Life-long Learning with Applications in Monitoring Biodiversity
In biodiversity research sensors already collect numerous data that is difficult if not impossible to evaluate by hand. Examples are camera traps continuouslymonitoring the environment to evaluate distribution of species over a certain area and time. This leads to a big-data problem where the data contains the knowledge the researcher is gaining for. Computer vision and machine learning can provide methods for (semi-)automatic evaluation and structuring of large data streams. This presentation summarizes first results for automatic analysis of images and videos that keep the human in the loop. Quantitative evaluation for automatic bird species and moths classification, as well as interactive image retrieval demonstrates the current state. It also points to potentials of active and incremental learning in such an application.