection process from a simple choice to a multi-parameter optimization problem, automatically identifying the most informative image.
3Adaptability or versatility
If the sweeper captures images at various distances and angles from obstacles, then more comprehensive obstacle views are obtained, but the image quality and usefulness for recognition vary significantly
Solution Approach 1:
The patent applies parameter changes by establishing scoring rules that evaluate images based on multiple parameters including capture distance, angle, lighting conditions, and obstacle area ratio. This allows the system to objectively assess image quality across different capture scenarios and select the most suitable image for obstacle recognition.
Solution Approach 2:
The patent performs preliminary evaluation of captured images using scoring rules before displaying them to the user. By pre-assessing image quality and obstacle visibility, the system ensures that only high-quality, informative images are presented, maintaining measurement precision despite capture flexibility.
Data Source
AI summary
An image selection method, applied to a self-propelled apparatus, includes: collecting an image from a surrounding environment through an image collection device during the self-propelled apparatus travels; scoring the image according to a scoring rule when there is a recognizable obstacle in the collected image, wherein a value of the scoring is used to indicate an imaging quality of the recognizable obstacle in the image; and selecting an image that comprises the recognizable obstacle and that has a highest score as a to-be-displayed image in response to receive a request to view the image of the recognizable obstacle. A computer-readable storage medium and a self-propelled apparatus are further provided.