Object Recognition via Sensor Signal Pairing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object recognition methods are impractical for reliable identification as they require defining all conceivable expressions of object characteristics beforehand, making it impossible to identify objects with absolute accuracy without extensive data collection.
Innovation Solution
A method involving the observation of an object using multiple sensors to form identification characteristic pairs, which are then compared to stored object characteristic classes using Mendelian genetics principles, allowing for reliable identification even if all object characteristics and their expressions are not known or detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all object characteristics and their expressions are defined and detected beforehand, then object identification accuracy is improved, but device complexity and data collection effort increase enormously
Solution Approach 1:
The patent applies partial action by not requiring detection of all possible object characteristics, but only a selected subset sufficient for identification. The system detects object characteristics using sensors and determines object identity based on partial information from sensor signal patterns, avoiding the need to define and detect all conceivable expressions of all object characteristics beforehand.
Solution Approach 2:
The patent implements universality through a sensor system that can detect multiple different object characteristics using the same sensors. The evaluation unit universally evaluates sensor signal patterns to identify different objects based on their characteristic expressions, making the system adaptable to various object types without requiring separate specialized detection mechanisms for each characteristic.
2Reliability
If multiple sensors are used to detect object characteristics, then object identification reliability is improved, but device complexity increases
Solution Approach 1:
The patent merges information from multiple sensors by evaluating sensor signal patterns collectively. The evaluation unit combines signals from different sensors to determine object identity, where the sensor system includes multiple sensors that detect different object characteristics and their expressions, and the evaluation unit integrates these signals to identify objects based on pattern recognition rather than requiring each sensor to independently identify objects.
3Measurement precision
If all object characteristic expressions are detected to achieve 100% recognition accuracy, then identification certainty is improved, but productivity and processing time decrease
Solution Approach 1:
The patent applies partial action by determining object identity based on a subset of detected sensor characteristics rather than requiring all possible characteristics. The system evaluates sensor signal patterns to identify objects with sufficient certainty without exhaustively detecting every conceivable object characteristic expression, thereby maintaining both accuracy and processing efficiency.
Data Source
AI summary
A method for recognizing an object that has a plurality of expressions of abstract object characteristics, and is associated with an object characteristic class of a hierarchical system of object characteristic classes stored in a first memory. The method includes i) observing at least one location at which the object is presumed to be present, using a plurality of sensors in a sensor population, each of said sensors responding to at least one object characteristic and accordingly emitting a sensor signal; ii) checking whether each of the emitted sensor signals exceeds a specified threshold value for the sensor signals, and accepting sensor signals which exceed the threshold value; iii) pairing combinations of the sensor characteristics, for the accepted sensor signals obtained in ii) to form identification characteristic pairs; iv) comparing the population of identification characteristic pairs obtained in iii) to the object characteristic classes stored in the first memory; and v) identifying the object, based on the object characteristic class, whose object characteristic pairs are identical to the identification characteristic pairs obtained in iii).