Ultrasonic Object Classification via Position and Direction Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating the height of objects using ultrasonic sensor technology often produce incorrect results when applied to vehicles.
Innovation Solution
A method for classifying objects into object classes based on information from at least one ultrasonic sensor, involving cluster formation, statistical distribution analysis of position and directional information, and decision-making using threshold values and machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If height estimation is performed on all detected objects using ultrasonic sensor technology, then height information can be obtained for various objects, but incorrect results are produced when applied to vehicles
Solution Approach 1:
The method segments objects into different object classes (vehicle, pedestrian, cyclist, animal, other) based on detection patterns from multiple ultrasonic sensors. By dividing the detection space into distinct classes and applying class-specific processing, the system avoids applying uniform height estimation to all objects, thereby preventing incorrect vehicle height measurements while maintaining accurate measurements for appropriate object types.
Solution Approach 2:
The system changes the evaluation parameters based on object class. For vehicles, height estimation is excluded or handled differently, while for pedestrians, cyclists, and animals, standard height estimation methods are applied. This parameter adaptation based on classification results resolves the contradiction by ensuring reliable measurements only for object types where the measurement method is appropriate.
2Measurement precision
If multiple ultrasonic sensors are used to improve detection accuracy, then more reliable object detection is achieved, but computing effort increases due to cluster formation and statistical analysis
Solution Approach 1:
The system performs preliminary clustering and classification of detections from multiple sensors before proceeding to height estimation. By pre-grouping detections into object clusters and determining object classes in advance, the system prepares the data structure needed for accurate measurement while avoiding redundant computations. This preliminary organization reduces the overall computing effort despite using multiple sensors.
Solution Approach 2:
The system applies statistical distribution analysis and cluster formation selectively based on detection quality and object class. Not all detections require full statistical analysis - the system performs computations only where necessary to achieve reliable classification and measurement, avoiding excessive processing of already-clear cases while maintaining precision where needed.
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
Enables accurate and efficient object classification, particularly excluding vehicle detections from height estimation to minimize errors and computing effort.
Implementation Method 1
an item of position information and an item of directional information are assigned to each detection. The position information indicates the reflection location at which an ultrasonic signal of the at least one ultrasonic sensor was reflected
Data Source
AI summary
A method for classifying objects into object classes on the basis of information of an ultrasonic sensor of a vehicle, including receiving multiple detections of a vehicles's ultrasonic sensor. Items of position information and directional information are assigned to each detection. The position information indicates a reflection location where an ultrasonic sensor's signal was reflected and the directional information indicates a direction along which the ultrasonic signal propagates between the reflection location and ultrasonic sensor. The method includes forming detection clusters based on the received detections, with one cluster including multiple detections; calculating statistical distribution information of the position information and the directional information of the detections assigned to the respective cluster; and classifying an object into an object class based on the statistical distribution information of the position information and the directional information of the clusters.