Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Flying Fox Recogniser #238

Closed
towsey opened this issue Jun 15, 2019 · 1 comment · Fixed by #239
Closed

Flying Fox Recogniser #238

towsey opened this issue Jun 15, 2019 · 1 comment · Fixed by #239
Assignees
@towsey
Labels
enhancement

Comments

@towsey
Copy link
Contributor

towsey commented Jun 15, 2019

Paul Roe has requested a flying fox recogniser.

I have proposed that the recogniser have following steps:

  1. Break long recordings into one-minute segments.
  2. Convert each segment to a spectrogram.
  3. Obtain a noise profile for each segment. This is to be used later to remove insect chorusing.
  4. Scan the one-minute waveform and select "spike maxima" whose amplitude exceeds a decibel threshold, D.
  5. Extract a single frame (say 512 samples) centred on each spike and convert to a spike spectrum.
  6. Subtract the noise profile from the spike spectrum.
  7. Smooth the remaining spectrum.
  8. Look for evenly spaced harmonics in the smoothed spectrum. Typically the lowest harmonic will lie between 1200 Hz and 3000 Hz and the higher ones evenly spaced. This is the tricky bit due to variability but may work to use auto-correlation.
@atruskie atruskie mentioned this issue Jun 17, 2019
Merged
towsey added a commit that referenced this issue Jun 21, 2019
@towsey
Begin work on flying fox recogniser
d7ac462 
Branch for Issue-#238
towsey added a commit that referenced this issue Jun 24, 2019
@towsey
Further work on the flying fox recogniser.
d8813c2 
Issue-#238 Further work on the flying fox recogniser. Refactored a method used for frog recognisers and made it generally available in the class StandardSpectrograms.cs
towsey added a commit that referenced this issue Jun 25, 2019
@towsey
New method to find events
3a5db0a 
Issue-#238 Main work was to add a new method to AcousticEvents.cs in order to find events located at a score maximum. All such events have the same (user defined) time duration centred on the maximum.
towsey added a commit that referenced this issue Aug 12, 2019
@towsey
Refactor acoustic events method
5e5016e 
Issue #238: change method which makes first attempt to look for FF chirps. Start second method which filters those on the basis of the similarity of their spectral profile to that of a flying fox.
@atruskie
Copy link
Member

Hi @towsey,

Some notes from our meeting with Gary Plamer:

  • labelled examples (labelled with Audacity) are here: Y:\Gary Palmer\Flying Fox\Examples
  • 3 species, all not-distinguishable with acoustics
  • they are interested in recognizing three types of acoustic events:
    • territorial calls: short, single-syllable, amplitude modulated, screeches with stacked harmonics
    • agonistic calls: longer calls, multiple-syllables, seem to a series of warbling harmonic syllables, approximately 5-7 seconds long
    • wingbeats: a series of impulses in rapid succession
  • additionally, it would be good if we report the
    • dominant frequency (where applicable)
    • and the dominant frequency intensity

towsey added a commit that referenced this issue Aug 13, 2019
@towsey
Penultimate work on FF recogniser
7a2c5e1 
Issue #238  This recogniser now works well on a ten minute recording containing 14-16 FF calls.
TODO: The search parameters need to be read from config file. At moment hard coded.
towsey added a commit that referenced this issue Aug 14, 2019
@towsey
Add wingbeat profile to Flying Fox
6e6cce8 
Issue #238 Add Wingbeat profile to recogniser. It picks up wingbeats but also some human speech.
Also set up to read parameters from the config file.
towsey added a commit that referenced this issue Aug 27, 2019
@towsey
Update PteropusSpecies.cs
23429bd 
Issue #238 Do final work on Flying Fox wing beat detection.
Produce event spectra for experimental debug purposes.
towsey added a commit that referenced this issue Aug 27, 2019
@towsey
Fine adjustment of parameters
10ad62a 
Issue #238 Reviewed FF recogniser on a four extra recordings. In particular worked on a 60 minute recording and was able to pick up most ac events of interest with few FPs and FNs.
towsey added a commit that referenced this issue Aug 28, 2019
@towsey
Responding to comments from Anthony
877703f 
Issue #238 work on changes suggested by Anthony.
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
Begin work on flying fox recogniser
414b392 
Branch for Issue-#238
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
Further work on the flying fox recogniser.
d123d30 
Issue-#238 Further work on the flying fox recogniser. Refactored a method used for frog recognisers and made it generally available in the class StandardSpectrograms.cs
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
New method to find events
c86caaa 
Issue-#238 Main work was to add a new method to AcousticEvents.cs in order to find events located at a score maximum. All such events have the same (user defined) time duration centred on the maximum.
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
Refactor acoustic events method
f74098d 
Issue #238: change method which makes first attempt to look for FF chirps. Start second method which filters those on the basis of the similarity of their spectral profile to that of a flying fox.
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
Penultimate work on FF recogniser
2cf3847 
Issue #238  This recogniser now works well on a ten minute recording containing 14-16 FF calls.
TODO: The search parameters need to be read from config file. At moment hard coded.
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
Add wingbeat profile to Flying Fox
14a3214 
Issue #238 Add Wingbeat profile to recogniser. It picks up wingbeats but also some human speech.
Also set up to read parameters from the config file.
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
Update PteropusSpecies.cs
a1eb4e7 
Issue #238 Do final work on Flying Fox wing beat detection.
Produce event spectra for experimental debug purposes.
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
Fine adjustment of parameters
f6537bf 
Issue #238 Reviewed FF recogniser on a four extra recordings. In particular worked on a 60 minute recording and was able to pick up most ac events of interest with few FPs and FNs.
atruskie pushed a commit that referenced this issue Aug 28, 2019
@towsey @atruskie
Responding to comments from Anthony
d2b94f0 
Issue #238 work on changes suggested by Anthony.
towsey added a commit that referenced this issue Aug 29, 2019
@towsey
Finished response to requests from Anthony
1d1c552 
Issue #238 Only unit tests to be done.
towsey added a commit that referenced this issue Aug 29, 2019
@towsey
More changes to FF code
03a304d 
Issue #238 Changes mostly to get acoustic event information transfered to the FF methods.
towsey added a commit that referenced this issue Aug 30, 2019
@towsey
Set up unit tests for the flying fox recogniser
67e023b 
Issues-#238 Set up unit tests for the flying fox recogniser. Currently he two methods have dummy content pasted from elsewhere
towsey added a commit that referenced this issue Aug 31, 2019
@towsey
More work on FlyingFox tests
93cb93b 
Issue #238 More work on unit tests
towsey added a commit that referenced this issue Sep 1, 2019
@towsey
Update SonogramTests.cs
70caaaf 
Issue #238 Revert file name in SonogramTests.cs which was mistkenly changed yesterday.
towsey added a commit that referenced this issue Sep 1, 2019
@towsey
Finish Unit tests for Flying FOx class
1228b46 
Issue #238 Complete two tests of methods used in the Flying Fox recogniser.
towsey added a commit that referenced this issue Oct 26, 2019
@towsey
Reworking the oscillation detection component of Flying Foxrecognizer
a0e643b 
Issue #238 Flying fox
towsey added a commit that referenced this issue Oct 28, 2019
@towsey
More work on Oscillation recognizer
b31598b 
Issue #238 More work on Oscillation recognizer to pick up bat wing beats.
towsey added a commit that referenced this issue Nov 14, 2019
@towsey
Issue-#238 Fix failed tests for flying fox
33c5094 
For some reason, acoustic event bounds were not being calculated. Had to fix acoustic event class, and then do slight readjustments to the expected bounds of wing-beat events.
atruskie added a commit that referenced this issue Nov 14, 2019
@atruskie
Merge pull request #272 from QutEcoacoustics/Issue-#238_FlyingFoxReco…
8b68587 
…gnizer

Closes #238 flying fox recognizer

Also included an attempt at a new oscillation index.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@towsey towsey

Labels
enhancement
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Flying fox recognizer QutEcoacoustics/audio-analysis
2 participants
@atruskie @towsey