ViXeN: View eXtract aNnotate Multimedia Data

Post provided by KadaMbari Devarajan

At a time when data is everywhere, and data science is being talked about as the future in different fields, a method that produces huge amounts of multimedia data is camera-trapping. We need ways to manage these kinds of media data efficiently. ViXeN is an attempt to do just that.

Camera traps have been a game-changer for ecological studies, especially those involving mammals in the wild. This has resulted in an increasing amount of camera trap datasets. However, the tools to manage camera trap data tend to be very specific and customised for images. They typically come with stringent data organisation requirements. There’s a growing amount of multimedia datasets and a lack of tools that can manage several types of media data.

In ‘ViXeN: An open‐source package for managing multimedia data’ we try to fix this visible gap. Camera trap management is a very specific a use-case. We thought that the field was missing general-purpose tools, capable of handling a variety of media data and formats, that were also free and open source. ViXeN was born from this idea. It stands for View eXtract aNnotate (media data). The name is also an ode to the canids I was studying at the time which included two species of foxes.


Example camera trap video Continue reading

Citizen Science Projects Have a Surprising New Partner – The Computer

Below is a press release about the Methods in Ecology and Evolution article ‘Identifying animal species in camera trap images using deep learning and citizen science‘ taken from the University of Minnesota-Twin Cities.

The computer’s accuracy rates for identifying specific species, like this warthog, are between 88.7 percent and 92.7 percent. Image credit: ©Panthera

The computer’s accuracy rates for identifying specific species, like this warthog, are between 88.7 percent and 92.7 percent. ©Panthera

For more than a decade, citizen science projects have helped researchers use the power of thousands of volunteers who help sort through datasets that are too large for a small research team. Previously, this data generally couldn’t be processed by computers because the work required skills that only humans could accomplish.

Now, computer machine learning techniques that teach the computer specific image recognition skills can be used in crowdsourcing projects to deal with massively increasing amounts of data—making computers a surprising new partner in citizen science projects.

Continue reading

Estimating the Size of Animal Populations from Camera Trap Surveys

Below is a press release about the Methods paper ‘Distance sampling with camera traps‘ taken from the Max Planck Society.

A Maxwell's duiker photographed using a camera trap. Marie-Lyne Després-Einspenner

A Maxwell’s duiker photographed using a camera trap. ©Marie-Lyne Després-Einspenner

Camera traps are a useful means for researchers to observe the behaviour of animal populations in the wild or to assess biodiversity levels of remote locations like the tropical rain forest. Researchers from the University of St Andrews, the Max Planck Institute for Evolutionary Anthropology (MPI-EVA) and the German Centre for Integrative Biodiversity Research (iDiv) recently extended distance sampling analytical methods to accommodate data from camera traps. This new development allows abundances of multiple species to be estimated from camera trapping data collected over relatively short time intervals – information critical to effective wildlife management and conservation.

Remote motion-sensitive photography, or camera trapping, is revolutionising surveys of wild animal populations. Camera traps are an efficient means of detecting rare species, conducting species inventories and biodiversity assessments, estimating site occupancy, and observing behaviour. If individual animals can be identified from the images obtained, camera trapping data can also be used to estimate animal density and population size – information critical to effective wildlife management and conservation. Continue reading

Just snap it! Using Digital Cameras to Discover What Birds Eat

Post provided by Davide Gaglio and Richard Sherley

Digital photography has revolutionised the way we view ourselves, each other and our environment. The use of automated cameras (including camera traps) in particular has provided remarkable opportunities for biological research. Although mostly used for recreational purposes, the development of user-friendly, versatile auto-focus digital single lens reflex (DSLR) cameras allows researchers to collect large numbers of high quality images at relatively little cost.

These cameras can help to answer questions such as ‘What does that species feed its young?’ or ‘How big is this population?’, and can provide researchers with glimpses of rare events or previously unknown behaviours. We used these powerful research tools to develop a non-invasive method to assess the diets of birds that bring visible prey (e.g. prey carried in the bill or feet) back to their chicks. Continue reading

Issue 7.12

Issue 7.12 is now online!

The final 2016 issue of Methods is now online!

This month’s issue contains four Applications articles and two Open Access articles, all of which are freely available.

– iNEXT: The R package iNEXT (iNterpolation/EXTrapolation) provides simple functions to compute and plot the seamless rarefaction and extrapolation sampling curves for the three most widely used members of the Hill number family (species richness, Shannon diversity and Simpson diversity).

– camtrapR: A new toolbox for flexible and efficient management of data generated in camera trap-based wildlife studies. The package implements a complete workflow for processing camera trapping data.

– rotl: An R package to search and download data from the Open Tree of Life directly in R. It uses common data structures allowing researchers to take advantage of the rich set of tools and methods that are available in R to manipulate, analyse and visualize phylogenies.

– Fluctuating-temperature chamber: A design for economical, programmable fluctuating-temperature chambers based on a relatively small commercially manufactured constant temperature chamber modified with a customized, user-friendly microcontroller.

Continue reading

Issue 7.10

Issue 7.10 is now online!

The October issue of Methods is now online!

This month’s issue contains three Applications articles and two Open Access articles, all of which are freely available.

– CODYN: New analytical tools applied to long-term data demonstrate that ecological communities are highly dynamic over time. The R package, library(“codyn”), helps ecologists implement these tools and gain insi–ghts into ecological community dynamics.

– Geometric Morphometrics: A tool for the R statistical environment that optimises the smoothing procedure for 3D surfaces used in Geometric Morphometrics.

– TRAPPER: Open source, multi-user software that facilitates analysis of videos and images, provides spatial filtering and web-mapping, allows flexible implementation of specific data collection protocols, and supports data re-use and (re)discovery.

Continue reading

Automatic Camera Monitoring: A Window into the Daily Life of Pollinators

Post provided by Ronny Steen

Image from the Canon PowerShot camera with CHDK script ‘Motion Detect Plus’. The thistle flower being visited by ♀ honeybee Apis mellifera L.

Image from the Canon PowerShot camera with CHDK script ‘Motion Detect Plus’. The thistle flower being visited by ♀ honeybee Apis mellifera L.

Pollinators have fascinated ecologists for decades, and they have traditionally been monitored by on-site human observations. This can be a time-consuming enterprise and – more importantly – species identification and recordings of behaviour have to be registered at the time of observation. This has two complications:

  1. While writing notes, or recording them electronically, the observer cannot continue focusing on the animal or behaviour in question.
  2. Such data then have to be transcribed, with the risk of making transcription errors.

Bringing Monitoring into the 21st Century

Although on-site human observations have predominated, today’s widespread availability of digital monitoring equipment has enabled unique data on flower visitors to be collected. In my research, I have used a time-efficient automated procedure for monitoring flower-visiting animals – namely foraging bumblebees visiting focal white clovers and honeybees visiting thistles.

Continue reading