Vehicle Object Positioning Using Camera-Ultrasonic Association
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current park pilot systems face challenges in accurately determining the position of dynamic objects, particularly pedestrians, in close proximity to the vehicle due to limitations in camera image capture and incorrect measurement association, leading to imprecise position and movement estimation.
Innovation Solution
A method utilizing at least two ultrasonic sensors and a vehicle camera to continuously detect sensor data and camera images, employing trilateration and trained machine recognition methods to ascertain the approximate object position of dynamic objects, with a Kalman filter for improved association and classification of reflection origin positions, ensuring accurate positioning even in close range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If camera images are used for position estimation, then dynamic objects can be recognized, but position estimation fails for objects in close range of the vehicle camera
Solution Approach 1:
The patent combines camera-based object recognition with ultrasonic sensor-based position measurement. The camera identifies dynamic objects in the scene, while ultrasonic sensors provide accurate distance measurements for objects in close range (within 5 meters). This merging allows the system to leverage the strengths of both sensors: camera for object identification and ultrasonic for precise near-field positioning.
Solution Approach 2:
Ultrasonic sensors act as an intermediary measurement system that bridges the gap where camera-based position estimation fails. When objects are detected by the camera but their position cannot be accurately estimated due to being in close range, the ultrasonic sensors provide the intermediate position data needed to complete the measurement.
2Reliability
If multiple ultrasonic sensors are used for position determination, then measurement reliability improves, but incorrect association of measurements with object tracks reduces accuracy
Solution Approach 1:
The system uses feedback from multiple sources (camera object recognition, ultrasonic sensor measurements, and existing object tracks) to continuously refine position estimates. The Kalman filter processes this feedback information, comparing predicted object positions with actual sensor measurements to correct associations and improve accuracy over time.
Solution Approach 2:
The patent changes the parameters used for measurement association by incorporating not only position data but also velocity and acceleration information from the Kalman filter. This multi-parameter approach allows for more reliable distinction between different objects, especially when they are close together or have similar ultrasonic signatures.
3Productivity
If camera images are used for close range objects, then objects can be detected, but the objects cannot be completely captured in the camera image
Solution Approach 1:
The patent replaces the mechanical/optical limitation of camera capture with ultrasonic sensing capability. While the camera provides object detection and classification, ultrasonic sensors substitute for the need to optically capture the entire object, providing accurate position measurements even when the object is too close to be fully visible in the camera image.
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 provides accurate and reliable determination of dynamic object positions, including pedestrians within 2 meters of the vehicle, enhancing parking operations by distinguishing between pedestrians and static objects, and improving movement estimation.
Implementation Method 1
The ultrasonic sensors are typically configured to emit an ultrasonic signal. This emitted ultrasonic signal is reflected at obstacles. The reflected ultrasonic signal is once again received by the ultrasonic sensors as an echo signal, and from the propagation time a distance from the obstacle is computed.
Implementation Method 2
from the propagation time a distance from the obstacle is computed
Data Source
AI summary
A method for ascertainment of an approximate object position of a dynamic object in the surroundings of a vehicle. The method includes: detecting sensor data; ascertaining a present reflection origin position of a static or dynamic object as a function of the detected sensor data; detecting a camera image; recognition of the dynamic object as a function of the detected camera image; and ascertaining a present estimated position of the recognized dynamic object relative to the vehicle as a function of the detected camera image. When a position distance between the ascertained estimated position of the recognized dynamic object and the ascertained reflection origin position is less than or equal to a distance threshold value, a classification of the present reflection origin position as belonging to the recognized dynamic object takes place as a function of the underlying sensor data for the ascertainment of the reflection origin position.