Programs presented in the first workshop of Wildlife photo-ID network (November 3-6, 2014, Joensuu, Finland)

 

IBEIS

  • Image-Based Ecological Information System (IBEIS) turns massive collections of images into a high-resolution information database about animals
  • Current tools – the HotSpotter software for individual animal identification and the WildBook ecological information management system
  • IBEIS is a large autonomous computational system that starts from image collections and progresses all the way to answering ecological and conservation queries, such as population sizes, species distributions and interactions, and movement patterns
  • The images are taken by field scientists, tourists, and incidental photographers, and are gathered from camera traps and autonomous vehicles
  • IBEIS can detect various species of animals in those images and identify individual animals of most striped, spotted, wrinkled or notched species
    • It stores the information about who the animals are, where they are and when they are there in a database and provides query tools to that data for scientists and curious people to find out what those animals are doing and why they are doing it

SEE MORE

 

Extract Compare

  • Automated photo-id systems developed for various species:
    • Shark, cheetahs, tigers, seal, wildebeest, zebra, salamander, chital, sand lizard, crested newt, adders, clouded leopard, leopard, frog, lynx, giraffe, wild dogs, cobras
  • Fitting the image to 3D surface model programs capture a pattern that is unaffected by the camera angle or posture
  • Program compares the new pattern with previous patterns stored in a library and display the most likely matches
  • Suitable images may be from researchers, tourists or camera traps and the resulting database of match results can be used to provide the usual benefits of mark/recapture studies
    • Monitoring of population size and other parameters
    • Determining the fate of individual animals
    • Encouraging cooperation between different research groups and so on

SEE MORE

 

Discovery

  • Provides a dynamic, user-friendly platform to assist researchers not only with the matching of individual photo-ID data, but also at the multitude of steps of field data collection and the complex data management and analyses that follow after individual matching is completed
  • System assists with filtering of raw data and all levels of individual-ID matching
    • It assists with processing, storing and managing digital images
    • It provides file naming routines and links sighting information with environmental, geographic, and numerous user-defined parameters
    • It provides graphic displays of data and basic analytical tools
  • Can be used to centralize a database for multiple species and multiple study areas
    • It is particularly useful for maintaining a single database for research projects collecting data at large geographical scales and between multiple research teams working on different databases
    • Also provides a means of linking the new system with traditional datasets based on film photography, to form continuous complete datasets

System has been designed so that it can easily facilitate integration of all collected and stored data to and from other tools; with a multitude of dynamic functions it was designed to meet project-specific requirements and user-specific needs

SEE MORE

 

I3S

  • Free computer-aided photo-identification application that relies on natural marks to identify individual animals
    • I3S has proven very successful in identification of these species based on their natural spots
    • I3S helps the researcher to extract the spot pattern and then compares this pattern against all animals in the database and shows the researcher the most relevant results
    • When tested on a large whale shark database (~500 individuals, ~1600 images), I3S was able to recognize over 92% of recurring animals in the top 10 (2 reference images)
    • Upon addition to the photo database, I3S expects the researcher to provide information about the spot pattern. This step takes about one to two minutes. After this step, the search is entirely automatic and highly accurate
  • Initially, the user has to point out the most distinguishing features (i.e. the spots and reference features, e.g. fins) of the unknown individual
    •  In the next step, I3S assists the user in the tedious task of matching the (shark) image with a collection of images of known sharks
    • Results are shown as a ranked list. The user will always be responsible for making the final match between the unknown image and an image from the database

SEE MORE

Other programs available

Coastal Walkabout An open access citizen science initiative which utilises smart phone technology and social media to engage and motivate local communities to gather scientific observations within coastal and estuarine environments.

 

OBIS-SEAMAP Ocean Biogeographic Information System Spatial Ecological Analysis of Megavertebrate Populations (=OBIS-SEAMAP) is online global biogeographic database, aggregating marine mammal, seabird and sea turtle observation data from across the globe. It includes different kind of data types (telemetry tracking, acoustic data, photo-ID etc.) In photo-ID studies OBIS-SEAMAP can be used as online interface for images and data from photo‐identification catalogs to facilitate collaboration among photo‐ID researchers.

 

Robo Realm

  • Application for use in computer vision, image analysis, and robotic vision systems
  • Using an easy point and click interface RoboRealm simplifies vision programming! With an inexpensive USB webcam and the PC you already have you can now add machine vision to your robotic projects
  • Image and/or video processing can be technically difficult. Home robots are continuously moving towards PC based systems (laptop, netbook, embedded, etc.) that have the power to support complex image processing functions
  • We've compiled many image processing functions into an easy to use windows based application that you can use with a webcam, TV Tuner, IP Camera, etc.
  • Use RoboRealm to see your robot's environment, process the acquired image, analyze what needs to be done and send the needed signals to your robot's motors, servos, etc.
    • For example, you can use RoboRealm to track colored objects, navigate with obstacle avoidance, identify fiducials that let your robot know where it is, and much more

 

FinBase

  • Customized Microsoft Access database system that stores and manages textual and numerical data from photo-identification surveys, and performs many of the tasks associated with image management and analysis
  • Maintains a catalog in which individuals can possess multiple attributes (e.g., chopped dorsal fin, apex dorsal fin notch, lower dorsal fin notch, peduncle scar/notch, etc.), any combination of which can be selected to sort the catalog
  • This expedites the matching process by allowing analysts to sort the entire catalog based on the similarity of each existing catalog individuals' attributes to those of newly sighted individuals
  • Developed by NOAA to store and manage data for research being conducted by NOAA's National Ocean Service and Fisheries field offices

A number of research programs have adopted the system for a variety of species

 

Darwin

  • Software system which allows marine scientists to maintain information for the study of various behavioral and ecological patterns of bottlenose dolphins, Tursiops truncatus
  • The software provides a graphical user interface to access a collection of digital dorsal fin images along with textual information which describes individual animals as well as relevant sighting data
    • Users may query the system with the name of a specific individual or the entire collection may be sorted and viewed based upon sighting location, sighting date, or damage category
    • Alternatively, the researcher may query a database of previously identified dolphin dorsal fin images with an image of an unidentified dolphin's fin
    • DARWIN responds with a rank ordered list of database fin images that most closely resemble the query image

 

Stripe Spotter

  • An automatic individual animal identification system for animals with prominent stripes or patches
  • It is intended to be used to identify animals in the wild, and to build biometric databases using photographs taken in the field
    • Currently used to build a zebra-print database for Plains and Grevys zebra in Kenya
  • Completely free and open-source
    • Runs on Windows, Mac and Linux
    • Allows the creation of databases with ecological metadata
    • Can use Dropbox or similar service to synchronize database between many users

 

WILD ID

  • A non-invasive photographic identification software program (JAVA)
  • Uses the scale invariant feature transform algorithm for pattern extraction
  • Developed at Dartmouth to individually identify wildebeest by their shoulder stripe patterns

 

SLOOP

  • Pattern retrieval engine for Animal Biometrics that uses cloud computing, machine learning and crowd sourcing to greatly improve the study of animal movement and behavior
  • SLOOP applies pattern recognition to same images. It then challenges online crowds to sort and identify a small proportion of potential matches. SLOOP learns from the citizen scientist's skill to match images of individual animals more accurately and far faster than by previous methods

 

WildBook

  • Open source software framework that supports mark-recapture, molecular ecology and social ecology studies
  • Complementary software application for analyzing wildlife data 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

Example catalogs and other applications:

Humpback whale

Humpback whale

Humpback whale

Whale shark

Manta

 

Ravenous

WildMe  and in facebook

Finding Rover

Autopano

Tiger Nation

Zooniverse

If other interesting programs or applications are missing, please contact us (photo-id(at)uef.fi)