1 / 25

SirenDetect

SirenDetect. Jennifer Michelstein Department of Electrical Engineering Adviser: Professor Peter Kindlmann May 1, 2003. Alerting Drivers about Emergency Vehicles. GPS. INSIDE A CAR. BUTTONS. CALENDAR/MINI PC. INSIDE A CAR. RADIO, CD PLAYER, SPEAKERS. PHONE WITH BUTTONS IN STEERING WHEEL.

basil
Télécharger la présentation

SirenDetect

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. SirenDetect Jennifer Michelstein Department of Electrical Engineering Adviser: Professor Peter Kindlmann May 1, 2003 Alerting Drivers about Emergency Vehicles

  2. GPS INSIDE A CAR BUTTONS

  3. CALENDAR/MINI PC INSIDE A CAR RADIO, CD PLAYER, SPEAKERS PHONE WITH BUTTONS IN STEERING WHEEL

  4. Cars have too many distractions. Added features = Less attention to the road and other vehicles. Driving has become perilous.

  5. Using microphones, collect street sounds. SirenDetect Summary of Key Features • Using DSP chip, analyze incoming data. Determine if sound is a siren. • If yes, alert driver. If no, continue sampling.

  6. 1) Software Solution Matlab version 6.0 to analyze frequencyplots of sirens, construct filtering algorithms. Two-Part Process: 2) Hardware Solution Motorola DSP56826evm Digital Signal Processing kit with Metrowerks CodeWarrier software to create the device.

  7. Sample Siren Amplitude Time

  8. The FFT is an algorithm that “reduces the number of computations from something on the order of N02 to N0 log N0.”* Fast Fourier Transform (FFT) *http://aurora.phys.utk.edu/~forrest/papers/fourier/#FFT

  9. FFT of Sample Siren Peak 1: 105 – 180 Hz Peak 3: Peak 2: 370 - 430 Hz 220 – 300 Hz

  10. = 1 The Butterworth Filter N - order of the filter;  - analog frequency; s - complex Laplace variable such that s =  + j. * Kuc, Roman. Introduction to Digital Signal Processing. New York: McGraw-Hill, 1988.

  11. Butterworth Filtering with Matlab n - order of the filter Wn - the two-element vector Wn = [f1, f2] where f1, f2 are the limits of the passband, scaled from 0 to 1 [b,a] - filtering coefficients By experiment, n1 = n2 = 8; n3 = 6.

  12. 1. Create three bandpass Butterworth filters for P1, P2, P3. 2. Construct filters in parallel; pass siren through filters. 3. Obtain peak amplitude of each key region. 4. Repeat steps 2-3 for multiple siren samples; average amplitudes to obtain typical A1, A2, A3. 5. Run current sound sample through parallel filters; compare resulting amplitudes to A1, A2, and A3 to determine if sample is a siren. Matlab Algorithm

  13. Filtering: Graphical Representation of Inputs

  14. Filtering: Graphical Representation of Outputs Filter 1 Filter 2 Filter 3 Bandpass Region 1 Bandpass Region 2 Bandpass Region 3 Max(Peak1) Max(Peak2) Max(Peak3)

  15. 1. Absolute Magnitude Comparisons. Advantages: Simple(st), Fast(est), and Inexpensive Implementation. Disadvantages: Inaccuracy in presence of noise, disturbances. Next: How to compare bandpass regions? 2. Respective Magnitude Comparisons. Advantages: Simple, Fast, and Inexpensive; high accuracy. Disadvantages: Robustness? Testing necessary.

  16. How to compare bandpass regions? (continued) 3. Time Domain. Advantages: High Accuracy. Disadvantages: Difficult, more costly implementation. 4. Combination of 2 (Relative Magnitudes) and 3 (Time Domain). Advantages: Greatest Accuracy. Disadvantages: Costly and possibly redundant algorithm.

  17. Testing various algorithms proved that comparing respective amplitudes was the ideal implementation. Adjusting thresholds after testing various siren samples made detection more reliable.

  18. Matlab Code for Relative Amplitudes if (x13 > ??) & (x13 < ??) true2 = 1;end;if (x23 > ??) & (x23 < ??) true3 = 1;end;if (true1) & (true2) & (true3) its_a_siren=1;end; x12 = max1 / max2;x13 = max1 / max3;x23 = max2 / max3;true1 = 0;true2 = 0;true3 = 0;its_a_siren=0;if (x12 >??) & (x12 < ??) true1 = 1;end;

  19. Start Engine Key: R1 = max(x1)/max(x2) R2 = max(x1)/max(x3) R3 = max(x2)/max(x3) FFT Algorithm for Flow Chart - Top Level all incoming sound LED OFF n y R1? n y R2? y n R3? LED ON

  20. Real Time Data Stream Block Diagram Bandpass Filter 1 Bandpass Filter 2 Bandpass Filter 3 max(A1) max(A2) max(A3) A1/A2 A2/A3 A1/A3 Comparisons to R1, R2, R3 LED’s on / off

  21. Repeat Process on Motorola DSP56826evm Digital Signal Processing kit with Metrowerks CodeWarrier. Test in Laboratory Setting using microphones oriented in various directions; sirens mixed with street noises, music, etc.

  22. 1. Siren Library Expansion. SirenDetect will store a fingerprint for each of the unique siren sounds emitted by emergency vehicles. The Future of SirenDetect 2. Siren Differentiation. SirenDetect will distinguish between the siren of an ambulance, fire truck, police car, or other emergency vehicle. The driver will be notified of the type of car that is approaching.

  23. The Future of SirenDetect (continued) 3. Directional Capabilities. Strategic positioning of microphones will allow SirenDetect to compare amplitudes of signals and identify the precise location from which the emergency vehicle is approaching.

  24. The Future of SirenDetect (continued) 4. Robustness Evaluation. The system must be tested in residential areas, on highways, in cars traveling the same direction as emergency vehicles, the opposite direction, and at various angles (30, 45, 60, 90, etc.). Possible hazards are the Doppler effect and noise interference. The thresholds employed in the current code may need slight adjustments to be comprehensive in various driving conditions, yet should not be all-inclusive (i.e. detecting too many noises as sirens). Efficiency - Accuracy Trade-Off.

  25. Acknowledgments Peter Kindlmann, Project Adviser Edward Jackson Roman Kuc

More Related