Ultrasonic Sensor Dynamic Object Classification via Multi-Cycle Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ultrasonic sensors in motor vehicles face limitations in detection accuracy and dynamic object recognition, leading to incorrect representation of environmental conditions, particularly in distinguishing between static and dynamic objects, which affects parking assistance systems.
Innovation Solution
A method utilizing multiple detection cycles with ultrasonic sensors to feed information into an assessment model, allowing classification of objects as static or dynamic, and predicting the movement of dynamic objects to determine suitable parking spaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Length of stationary object
If ultrasonic sensors are used to detect objects in the surrounding area, then the detection range is extended, but the detection accuracy and ability to distinguish dynamic objects deteriorates
Solution Approach 1:
The system dynamically updates object states by continuously comparing detection results across multiple cycles. Objects are re-evaluated in each cycle, and their static/dynamic status is updated based on position changes, allowing the system to adapt to moving objects while maintaining accurate detection over extended ranges
Solution Approach 2:
The system implements feedback by comparing detection results from multiple cycles. The position of detected objects is compared across cycles, and based on this feedback, objects are classified as static or dynamic. This feedback mechanism enables the system to distinguish dynamic objects even at greater distances where single-cycle detection accuracy is limited
2Area of stationary object
If ultrasonic sensors detect objects at greater distances, then the coverage area increases, but the angular accuracy and detection precision deteriorates
Solution Approach 1:
The system applies dynamic state updates by continuously re-evaluating object positions across multiple detection cycles. Objects that show position changes beyond a threshold are reclassified as dynamic, allowing the system to maintain accurate angular discrimination over larger coverage areas through temporal rather than spatial differentiation
Solution Approach 2:
The system transitions from relying solely on spatial/angular precision to incorporating temporal dimension for object classification. By adding the time dimension through multiple detection cycles, the system can distinguish dynamic objects based on their movement over time, compensating for reduced angular accuracy at greater distances
3Device complexity
If conventional ultrasonic detection is used, then the device complexity is low, but the ability to correctly represent environmental conditions and distinguish dynamic objects deteriorates
Solution Approach 1:
The system implements dynamic object state tracking by continuously updating object classifications based on position changes across detection cycles. This dynamic approach allows the system to correctly represent environmental conditions with minimal additional complexity, as it reuses existing sensor data through temporal comparison rather than adding complex hardware
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
Enhances the precision of object classification and movement prediction, enabling more accurate assessments and reducing unnecessary waiting times by correctly identifying dynamic objects and their movement patterns.
Implementation Method 1
the surrounding area is detected using at least one vehicle-mounted ultrasonic detection device
Implementation Method 2
A specific clearance is then generated depending on the distance between a vehicle-mounted ultrasonic sensor and an object
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
The invention relates to a method for detecting an object (12, 13, 14) in an environment (7, 7', 8, 8') of a motor vehicle (1, 1'), in which the environment (7, 7', 8, 8') is detected by at least one vehicle-side ultrasonic detection device (4), wherein a detection cycle for detecting the environment (7, 8) is carried out with the ultrasonic detection device (4) at at least two different times (t0, t1, t2, t3), and the information about an object (12, 13, 14) in the environment (7, 8) acquired in the two detection cycles is provided to an evaluation model, wherein the evaluation model assesses, depending on this information from the ultrasonic detection device (4), whether the object (12, 13, 14) is classified as a dynamic object (12). The invention also relates to a driver assistance system (2) and a motor vehicle (1), as well as a computer program product.