Ultrasonic Object Classification for Driver Assistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ultrasonic-based methods struggle to accurately classify point-like objects, such as poles and traffic signs, due to their low reflectivity and amplitude, which makes it difficult to distinguish them from traversable objects like curbs and speed bumps, leading to potential incorrect warnings or interventions in driver assistance systems.
Innovation Solution
A method using multiple ultrasonic sensors with overlapping fields of vision to determine object positions via lateration, combined with classification parameters like update rate, stability of position, amplitude of echoes, and likelihood of detection, to differentiate between extensive and point-like objects, particularly focusing on the height classification of point-like objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional ultrasonic-based methods are used to detect objects, then objects can be detected in the surroundings, but point-like objects such as poles and traffic signs cannot be reliably distinguished from traversable objects due to low reflectivity and amplitude
Solution Approach 1:
The patent segments the classification process into multiple stages: first distinguishing extensive objects from point-like objects using lateration and object hypotheses, then separately classifying the height of point-like objects using multiple parameters. This segmentation allows specialized handling of point-like objects with low reflectivity.
Solution Approach 2:
The patent introduces multiple classification parameters for point-like objects including update rate, position stability, echo amplitude, and detection likelihood. By changing from single-parameter to multi-parameter classification, the system reliably distinguishes point-like objects despite their low reflectivity.
2Measurement precision
If multiple classification parameters are used for point-like objects, then classification accuracy improves, but system complexity increases
Solution Approach 1:
The classification system is segmented into two independent modules: extensive object detection using lateration, and point-like object height classification using multiple parameters. This modular segmentation manages complexity by separating concerns.
Solution Approach 2:
The object hypothesis framework serves multiple functions: it tracks objects over time, provides position stability assessment, enables amplitude analysis, and supports update rate calculation. This multi-functionality reduces overall system complexity by using a single framework for multiple classification needs.
3Measurement precision
If ultrasonic sensors with overlapping fields of vision are used, then position determination via lateration becomes possible, but the system requires at least two sensors increasing device complexity
Solution Approach 1:
The patent merges the functionality of multiple ultrasonic sensors into a coordinated system where sensors with overlapping fields of vision work together. The lateration algorithm combines data from multiple sensors to achieve precise position determination, making the combined system more effective than individual sensors.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables reliable classification of point-like objects as either traversable or non-traversable, reducing incorrect warnings and interventions, and improving the accuracy of driver assistance systems by effectively distinguishing between collision-relevant and irrelevant objects.
Implementation Method 1
ultrasonic sensors which emit ultrasonic pulses and receive back ultrasonic echoes reflected by objects
Implementation Method 2
distances between the respective ultrasonic sensor and objects in the surroundings reflecting ultrasonic pulses being ascertained via at least two ultrasonic sensors
Data Source
AI summary
A method for classifying objects in the surroundings of a vehicle using ultrasonic sensors which emit ultrasonic pulses and receive ultrasonic echoes reflected by objects. Distances between the sensors and objects reflecting ultrasonic pulses are ascertained via at least two ultrasonic sensors including overlapping fields of vision, and a position determination of the reflecting objects taking place using lateration and the assignment of the received ultrasonic echoes to object hypotheses for distinguishing between extensive objects and point-like objects. A height classification of a point-like object represented by an object hypothesis is carried out, based on an update rate of the object hypothesis, a stability of the position of the object represented by the object hypothesis, the amplitude of the ultrasonic echoes assigned to the object hypothesis, and a likelihood of the ultrasonic sensors receiving an ultrasonic echo from the object which is represented by the object hypothesis, as classification parameters.