Innovations in Camera Trapping Technology and Approaches: The Integration of Citizen Science and Artificial Intelligence

Abstract

Simple Summary: Camera traps, also known as "game cameras" or "trail cameras", have increasingly been used in wildlife research over the last 20 years. Although early units were bulky and the set-up was complicated, modern camera traps are compact, integrated units able to collect vast digital datasets. Some of the challenges now facing researchers include the time required to view, classify, and sort all of the footage collected, as well as the logistics of establishing and maintaining camera trap sampling arrays across wide geographic areas. One solution to this problem is to enlist or recruit the public for help as 'citizen scientists' collecting and processing data. Artificial Intelligence (AI) is also being used to identify animals in digital photos and video; however, this process is relatively new, and machine-based classifications are not yet fully reliable. By combining citizen science with AI, it should be possible to improve efficiency and increase classification accuracy, while simultaneously maintaining and promoting the benefits associated with public engagement with, and awareness of, wildlife.Abstract: Camera trapping has become an increasingly reliable and mainstream tool for surveying a diversity of wildlife species. Concurrent with this has been an increasing effort to involve the wider public in the research process, in an approach known as 'citizen science'. To date, millions of people have contributed to research across a wide variety of disciplines as a result. Although their value for public engagement was recognised early on, camera traps were initially ill-suited for citizen science. As camera trap technology has evolved, cameras have become more user-friendly and the enormous quantities of data they now collect has led researchers to seek assistance in classifying footage. This has now made camera trap research a prime candidate for citizen science, as reflected by the large number of camera trap projects now integrating public participation. Researchers are also turning to Artificial Intelligence (AI) to assist with classification of footage. Although this rapidly-advancing field is already proving a useful tool, accuracy is variable and AI does not provide the social and engagement benefits associated with citizen science approaches. We propose, as a solution, more efforts to combine citizen science with AI to improve classification accuracy and efficiency while maintaining public involvement.

eDNA metabarcoding for biodiversity assessment, generalist predators as sampling assistants

“…Thus, rapid, habitat-specific and non-invasive biodiversity assessments are urgently needed 2 . Biodiversity has been assessed, at varying geographic scales, by a variety of methods such as flight trapping, pitfall traps 3 , acoustic surveys 4 , camera traps 5 and field observations 6 . While these methods have been designed for application to specific environments, study systems, and species, they have several drawbacks and limitations.…”

Chimpanzee identification and social network construction through an online citizen science platform

“…Camera trap videos are being recorded and uploaded with higher quality and increasing efficiency, with the potential to view videos in real time as they are recorded. Video analysis by citizen scientists may be aided by hybrid approaches involving automated machine learning for species detection prior to citizen scientist identification of individuals and behaviors, making applications for research and conservation more streamlined and efficient (Green et al., 2020; Willi et al., 2019). Citizen science data accuracy can also be enhanced in various ways, for example by providing pretraining to citizen scientists (Nagy et al., 2012), or by taking advantage of experience citizen scientists already have (Silvertown et al., 2015) or that they acquire through their involvement in a citizen science project (Kelling et al., 2015; Swanson et al., 2016).…”

“…Therefore, it is necessary to assess the reliability of citizen scientist observations prior to relying on these data for subsequent analyses, particularly since identification errors can lead to analytical biases such as the overestimation of species abundance (Johansson et al., 2020; Stevick et al., 2001). Although machine learning has also advanced considerably in recent years, allowing the potential for automated detection of individuals from recorded images (Schofield et al., 2019), its implementation still poses challenges (Green et al., 2020). Simultaneously, the benefits of citizen science are numerous, suggesting that machine learning and citizen science can work as integrated, complementary approaches to collecting high‐quality data on individual animals (Green et al., 2020).…”

“…Although machine learning has also advanced considerably in recent years, allowing the potential for automated detection of individuals from recorded images (Schofield et al., 2019), its implementation still poses challenges (Green et al., 2020). Simultaneously, the benefits of citizen science are numerous, suggesting that machine learning and citizen science can work as integrated, complementary approaches to collecting high‐quality data on individual animals (Green et al., 2020).…”

The Verification of Ecological Citizen Science Data: Current Approaches and Future Possibilities

“…Community consensus may be preferable for schemes with sufficient participants, as crowdsourcing the assessment of physical evidence spreads the task of verification across a greater number of individuals, and can be particularly useful when verifying camera trap datasets, which can rapidly grow to very large sizes (Swanson et al 2016;Hsing et al 2018). Community consensus approaches can also be used alongside automated approaches in a hierarchical verification system (Green et al 2020). Once multiple users have classified a record, consensus algorithms can be applied to analyse classifications and to categorise confidence in a record (Siddharthan et al 2016;Hsing et al 2018).…”