Fieldwork

Data digging from photographs of moths using deep-learning-based object detection

Background Biodiversity decline disproportionally affects hyperdiverse, yet low and middle-income, tropical regions, and Lepidoptera are among the most impacted taxa. Whereas monitoring in these countries is essential, only implementing low-cost solutions can guarantee success. The recent automatic image analysing methods allow for fast and low-cost solutions in monitoring biodiversity. Lepidoptera monitoring is relatively simple and …

Fieldwork

Automated pollinator identification, community and interaction monitoring from video captures

Background In order to understand the processes behind the pollinator declines, besides monitoring species occurrences, we also have to focus on monitoring interactions. In addition to traditional trapping and observation methods, we should develop fast, reliable, and cheap automated methods which are capable of monitoring both species occurrences and interactions. Using cutting-edge tools in ecology, …