Diving with Penguins: Detecting Penguins and their Prey in Animal-borne Underwater Videos via Deep Learning
This work addresses conservation needs for an endangered species by automating the analysis of animal-borne video data, though it is incremental in applying existing deep learning methods to a new domain.
The paper tackles the problem of analyzing underwater hunting behaviors of endangered African penguins by introducing a deep learning system that detects penguins with 98.0% mAP50 and fish with 73.3% mAP50, and provides initial results for predation behavior recognition.
African penguins (Spheniscus demersus) are an endangered species. Little is known regarding their underwater hunting strategies and associated predation success rates, yet this is essential for guiding conservation. Modern bio-logging technology has the potential to provide valuable insights, but manually analysing large amounts of data from animal-borne video recorders (AVRs) is time-consuming. In this paper, we publish an animal-borne underwater video dataset of penguins and introduce a ready-to-deploy deep learning system capable of robustly detecting penguins (mAP50@98.0%) and also instances of fish (mAP50@73.3%). We note that the detectors benefit explicitly from air-bubble learning to improve accuracy. Extending this detector towards a dual-stream behaviour recognition network, we also provide the first results for identifying predation behaviour in penguin underwater videos. Whilst results are promising, further work is required for useful applicability of predation behaviour detection in field scenarios. In summary, we provide a highly reliable underwater penguin detector, a fish detector, and a valuable first attempt towards an automated visual detection of complex behaviours in a marine predator. We publish the networks, the DivingWithPenguins video dataset, annotations, splits, and weights for full reproducibility and immediate usability by practitioners.