Automated distance estimation for wildlife camera trapping

A non-invasive approach to measuring body dimensions of wildlife with camera traps: A felid field trial

Dimensions of body size are an important measurement in animal ecology, although they can be difficult to obtain due to the effort and cost associated with the invasive nature of these measurements. We avoid these limitations by using camera trap images to derive dimensions of animal size. To obtain measurements of object dimensions using this method, the size of the object in pixels, the focal length of the camera, and the distance to that object must be known. We describe a novel approach of obtaining the distance to the object through the creation of a portable distance marker, which, when photographed, creates a "reference image" to determine the position of the animal within an image. This method allows for the retrospective analysis of existing datasets and eliminates the need for permanent in-field distance markers. We tested the accuracy of this methodology under controlled conditions with objects of known size resembling Felis catus, our study species, validating the legitimacy of our method of size estimation. We then apply our method to measure feral cat body size using images collected in Tasmania, Australia. The precision of our methodology was evaluated by comparing size estimates across individual cats, revealing consistent and reliable results. The average height (front paw to shoulder) of the feral cats sampled was 25.25 cm (CI = 24.4, 26.1) and the average length (base of tail to nose) was 47.48 cm (CI = 46.0, 48.9), suggesting wild feral cats in our study area are no larger than their domestic counterparts. Given the success of its application within our study, we call for further trails with this method across a variety of species.

The Internet of Animals: what it is, what it could be

One of the biggest trends in ecology over the past decade has been the creation of standardized databases. Recently, this has included live data, formal linkages between disparate databases, and automated analytics, a synergy that we recognize as the Internet of Animals (IoA). Early IoA systems relate animal locations to remote-sensing data to predict species distributions and detect disease outbreaks, and use live data to inform management of endangered species. However, meeting the future potential of the IoA concept will require solving challenges of taxonomy, data security, and data sharing. By linking data sets, integrating live data, and automating workflows, the IoA has the potential to enable discoveries and predictions relevant to human societies and the conservation of animals.

SOCRATES: Introducing Depth in Visual Wildlife Monitoring Using Stereo Vision

The development and application of modern technology are an essential basis for the efficient monitoring of species in natural habitats to assess the change of ecosystems, species communities and populations, and in order to understand important drivers of change. For estimating wildlife abundance, camera trapping in combination with three-dimensional (3D) measurements of habitats is highly valuable. Additionally, 3D information improves the accuracy of wildlife detection using camera trapping. This study presents a novel approach to 3D camera trapping featuring highly optimized hardware and software. This approach employs stereo vision to infer the 3D information of natural habitats and is designated as StereO CameRA Trap for monitoring of biodivErSity (SOCRATES). A comprehensive evaluation of SOCRATES shows not only a 3.23% improvement in animal detection (bounding box mAP75), but also its superior applicability for estimating animal abundance using camera trap distance sampling. The software and documentation of SOCRATES is openly provided.