Welcome to the 2nd International Workshop on the Social Web for Environmental and Ecological Monitoring (SWEEM 2017)

The exponential growth of the popularity of social media has provided not only novel techniques for public communication and engagement, but has also generated unprecedented volumes of publicly-available, user-generated social media content. These trends open new opportunities for ecological and environmental applications, both in terms of alternative data sources and novel approaches for interacting with the public.

The goal of the workshop is to bring together a combination of academic and industrial participants to discuss ideas, challenges, and solutions at the intersection of Social Media and Environmental/Ecological Science.

Keynotes:

Tanya Berger-Wolf (University of Illinois at Chicago)
"From Pixels to Science and Conservation"

Photographs, taken by field scientists, tourists, automated cameras, and incidental photographers posting on social media, are the most abundant source of data on wildlife today. Our system, Wildbook, is an autonomous computational system that starts from massive collections of images and, by detecting various species of animals and identifying individuals, combined with sophisticated data management, turns them into high resolution information database, enabling scientific inquiry, conservation, and citizen science. We have built Wildbooks for whales (flukebook.org), sharks (whaleshark.org), two species of zebras (Grevy's and plains), and several others. In January 2016, Wildbook enabled the first ever full species (the endangered Grevy's zebra) census using photographs taken by ordinary citizens in Kenya. The resulting numbers are now the official species census used by IUCN Red List: http://www.iucnredlist.org/details/7950/0. In 2016, Wildbook partnered up with WWF to build Wildbook for Sea Turtles, Internet of Turtles (IoT), as well as systems for seals and lynx. I will give an overview of the logistical and analytical joys and challenges of using crowdsourced images for wildlife science and conservation.
Wildbook is co-founded by Tanya Berger-Wolf (UIC), Chuck Stewart (RPI), Dan Rubenstein (Princeton), and Jason Holmberg (WildMe.org)

Charles Stewart (Rensselaer Polytechnic Institute)
"Wildbook Computer Vision Algorithms:  Images to Individual Identities"

With a goal of ingesting thousands of images per day and handling large-scale citizen science population survey events, Wildbook must rely heavily on computer vision and machine learning algorithms working as autonomously as possible to convert images into data about the identities and locations of individual animals. This includes finding animals of interest in images, determining their species, extracting metadata and, most importantly, identifying the animals individually. This talk presents a suite of Wildbook computer vision algorithms that, while under continuous development, are already being used in practice. This includes a novel algorithmic framework that controls the entire process and allows the natural integration of alternative algorithms. Results are presented for species ranging from dolphins to sea turtles to zebras.