SlideShare une entreprise Scribd logo
1  sur  24
Télécharger pour lire hors ligne
http://www.plantnet-project.org/
Crowdsourcing Biodiversity
Monitoring: How Sharing your Photo
Stream can Sustain our Planet
1
Alexis Joly, Hervé Goëau, Julien Champ, Samuel Dufour-Kowalski,
Henning Müller, Pierre Bonnet
Acknowledgement: Nozha Boujemaa, Daniel Barthelemy,
Jean-François Molino
2
• Global warming, food crisis and biodiversity erosion
• Accurate knowledge of living species distribution and
evolution is essential
• Ultimate goal: sustainable and global biodiversity
monitoring tools
– Surveillance of global warming consequences, plant & animal diseases,
human activities impact, invasive species propagation
• The Taxonomic impediment
– Less and less people can identify plants and animals
– Less and less nature observers can produce biodiversity data
Context
Pl@ntNet project (launched 2010)
Bridging the taxonomic impediment thanks to an innovative
crowdsourcing workflow based on automated plant identification
The positive feedback loop does work !
+
+
+
Pl@ntNet project (launched 2010)
Pl@ntNet app today2,5 M downloads
14 M sessions
10-50 K users / day
150 Countries
5
Languages
FR, EN, ES, IT, PT,
DE, AR, ZH, SK
Pl@ntNet data
Validated data = 3% of the queried plant images
- 30K collaboratively revised observations per year (TelaBotanica)
- Publicly available through international initiatives (GBIF, LifeCLEF)
- Validation is a slow and hard process
Pl@ntNet data
Unlabeled data = 97% of the raw query stream
- > 1 Million of observations per year (5.1M today)
- Not exploited today
- A high potential for biodiversity monitoring
Pl@ntNet mobile search logs
Species Distribution Modelling from UGC
image streams ?
Can we predict (real-time and/or long-term) Species Distribution Models directly
from Pl@ntNet mobile search logs ?
Or from any other UGC image stream ?
9
Challenges
1. Improve recognition in open-world streams
10
Recognizing plants in an open world
11
An open-set recognition problem
- With 10K’s of known and unknown classes
- Highly imbalanced training data
We carried out an evaluation within LifeCLEF 2016
- Training set of 1000 known species (113K pictures)
- Test set = 8K manually annotated Pl@ntNet queries (half
known, half distractors)
- Classification Mean Average Precision on a subset of 26
invasive species
??
? ? ?
? ?
1. Improve automatic recognition of plants in open-world streams
- Novelty affects all systems, whatever the used rejection method (even supervised)
- No rejection method can deal with strong novelty rates
→ we are still far from being able to monitor biodiversity in Twitter or Snapchat streams !
12
Recognizing plants in an open world
Challenges
1. Improve recognition in open-world streams
2. Use geo-location and date
13
Geo-location and date ?
- Not so easy !
- No real success within 5 years of PlantCLEF challenge
- Why ?
- Plant distributions are not well known (this is actually our objective !)
- Habitats are extremely heterogeneous from a species to another one (some
plants live everywhere while others live in very specific biotopes)
- What can we do ?
- Big occurrence data (like GBIF) might help but is biased, heterogeneous and
incomplete (no absence data)
- Environmental variables might help but heterogeneous, incomplete, noisy, etc.
→ This will be one of the focus of LifeCLEF 2017
Challenges
1. Improve recognition in open-world streams
2. Use geo-location and date
3. Use taxonomy
15
Using taxonomy ?
Taxonomy = a hierarchical classification built by botanists for hundreds of years
→ 600 families > 14K genus > 300K species
But, taxonomy is highly heterogeneous and imbalanced
→ Classical hierarchical classification algorithms
can be not be directly used
- Some genus with up to 1000 very similar species
- But many genus and families include very distinct species
- The long tail distribution occurs at each level and in each
node
Genus
Orobanche
Genus
Bupleurum
Family
Bupleurum
Challenges
1. Improve recognition in open-world streams
2. Use geo-location and date
3. Use taxonomy
4. Optimize and boost training data production
17
Pro-active crowdsourcing
Classifier (CNN)
Annotators (heterogeneous skills)
Tasks selection &
assignment
?
?
?
Training
Training
2. Create
quizzes by
Monte-carlo
sampling
Beginner
Intermediate
1. ConvNet predictions
3. Sort quizzes by difficulty (= success
expectation across all workers)
Identification
success rate
Experiments: Simpson’s paradox
20
Declared expertise
Workers are assigned tasks they have been trained on before !
Challenges
1. Improve recognition in open-world streams
2. Use geo-location and date
3. Use taxonomy
4. Optimize and boost data validation processes
5. Control bias in Species Distribution Models
21
22
Objectif: Estimate the relative abundance Aij
of species i in place j supposing
Nij
~ Law( Aij
, Bij
)
Nij
: Number of observations of i in j
Aij
: Abundance of i in j
Bij
: Bias that might be complex because of the diversity of contributors, the opportunistic property of
the observations and the confusions
Modeling bias factors ?
Conclusion: biodiversity
informatics needs MM
23
Biodiversity
Dimension
Biodiversity Conservation
Challenge
Who? Multimedia research topics
Aesthetic Enjoy and love it Everybody IR, Recommendation
Diverse Identify and classify Taxonomists Multimodal & Large-scale classification
Complex Decipher & model Biologists Multimedia Data analytics
Unknown Discover & associate Taxonomists Multimedia Data mining
Endangered Define & implement policies Decision makers Visualization, Interactivity
Indispensable Use sustainably Everybody Cross-media streams monitoring
Thank you

Contenu connexe

Similaire à Crowdsourcing Biodiversity Monitoring: How Sharing your Photo Stream can Sustain our Planet

Supporting researchers in the molecular life sciences Jeff Christiansen
Supporting researchers in the molecular life sciences Jeff Christiansen Supporting researchers in the molecular life sciences Jeff Christiansen
Supporting researchers in the molecular life sciences Jeff Christiansen ARDC
 
Tim Brown ACEAS Phenocams
Tim Brown ACEAS PhenocamsTim Brown ACEAS Phenocams
Tim Brown ACEAS Phenocamsaceas13tern
 
Grand round whsiao_may2015
Grand round whsiao_may2015Grand round whsiao_may2015
Grand round whsiao_may2015IRIDA_community
 
How Can We Make Genomic Epidemiology a Widespread Reality? - William Hsiao
How Can We Make Genomic Epidemiology a Widespread Reality?  - William HsiaoHow Can We Make Genomic Epidemiology a Widespread Reality?  - William Hsiao
How Can We Make Genomic Epidemiology a Widespread Reality? - William HsiaoWilliam Hsiao
 
2015. Jason Wallace. Applying high throughput genomics to crops for the devel...
2015. Jason Wallace. Applying high throughput genomics to crops for the devel...2015. Jason Wallace. Applying high throughput genomics to crops for the devel...
2015. Jason Wallace. Applying high throughput genomics to crops for the devel...FOODCROPS
 
2015-08-13 ESA: NextGen tools for scaling from seeds to traits to ecosystems
2015-08-13 ESA: NextGen tools for scaling from seeds to traits to ecosystems2015-08-13 ESA: NextGen tools for scaling from seeds to traits to ecosystems
2015-08-13 ESA: NextGen tools for scaling from seeds to traits to ecosystemsTimeScience
 
Perth ausplots presentation_070616_internet_qu
Perth ausplots presentation_070616_internet_quPerth ausplots presentation_070616_internet_qu
Perth ausplots presentation_070616_internet_qubensparrowau
 
2015 05 Scaling from seeds to ecosystems
2015 05 Scaling from seeds to ecosystems2015 05 Scaling from seeds to ecosystems
2015 05 Scaling from seeds to ecosystemsTimeScience
 
Ecosystem science requirements for uas remote sensing
Ecosystem science requirements for uas remote sensing Ecosystem science requirements for uas remote sensing
Ecosystem science requirements for uas remote sensing bensparrowau
 
RPG iEvoBio 2010 Keynote
RPG iEvoBio 2010 KeynoteRPG iEvoBio 2010 Keynote
RPG iEvoBio 2010 KeynoteRob Guralnick
 
iEvoBio Keynote Talk 2010
iEvoBio Keynote Talk 2010iEvoBio Keynote Talk 2010
iEvoBio Keynote Talk 2010Rob Guralnick
 
ISU ENVSCI690 Graduate Seminar Slides
ISU ENVSCI690 Graduate Seminar SlidesISU ENVSCI690 Graduate Seminar Slides
ISU ENVSCI690 Graduate Seminar SlidesAdina Chuang Howe
 
2016 International Conference on Pulses – Concluding remarks
2016 International Conference on Pulses – Concluding remarks2016 International Conference on Pulses – Concluding remarks
2016 International Conference on Pulses – Concluding remarksCGIAR
 
International Conference on Pulses 2016 Concluding Remarks
International Conference on Pulses 2016 Concluding RemarksInternational Conference on Pulses 2016 Concluding Remarks
International Conference on Pulses 2016 Concluding RemarksICARDA
 
TraitCapture: NextGen phenomics tools for lab and field [ComBio2015]
TraitCapture: NextGen phenomics tools for lab and field [ComBio2015]TraitCapture: NextGen phenomics tools for lab and field [ComBio2015]
TraitCapture: NextGen phenomics tools for lab and field [ComBio2015]TimeScience
 
Survival of the Fittest – Utilization of Natural selection Mechanisms for Imp...
Survival of the Fittest – Utilization of Natural selection Mechanisms for Imp...Survival of the Fittest – Utilization of Natural selection Mechanisms for Imp...
Survival of the Fittest – Utilization of Natural selection Mechanisms for Imp...Behnam Taraghi
 
Phenomics in crop improvement
Phenomics in crop  improvementPhenomics in crop  improvement
Phenomics in crop improvementsukruthaa
 

Similaire à Crowdsourcing Biodiversity Monitoring: How Sharing your Photo Stream can Sustain our Planet (20)

Supporting researchers in the molecular life sciences Jeff Christiansen
Supporting researchers in the molecular life sciences Jeff Christiansen Supporting researchers in the molecular life sciences Jeff Christiansen
Supporting researchers in the molecular life sciences Jeff Christiansen
 
Tim Brown ACEAS Phenocams
Tim Brown ACEAS PhenocamsTim Brown ACEAS Phenocams
Tim Brown ACEAS Phenocams
 
Grand round whsiao_may2015
Grand round whsiao_may2015Grand round whsiao_may2015
Grand round whsiao_may2015
 
How Can We Make Genomic Epidemiology a Widespread Reality? - William Hsiao
How Can We Make Genomic Epidemiology a Widespread Reality?  - William HsiaoHow Can We Make Genomic Epidemiology a Widespread Reality?  - William Hsiao
How Can We Make Genomic Epidemiology a Widespread Reality? - William Hsiao
 
2015. Jason Wallace. Applying high throughput genomics to crops for the devel...
2015. Jason Wallace. Applying high throughput genomics to crops for the devel...2015. Jason Wallace. Applying high throughput genomics to crops for the devel...
2015. Jason Wallace. Applying high throughput genomics to crops for the devel...
 
2015-08-13 ESA: NextGen tools for scaling from seeds to traits to ecosystems
2015-08-13 ESA: NextGen tools for scaling from seeds to traits to ecosystems2015-08-13 ESA: NextGen tools for scaling from seeds to traits to ecosystems
2015-08-13 ESA: NextGen tools for scaling from seeds to traits to ecosystems
 
Perth ausplots presentation_070616_internet_qu
Perth ausplots presentation_070616_internet_quPerth ausplots presentation_070616_internet_qu
Perth ausplots presentation_070616_internet_qu
 
2014 mmg-talk
2014 mmg-talk2014 mmg-talk
2014 mmg-talk
 
2015 05 Scaling from seeds to ecosystems
2015 05 Scaling from seeds to ecosystems2015 05 Scaling from seeds to ecosystems
2015 05 Scaling from seeds to ecosystems
 
3.1 session by hershey
3.1 session by hershey   3.1 session by hershey
3.1 session by hershey
 
Ecosystem science requirements for uas remote sensing
Ecosystem science requirements for uas remote sensing Ecosystem science requirements for uas remote sensing
Ecosystem science requirements for uas remote sensing
 
RPG iEvoBio 2010 Keynote
RPG iEvoBio 2010 KeynoteRPG iEvoBio 2010 Keynote
RPG iEvoBio 2010 Keynote
 
iEvoBio Keynote Talk 2010
iEvoBio Keynote Talk 2010iEvoBio Keynote Talk 2010
iEvoBio Keynote Talk 2010
 
CBGW John Pollak
CBGW John PollakCBGW John Pollak
CBGW John Pollak
 
ISU ENVSCI690 Graduate Seminar Slides
ISU ENVSCI690 Graduate Seminar SlidesISU ENVSCI690 Graduate Seminar Slides
ISU ENVSCI690 Graduate Seminar Slides
 
2016 International Conference on Pulses – Concluding remarks
2016 International Conference on Pulses – Concluding remarks2016 International Conference on Pulses – Concluding remarks
2016 International Conference on Pulses – Concluding remarks
 
International Conference on Pulses 2016 Concluding Remarks
International Conference on Pulses 2016 Concluding RemarksInternational Conference on Pulses 2016 Concluding Remarks
International Conference on Pulses 2016 Concluding Remarks
 
TraitCapture: NextGen phenomics tools for lab and field [ComBio2015]
TraitCapture: NextGen phenomics tools for lab and field [ComBio2015]TraitCapture: NextGen phenomics tools for lab and field [ComBio2015]
TraitCapture: NextGen phenomics tools for lab and field [ComBio2015]
 
Survival of the Fittest – Utilization of Natural selection Mechanisms for Imp...
Survival of the Fittest – Utilization of Natural selection Mechanisms for Imp...Survival of the Fittest – Utilization of Natural selection Mechanisms for Imp...
Survival of the Fittest – Utilization of Natural selection Mechanisms for Imp...
 
Phenomics in crop improvement
Phenomics in crop  improvementPhenomics in crop  improvement
Phenomics in crop improvement
 

Dernier

GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024Jene van der Heide
 
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPRPirithiRaju
 
Pests of Sunflower_Binomics_Identification_Dr.UPR
Pests of Sunflower_Binomics_Identification_Dr.UPRPests of Sunflower_Binomics_Identification_Dr.UPR
Pests of Sunflower_Binomics_Identification_Dr.UPRPirithiRaju
 
Environmental acoustics- noise criteria.pptx
Environmental acoustics- noise criteria.pptxEnvironmental acoustics- noise criteria.pptx
Environmental acoustics- noise criteria.pptxpriyankatabhane
 
Oxo-Acids of Halogens and their Salts.pptx
Oxo-Acids of Halogens and their Salts.pptxOxo-Acids of Halogens and their Salts.pptx
Oxo-Acids of Halogens and their Salts.pptxfarhanvvdk
 
whole genome sequencing new and its types including shortgun and clone by clone
whole genome sequencing new  and its types including shortgun and clone by clonewhole genome sequencing new  and its types including shortgun and clone by clone
whole genome sequencing new and its types including shortgun and clone by clonechaudhary charan shingh university
 
Forensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptxForensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptxkumarsanjai28051
 
Observational constraints on mergers creating magnetism in massive stars
Observational constraints on mergers creating magnetism in massive starsObservational constraints on mergers creating magnetism in massive stars
Observational constraints on mergers creating magnetism in massive starsSérgio Sacani
 
The Sensory Organs, Anatomy and Function
The Sensory Organs, Anatomy and FunctionThe Sensory Organs, Anatomy and Function
The Sensory Organs, Anatomy and FunctionJadeNovelo1
 
Quarter 4_Grade 8_Digestive System Structure and Functions
Quarter 4_Grade 8_Digestive System Structure and FunctionsQuarter 4_Grade 8_Digestive System Structure and Functions
Quarter 4_Grade 8_Digestive System Structure and FunctionsCharlene Llagas
 
bonjourmadame.tumblr.com bhaskar's girls
bonjourmadame.tumblr.com bhaskar's girlsbonjourmadame.tumblr.com bhaskar's girls
bonjourmadame.tumblr.com bhaskar's girlshansessene
 
FBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxFBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxPayal Shrivastava
 
CHROMATOGRAPHY PALLAVI RAWAT.pptx
CHROMATOGRAPHY  PALLAVI RAWAT.pptxCHROMATOGRAPHY  PALLAVI RAWAT.pptx
CHROMATOGRAPHY PALLAVI RAWAT.pptxpallavirawat456
 
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep LearningCombining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learningvschiavoni
 
DNA isolation molecular biology practical.pptx
DNA isolation molecular biology practical.pptxDNA isolation molecular biology practical.pptx
DNA isolation molecular biology practical.pptxGiDMOh
 
WEEK 4 PHYSICAL SCIENCE QUARTER 3 FOR G11
WEEK 4 PHYSICAL SCIENCE QUARTER 3 FOR G11WEEK 4 PHYSICAL SCIENCE QUARTER 3 FOR G11
WEEK 4 PHYSICAL SCIENCE QUARTER 3 FOR G11GelineAvendao
 
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...D. B. S. College Kanpur
 
DOG BITE management in pediatrics # for Pediatric pgs# topic presentation # f...
DOG BITE management in pediatrics # for Pediatric pgs# topic presentation # f...DOG BITE management in pediatrics # for Pediatric pgs# topic presentation # f...
DOG BITE management in pediatrics # for Pediatric pgs# topic presentation # f...HafsaHussainp
 
Introduction of Human Body & Structure of cell.pptx
Introduction of Human Body & Structure of cell.pptxIntroduction of Human Body & Structure of cell.pptx
Introduction of Human Body & Structure of cell.pptxMedical College
 

Dernier (20)

GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024GenAI talk for Young at Wageningen University & Research (WUR) March 2024
GenAI talk for Young at Wageningen University & Research (WUR) March 2024
 
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
6.1 Pests of Groundnut_Binomics_Identification_Dr.UPR
 
Pests of Sunflower_Binomics_Identification_Dr.UPR
Pests of Sunflower_Binomics_Identification_Dr.UPRPests of Sunflower_Binomics_Identification_Dr.UPR
Pests of Sunflower_Binomics_Identification_Dr.UPR
 
Environmental acoustics- noise criteria.pptx
Environmental acoustics- noise criteria.pptxEnvironmental acoustics- noise criteria.pptx
Environmental acoustics- noise criteria.pptx
 
Interferons.pptx.
Interferons.pptx.Interferons.pptx.
Interferons.pptx.
 
Oxo-Acids of Halogens and their Salts.pptx
Oxo-Acids of Halogens and their Salts.pptxOxo-Acids of Halogens and their Salts.pptx
Oxo-Acids of Halogens and their Salts.pptx
 
whole genome sequencing new and its types including shortgun and clone by clone
whole genome sequencing new  and its types including shortgun and clone by clonewhole genome sequencing new  and its types including shortgun and clone by clone
whole genome sequencing new and its types including shortgun and clone by clone
 
Forensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptxForensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptx
 
Observational constraints on mergers creating magnetism in massive stars
Observational constraints on mergers creating magnetism in massive starsObservational constraints on mergers creating magnetism in massive stars
Observational constraints on mergers creating magnetism in massive stars
 
The Sensory Organs, Anatomy and Function
The Sensory Organs, Anatomy and FunctionThe Sensory Organs, Anatomy and Function
The Sensory Organs, Anatomy and Function
 
Quarter 4_Grade 8_Digestive System Structure and Functions
Quarter 4_Grade 8_Digestive System Structure and FunctionsQuarter 4_Grade 8_Digestive System Structure and Functions
Quarter 4_Grade 8_Digestive System Structure and Functions
 
bonjourmadame.tumblr.com bhaskar's girls
bonjourmadame.tumblr.com bhaskar's girlsbonjourmadame.tumblr.com bhaskar's girls
bonjourmadame.tumblr.com bhaskar's girls
 
FBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptxFBI Profiling - Forensic Psychology.pptx
FBI Profiling - Forensic Psychology.pptx
 
CHROMATOGRAPHY PALLAVI RAWAT.pptx
CHROMATOGRAPHY  PALLAVI RAWAT.pptxCHROMATOGRAPHY  PALLAVI RAWAT.pptx
CHROMATOGRAPHY PALLAVI RAWAT.pptx
 
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep LearningCombining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning
 
DNA isolation molecular biology practical.pptx
DNA isolation molecular biology practical.pptxDNA isolation molecular biology practical.pptx
DNA isolation molecular biology practical.pptx
 
WEEK 4 PHYSICAL SCIENCE QUARTER 3 FOR G11
WEEK 4 PHYSICAL SCIENCE QUARTER 3 FOR G11WEEK 4 PHYSICAL SCIENCE QUARTER 3 FOR G11
WEEK 4 PHYSICAL SCIENCE QUARTER 3 FOR G11
 
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
Fertilization: Sperm and the egg—collectively called the gametes—fuse togethe...
 
DOG BITE management in pediatrics # for Pediatric pgs# topic presentation # f...
DOG BITE management in pediatrics # for Pediatric pgs# topic presentation # f...DOG BITE management in pediatrics # for Pediatric pgs# topic presentation # f...
DOG BITE management in pediatrics # for Pediatric pgs# topic presentation # f...
 
Introduction of Human Body & Structure of cell.pptx
Introduction of Human Body & Structure of cell.pptxIntroduction of Human Body & Structure of cell.pptx
Introduction of Human Body & Structure of cell.pptx
 

Crowdsourcing Biodiversity Monitoring: How Sharing your Photo Stream can Sustain our Planet

  • 1. http://www.plantnet-project.org/ Crowdsourcing Biodiversity Monitoring: How Sharing your Photo Stream can Sustain our Planet 1 Alexis Joly, Hervé Goëau, Julien Champ, Samuel Dufour-Kowalski, Henning Müller, Pierre Bonnet Acknowledgement: Nozha Boujemaa, Daniel Barthelemy, Jean-François Molino
  • 2. 2 • Global warming, food crisis and biodiversity erosion • Accurate knowledge of living species distribution and evolution is essential • Ultimate goal: sustainable and global biodiversity monitoring tools – Surveillance of global warming consequences, plant & animal diseases, human activities impact, invasive species propagation • The Taxonomic impediment – Less and less people can identify plants and animals – Less and less nature observers can produce biodiversity data Context
  • 3. Pl@ntNet project (launched 2010) Bridging the taxonomic impediment thanks to an innovative crowdsourcing workflow based on automated plant identification
  • 4. The positive feedback loop does work ! + + + Pl@ntNet project (launched 2010)
  • 5. Pl@ntNet app today2,5 M downloads 14 M sessions 10-50 K users / day 150 Countries 5 Languages FR, EN, ES, IT, PT, DE, AR, ZH, SK
  • 6. Pl@ntNet data Validated data = 3% of the queried plant images - 30K collaboratively revised observations per year (TelaBotanica) - Publicly available through international initiatives (GBIF, LifeCLEF) - Validation is a slow and hard process
  • 7. Pl@ntNet data Unlabeled data = 97% of the raw query stream - > 1 Million of observations per year (5.1M today) - Not exploited today - A high potential for biodiversity monitoring
  • 9. Species Distribution Modelling from UGC image streams ? Can we predict (real-time and/or long-term) Species Distribution Models directly from Pl@ntNet mobile search logs ? Or from any other UGC image stream ? 9
  • 10. Challenges 1. Improve recognition in open-world streams 10
  • 11. Recognizing plants in an open world 11 An open-set recognition problem - With 10K’s of known and unknown classes - Highly imbalanced training data We carried out an evaluation within LifeCLEF 2016 - Training set of 1000 known species (113K pictures) - Test set = 8K manually annotated Pl@ntNet queries (half known, half distractors) - Classification Mean Average Precision on a subset of 26 invasive species ?? ? ? ? ? ?
  • 12. 1. Improve automatic recognition of plants in open-world streams - Novelty affects all systems, whatever the used rejection method (even supervised) - No rejection method can deal with strong novelty rates → we are still far from being able to monitor biodiversity in Twitter or Snapchat streams ! 12 Recognizing plants in an open world
  • 13. Challenges 1. Improve recognition in open-world streams 2. Use geo-location and date 13
  • 14. Geo-location and date ? - Not so easy ! - No real success within 5 years of PlantCLEF challenge - Why ? - Plant distributions are not well known (this is actually our objective !) - Habitats are extremely heterogeneous from a species to another one (some plants live everywhere while others live in very specific biotopes) - What can we do ? - Big occurrence data (like GBIF) might help but is biased, heterogeneous and incomplete (no absence data) - Environmental variables might help but heterogeneous, incomplete, noisy, etc. → This will be one of the focus of LifeCLEF 2017
  • 15. Challenges 1. Improve recognition in open-world streams 2. Use geo-location and date 3. Use taxonomy 15
  • 16. Using taxonomy ? Taxonomy = a hierarchical classification built by botanists for hundreds of years → 600 families > 14K genus > 300K species But, taxonomy is highly heterogeneous and imbalanced → Classical hierarchical classification algorithms can be not be directly used - Some genus with up to 1000 very similar species - But many genus and families include very distinct species - The long tail distribution occurs at each level and in each node Genus Orobanche Genus Bupleurum Family Bupleurum
  • 17. Challenges 1. Improve recognition in open-world streams 2. Use geo-location and date 3. Use taxonomy 4. Optimize and boost training data production 17
  • 18. Pro-active crowdsourcing Classifier (CNN) Annotators (heterogeneous skills) Tasks selection & assignment ? ? ?
  • 19. Training Training 2. Create quizzes by Monte-carlo sampling Beginner Intermediate 1. ConvNet predictions 3. Sort quizzes by difficulty (= success expectation across all workers)
  • 20. Identification success rate Experiments: Simpson’s paradox 20 Declared expertise Workers are assigned tasks they have been trained on before !
  • 21. Challenges 1. Improve recognition in open-world streams 2. Use geo-location and date 3. Use taxonomy 4. Optimize and boost data validation processes 5. Control bias in Species Distribution Models 21
  • 22. 22 Objectif: Estimate the relative abundance Aij of species i in place j supposing Nij ~ Law( Aij , Bij ) Nij : Number of observations of i in j Aij : Abundance of i in j Bij : Bias that might be complex because of the diversity of contributors, the opportunistic property of the observations and the confusions Modeling bias factors ?
  • 23. Conclusion: biodiversity informatics needs MM 23 Biodiversity Dimension Biodiversity Conservation Challenge Who? Multimedia research topics Aesthetic Enjoy and love it Everybody IR, Recommendation Diverse Identify and classify Taxonomists Multimodal & Large-scale classification Complex Decipher & model Biologists Multimedia Data analytics Unknown Discover & associate Taxonomists Multimedia Data mining Endangered Define & implement policies Decision makers Visualization, Interactivity Indispensable Use sustainably Everybody Cross-media streams monitoring