Cooktop Boil Detection Using Motion Vector Histograms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing boil detection systems, such as motion sensors and temperature sensors, suffer from inaccuracies and false positives, leading to issues like overcooking, splattering, and potential fires due to incomplete heat reduction during boiling events.
Innovation Solution
A computer vision algorithm is applied to imagery from a camera positioned above the cooktop to detect boiling events by calculating dissimilarity scores between motion vectors in consecutive frames and pre-learned histograms, accurately distinguishing between boiling and non-boiling states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If motion sensors are used to detect boiling events, then the system can detect motion at the cooktop, but human motion or rising steam triggers false positives
Solution Approach 1:
The system segments the motion detection task by analyzing individual pixel changes and organizing them into motion vectors, then further segments the analysis by creating histograms of motion characteristics. This granular segmentation allows the system to distinguish between the specific motion patterns of boiling liquid and other motions like steam or human activity.
Solution Approach 2:
The system applies the principle of color changes metaphorically by transforming visual information into a different representation space - converting image frames into motion vector histograms. This transformation allows the system to detect boiling by comparing histogram characteristics rather than raw visual patterns, effectively distinguishing boiling from false positives.
2Measurement precision
If temperature sensors are used to detect boiling events, then the system can measure temperature at the cooktop, but the generally heated environment causes significant measurement errors
Solution Approach 1:
The system replaces the thermal measurement approach with a visual motion analysis approach. Instead of using temperature sensors that struggle in heated environments, the system uses a camera to capture visual motion patterns and analyzes them through histogram comparison. This substitution of measurement modality eliminates the interference from the generally heated environment.
Solution Approach 2:
The system changes the measurement parameter from temperature to motion characteristics. By detecting boiling through motion patterns in video frames rather than temperature readings, the system avoids the problem of temperature sensors being unable to distinguish boiling temperature from the generally heated cooktop environment.
3Reliability
If a camera and computer vision algorithm are used to detect boiling events, then the system can accurately distinguish boiling from non-boiling states, but the device complexity increases
Solution Approach 1:
The system extracts only the essential features needed for boil detection - motion vectors and their histogram characteristics - from the full video frames. By taking out and analyzing only these relevant features rather than processing entire images, the system achieves high accuracy while managing computational complexity.
Solution Approach 2:
The system performs preliminary action by pre-learning and storing histograms of boiling liquid characteristics before actual detection. During operation, it simply compares current motion histograms against these pre-established templates, avoiding the need for complex real-time analysis and reducing computational complexity while maintaining high reliability.
Data Source
AI summary
Systems and methods for boil detection are provided. One example system includes a vision sensor positioned to collect imagery depicting the cooktop and one or more processors implementing instructions to perform operations. The operations include obtaining a first frame of imagery and a second frame of imagery from the vision sensor. The first frame of imagery and the second frame of imagery respectively depict the cooktop. The operations include identifying a plurality of motion vectors based on the first and second frames of imagery. The operations include generating a histogram describing a characteristic of the plurality of motion vectors. The operations include calculating a dissimilarity score. The dissimilarity score describes a difference between the histogram and a pre-learned histogram. The pre-learned histogram describes the characteristic for imagery depicting boiling liquid. The operations include determining whether a boiling event is occurring at the cooktop based at least in part on the dissimilarity score.