Implicit biodiversity monitoring from mobile search logs

Joly, Alexis (Inria, ZENITH team, LIRMM, Montpellier, France) ; Goëau, Hervé (IRD, UMR AMAP, Montpellier, France) ; Champ, Julien (Inria, ZENITH team, LIRMM, Montpellier, France) ; Dufour-Kowalski, Samuel (INRA, UMR AMAP, Montpellier, France) ; Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Bonnet, Pierre (CIRAD, UMR AMAP, Montpellier, France)

Large scale biodiversity monitoring is essential for sustain-able development (earth stewardship). With the recent ad-vances in computer vision, we see the emergence of more and more effective identification tools allowing to set-up large-scale data collection platforms such as the popular Pl@ntNet initiative. Although it still covers only a fraction of the world flora, this platform is already being used by more than 300K people who produce tens of thousands of validated plant ob-servations each year. Nevertheless, this explicitly shared and validated data is only the tip of the iceberg. The real po-tential relies on the millions of raw image queries submitted by the users of the mobile application but for which there is no human validation at all. Allowing the exploitation of such contents in a fully automatic way could scale up the world-wide collection of plant observations by several orders of magnitude. In this paper, we first survey existing auto-mated plant identification systems through a five-year syn-thesis of the PlantCLEF benchmark and an impact study of the Pl@ntNet platform. We then focus more specifically on the implicit monitoring scenario and discuss several new re-lated research challenges. Finally, we discuss the results of a preliminary experimental study focused on the implicit mon-itoring of invasive species in mobile search logs. We show that the results are very promising but that there is still some room for improvement before being able to automat-ically share such implicit observations within international biodiversity platforms.

Type de conférence:
full paper
Economie et Services
HEG VS HES-SO Valais-Wallis - Haute Ecole de Gestion & Tourisme
Institut Informatique de gestion
Adresse bibliogr.:
Amsterdam, The Netherlands, 15-19 October 2016
Amsterdam, The Netherlands
15-19 October 2016
13 p.
Titre du document hôte:
Proceedings of the ACM Multimedia Conference 2016
Le document apparaît dans:

Note: The status of this file is: restricted

 Notice créée le 2017-12-18, modifiée le 2018-02-15

Télécharger le document

Évaluer ce document:

Rate this document:
(Pas encore évalué)