Why Wildbook?

According to a July 2017 study in the Proceedings of the National Academy of Sciences, a “sixth mass extinction” is underway, a trend signalled by widespread vertebrate losses that “will have negative cascading consequences on ecosystem functioning and services vital to sustaining civilization.” This meta-study is based on multiple, independent analyses and represents a growing awareness in the wildlife research community that more rapid assessment, response, and review are needed to understand and counter this decline.

Unfortunately, wildlife research efforts are frequently underfunded and small scale. The collection and management of wildlife data remains a largely ad hoc and academic exercise focused on moving small data sets (often in Excel and Access) into local, custom population studies for “one-off” analyses without long-term data curation or collaboration across borders and regions. Arriving at a critical mass of data for population analysis can take years (especially for rare or endangered species). Long required observation periods and manual data processing (e.g., matching photos “by eye”) can create multi-year lags between study initialization and scientific results, as well as create conclusions too coarse or slow for effective and optimizable conservation action. This limits the scope, scale, repeatability, continuity, and ROI of the studies as they face the limits of their home-grown tools and IT capabilities.

Wildlife researchers lack a common yet customizable platform for collaboration and often don’t have the technical experience or budget to take advantage of advanced computing tools (e.g., computer vision, artificial intelligence). These tools allows projects to obtain, curate, and analyze “Big Data”, such as the potential of citizen scientists to collect and contribute large volumes of wildlife data through tourism and volunteerism.

Data Management in the Cloud

Wildbook ® is an open source software framework to support collaborative mark-recapture, molecular ecology, and social ecology studies, especially where citizen science data needs to be incorporated and managed. It is developed by the non-profit Wild Me (PI Jason Holmberg) in close collaboration with research partners at the University of Illinois-Chicago (PI Tanya Berger-Wolf), Rensselaer Polytechnic Institute (PI Charles V. Stewart), and Princeton University (PI Daniel Rubenstein).

The biological and statistical communities already support a number of excellent tools, such as Program MARK,GenAlEx, and SOCPROG for use in analyzing wildlife data. Wildbook is a complementary software application that:

  • provides a scalable and collaborative platform for intelligent wildlife data storage and management, including advanced, consolidated searching
  • provides an easy-to-use software suite of functionality that can be extended to meet the needs of wildlife projects, especially where individual identification is used
  • provides an API to support the easy export of data to cross-disciplinary analysis applications (e.g., GenePop ) and other software (e.g., Google Earth)
  • provides a platform that supports the exposure of data in biodiversity databases (e.g., GBIF and OBIS)
  • provides a platform for animal biometrics that supports easy data access and facilitates matching application deployment for multiple species

Open Source with a Professional Support Option

Wildbook® is always free and open source. We are a community of IT professionals and wildlife researchers maintaining and improving a 21st century platform. However, sometimes you may need extra help on a deadline. Our non-profit Wild Me offers professional hosting and customization to fit your project's requirements. This helps us fund our non-profit projects. Contact us if you need help!

Gateway to A.I. and Computer Vision

Images have become the most abundant, available and cheap source of data. The explosive growth in the use of digital cameras, together with rapid innovations in storage technology and automatic image analysis software, makes this vision possible particularly for large animals with distinctive striped, spotted, wrinkled or notched markings, such as elephants, giraffes and zebras. This large number of collected images must be analyzed automatically to produce a database that records who the animals are, where they are, and when they were photographed. Combining this with geographic, environmental, behavioral and climate data would enable the determination of what the animals are doing, and why they are doing it.

Wildbook evolved out of multi-disciplinary, collaborative research conducted under National Science Foundation support (see ibeis.org). Wildbook employees computer vision and A.I. components to detect features in submitted images and detect and then identify individual animals. Wildbook brings massive-scale computer vision to wildlife research for the first time.

Wildbook integrates the data management software of Wild Me with the computer vision and A.I. research of RPI. Wildbook includes a two-part, multi-species computer vision pipeline to find and identify individual animals in photos collected under real-world conditions, especially with citizen science contribution.

Detection

Our detection pipeline is a cascade of deep convolutional neural networks (DCNNs) that applies a fully-connected classifier on extracted features. Three separate networks produce: (1) whole-scene classifications looking for specific species of animals in the photograph, (2) object annotation bounding box localizations, and (3) the viewpoint, quality, and final species classifications for the candidate bounding boxes.

In Wildbook, A.I.-powered detection finds and labels wildlife in photos.

Identification

The second major computer vision step is identification, which assigns a name label to each annotation from detection. To do this, SIFT descriptors are first extracted and then compared at keypoint locations. Scores from the query that match the same individual are accumulated to produce a single potential score for each animal. The animals in the database are then ranked by their accumulated scores. A post-processing step spatially verifies the descriptor matches and then re-scores and re-ranks the database individuals.

Example correct identifications. The upper left annotation in each frame is the annotation to be identified. The other frames are the other annotations for the same animal. The bottom left annotation is the primary matching frame. The colored line segments show connections between corresponding features of the same animal.

Analysis

The results of computer vision are returned to Wildbook’s data management software, which supports rapid curation, export, and analysis. Data can be rapidly viewed in tables, maps, charts, calendars, and as thumbnails. Data can also be searched, filtered, and used in R, Mark, ArcGIS, Google Earth, and other applications.

Get Wildbook

Get Support

Projects with Wildbook

People

Wildbook is a long-term, multi-disciplinary, multi-institution project combining skilled people in computer science, data science, ecology, and software engineering..

University of Illinois-Chicago

Professor Tanya Berger-Wolf provides computer science, data science, and overall project leadership to Wildbook.

Wild Me

www.wildme.org_wp-content_uploads_2015_09_1455109_10204334175773477_7845084325593654833_n1-300x300.jpg www.wildme.org_wp-content_uploads_2015_09_901250-300x300.jpg

Jason Holmberg is the Information Architect for Wildbook. Jon Van Oast, Drew Blount, and Colin Kingen are the primary software developers. Together we bring a wealth of professional software engineering experience to Wildbook.

Rensselaer Polytechnic Institute

Professor Charles Stewart and his students provide artificial intelligence and computer vision research and technology to Wildbook.

Princeton University

Professor Dan Rubenstein provides ecology and biology guidance to Wildbook as well as field testing Kenya.

Other

Dr. Scott Baker of Oregon State University designed the DNA-related components within the software and remains an active adviser on the project.

News

2017-07-22 Wildbook 7.0 development has kicked off, including a new computer vision API for multiple algorithms, a new data curation interface, and new data structures for tracking effort.

Past news...

Sponsors

Ongoing support for Wildbook is funded by the National Science Foundation, Amazon Web Services, collaborative co-investment by users, and donations to Wild Me.

Past development work for Wildbook has been supported by:

Collaboration Model

Wildbook is designed to produce successful, reproducible collaborations between biologists, biostatisticians, computer scientists, and citizen scientists by providing a Web-based software platform for collaboration.

Is Wildbook right for you?

If you answer yes to any of these questions, Wildbook may be a very good choice for your research.

  • Are you trying to track individual animals in a wildlife population using natural markings , genetic identifiers, or vocalizations?
  • Are you collecting biological samples from a wildlife population and performing genetic or chemical analyses (e.g., stable isotope measurements, haplotype determination, etc.)?
  • Are you looking to increase wildlife data collection through citizen science?
  • Are you looking to build a collaborative, distributed research network for a species?
  • Are you looking to develop a new animal biometrics solution (e.g., pattern matching from photos) for one or more species?
  • Are you collecting behavioral and/or social data for a wildlife study population?

Screenshots

Features

Using the web-based interface of Wildbook Framework, a research team can:

Encounters (a.k.a. “captures” or “sightings”)

  • Record an encounter (individual animal at a point in time and location) through a standardized data collection form
  • Search a database of standardized encounter data using predefined search criteria
  • Receive automated email updates when encounter reports are assigned to new or previously identified marked individuals
  • Receive RSS feeds of encounter identifications as they are made
  • View all reported encounters
  • View individual encounter reports
  • View thumbnail catalogs of submitted images
  • View adopters of individual encounters (a fundraising tool)
  • Edit encounter data with all changes tracked and permanently logged
  • Assign encounters to new or existing marked individuals
  • Set a list of additional email addresses to be notified with status and sighting updates for submitted encounters
  • View an on-line calendar of whale shark encounter reports
  • Restore accidentally deleted encounters
  • Easily map a TapirLink provider or Integrated Publishing Toolkit (IPT) to the underlying relational database for exposure of mark-recapture data to biodiversity frameworks
  • For species with marked individuals identified by unique spot patterning:
    1. Extract spot patterning from photographs and scan for matches across all patterns in library using two approaches to pattern recognition (I3S and Modified Groth).
    2. Share computing power among globally distributed machines.
    3. View pattern match reports and evaluate matches side-by-side, including direct spot remapping and statistical analysis of results.
  • Record physical, acoustic, and satellite tag data deployed during an encounter
  • Record tissue samples collected with an encounter
  • Record the results of genetic sex, haplotype, microsatellite marker, stable isotope, and contaminant analyses performed on a tissue sample

Marked Individuals

  • View all marked individuals
  • View consolidated capture and sampling history of marked individuals
  • Receive automated email updates when a marked individual is re-sighted
  • Search a global database of marked individuals using predefined search criteria
  • View consolidated mapping of sighting locations an individual
  • View co-occurrence for the individual with other individual (e.g., social grouping)

Photos

  • Define common photo keywords for your species (e.g. scarring types)
  • Add/remove keywords to encounter photos
  • Search across photographs using assigned keywords
  • Search all images\video using encounter data to create customized albums of images
  • View photo metadata (e.g. EXIF data)

General

  • Search all encounters and marked individual data using Google Search (when deployed as a web server)
  • Assign alternate identifiers to encounters and marked individuals
  • View sighting locations with satellite imagery incorporated from Google Maps (encounters, amrked individuals, and Encounter Search results)
  • Export sighting data as a KML file or an Excel spreadsheet for use in Google Earth and other mapping applications (Encounter Search).
  • Create and edit animal adoptions for project fundraising.
  • Review access security logs and track the source of individual logins.
  • Use a variety of relational and non-relational database types to store data. The full list of supported databases in available from the DataNucleus web site (our middleware).

API

The framework is open source and meant for you to extend it for your specific project! If it doesn't have the feature you need, use some simple Java programming and create it. Some things we have used it to do on whaleshark.org are:

  • Quickly generate open and closed capture history files for population modeling in statistical packages, such as U-CARE, CloseTest, and Program MARK
  • Generate statistical reports
  • Rely on spam filters to block spurious data submission

The development of additional functionality is currently underway.

Donation

You can help move Wildbook forward by making a donation! Your donation is tax deductible in the United States.

Feedback

Please send feedback to jason at whaleshark dot org. Your ideas to improve Wildbook are most welcome!

History

Wildbook was started by Jason Holmberg as the software behind the Wildbook for Whale Sharks, which is a multiuser, web-based, research application for studying whale sharks (Rhincodon typus). The aim of WIldbook for Whale Sharks is to prevent individual “silos” of whale shark data and to promote a global, cooperative approach to whale shark research using the Web as a communications and research platform. The Library went on-line and began collecting whale shark encounter data from the web in January 2003. In early 2004, the pattern-recognition system that allows the Library to distinguish between individual whale sharks using natural spot patterning was integrated. Since its first line of code, this Wildbook has seen continuous feature additions, bug fixes, and performance enhancements. Our work to maintain and enhance the Library is ongoing and requires knowledge of Java, J2EE, JDO, PHP , Flash/Flex, HTML , XML , RSS , a wee bit of Python, and CSS .

Publications

Design Influences

The following publications have influenced our design and development of Wildbook:

Wildbook is a registered trademark of Wild Me.

Wildbook is distributed under the GPL v2 open source license.