Ultrasonic Sensors Calibration

# Ultrasonic Sensors Calibration

## Ultrasonic Sensors Calibration

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
##### Presentation Transcript

1. Ultrasonic Sensors Calibration Omar A. Daud Truc-Vien T. Nguyen May 16, 2008 US Sensor Calibration

2. Plan • Ultrasonic sensors • Calibration • Approaches • Analysis • Conclusion US Sensor Calibration

3. Ultrasonic sensors • Evaluate attributes of a target by interpreting the echoes of sound waves. • Generate high frequency sound waves and evaluate the echo which is received back by the sensor. • Sensors calculate the time interval between sending the signal and receiving the echo to determine the distance to an object. US Sensor Calibration

4. Plan Ultrasonic sensors Calibration Approaches Analysis Conclusion US Sensor Calibration

5. Calibration • In performing a calibration, the following steps are necessary: • Examine the construction of the instrument, identifying the inputs. • Decide which of the inputs are significant for the application. • By holding some inputs constant, varying others, and recording the output(s), develop the desired static input-output relations US Sensor Calibration

6. Plan Ultrasonic sensors Calibration Approaches Analysis Conclusion US Sensor Calibration

7. Static Calibration Approach • All inputs, except one are kept at some constant values. Then the one input under study is varied over some range of constant values, which causes the output(s) to vary over some range of constant values. • Considerable care in choosing the means of determining the numerical values of these inputs. US Sensor Calibration

8. Support Vector Machine (SVM) Approach LibSVM – Polynomial kernel, degree = 3, One vs. One Parameter C = 2; n-fold cross-validation n = 10 12 sensors: accuracy = 58.3667 4 sensors 4,5,6,7: accuracy = 84.5667 3 sensors 4,5,6: accuracy = 85.4333 Correlation between Sensors - Distance

9. Plan Ultrasonic sensors Calibration Approaches Analysis Conclusion US Sensor Calibration

10. Analysis – Sensor 4 US Sensor Calibration

11. Analysis – Sensor 5 US Sensor Calibration

12. Analysis – Sensor 6 US Sensor Calibration

13. Analysis – Three sensors

14. Gaussian distribution Gaussian distribution in six distances

15. Plan Ultrasonic sensors Calibration Approaches Analysis Conclusion US Sensor Calibration

16. Conclusions • Farther is the object from the scene more inaccurate is the measurement of the US sensors. • By the contrary, as the object is near the sensors, the measurement is more accurate. • There is a sort of linear relationship between the input and the output until the measurement of 1 field. • Beyond the 1 field this relationship is lost. US Sensor Calibration