English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Understanding how biological communities respond to environmental changes isa key challenge in ecology and ecosystem management. The apparent decline ofinsect populations necessitates more biomonitoring but the time-consumingsorting and identification of taxa pose strong limitations on how many insectsamples can be processed. In turn, this affects the scale of efforts to mapinvertebrate diversity altogether. Given recent advances in computer vision, wepropose to replace the standard manual approach of human expert-based sortingand identification with an automatic image-based technology. We describe arobot-enabled image-based identification machine, which can automate theprocess of invertebrate identification, biomass estimation and sample sorting.We use the imaging device to generate a comprehensive image database ofterrestrial arthropod species. We use this database to test the classificationaccuracy i.e. how well the species identity of a specimen can be predicted fromimages taken by the machine. We also test sensitivity of the classificationaccuracy to the camera settings (aperture and exposure time) in order to moveforward with the best possible image quality. We use state-of-the-art Resnet-50and InceptionV3 CNNs for the classification task. The results for the initialdataset are very promising ($\overline{ACC}=0.980$). The system is general andcan easily be used for other groups of invertebrates as well. As such, ourresults pave the way for generating more data on spatial and temporal variationin invertebrate abundance, diversity and biomass.

Automatic image-based identification and biomass estimation of invertebrates