TY  - JOUR
A1  - Hahn-Klimroth, Maximilian Grischa
A1  - Kapetanopoulos, Tobias
A1  - Gübert, Jennifer
A1  - Dierkes, Paul Wilhelm
T1  - Deep learning-based pose estimation for African ungulates in zoos
T2  - Ecology and evolution
N2  - 1.Thedescriptionandanalysisofanimalbehavioroverlongperiodsoftimeisoneof the most important challenges in ecology. However, most of these studies are limited due to the time and cost required by human observers. The collection of data via video recordings allows observation periods to be extended. However, their evaluation by human observers is very time-consuming. Progress in automated evaluation, using suitable deep learning methods, seems to be a forward-looking approach to analyze even large amounts of video data in an adequate time frame.
2. In this study, we present a multistep convolutional neural network system for detecting three typical stances of African ungulates in zoo enclosures which works with high accuracy. An important aspect of our approach is the introduction of model averaging and postprocessing rules to make the system robust to outliers.
3. Our trained system achieves an in-domain classification accuracy of >0.92, which is improved to >0.96 by a postprocessing step. In addition, the whole system per- forms even well in an out-of-domain classification task with two unknown types, achieving an average accuracy of 0.93. We provide our system at https://github. com/Klimroth/Video-Action-Classifier-for-African-Ungulates-in-Zoos/tree/main/ mrcnn_based so that interested users can train their own models to classify im- ages and conduct behavioral studies of wildlife.
4. The use of a multistep convolutional neural network for fast and accurate clas- sification of wildlife behavior facilitates the evaluation of large amounts of image data in ecological studies and reduces the effort of manual analysis of images to a high degree. Our system also shows that postprocessing rules are a suitable way to make species-specific adjustments and substantially increase the accuracy of the description of single behavioral phases (number, duration). The results in the out-of-domain classification strongly suggest that our system is robust and achieves a high degree of accuracy even for new species, so that other settings (e.g., field studies) can be considered.
KW  - animal behavior states
KW  - automated monitoring
KW  - convolutional neural networks
KW  - deep learning tools
KW  - ecology of savannah animals
KW  - image classification
Y1  - 2021
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/61839
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30:3-618396
SN  - 2045-7758
VL  - 11
IS  - 11
SP  - 6015
EP  - 6032
PB  - John Wiley & Sons, Inc.
ER  -