The drastic decline in insect populations (“insect die-off”) is causing great concern for ecosystems worldwide. There is a lack of reliable and comprehensive surveys of insect populations in order to reliably record and understand these developments. The aim of the project is to develop a practical system for nationwide, automated monitoring of nocturnal insects in order to reliably document population changes. High-resolution, robust, automatic camera traps are used to capture insects that are attracted by a UV lamp. Initially, the relatively well-known nocturnal large butterflies with more than 1100 species in Germany will be investigated. The project will develop systems for data transmission, storage, and image annotation and investigate fundamental methodological questions, for example which insect groups are fundamentally suitable for the method.

Our subproject on AI image analysis

We are developing robust algorithms for insect localization and species identification of nocturnal insects by using latest technologies from computer vision and machine learning. In general, our fully automated image analysis consists of the following two phases.

Webdemo

An online demo system is available here.