Using ORB, BoW and SVM to identify and track tagged Norway lobster Nephrops norvegicus (L.)

Sustainable capture policies of many species strongly depend on the understanding
of their social behaviour. Nevertheless, the analysis of emergent behaviour
in marine species poses several challenges. Usually animals are captured and
observed in tanks, and their behaviour is inferred from their dynamics and interactions.
Therefore, researchers must deal with thousands of hours of video data. Without
loss of generality, this paper proposes a computer vision approach to identify
and track specific species, the Norway lobster, Nephrops norvegicus. We propose an
identification scheme were animals are marked using black and white tags with a
geometric shape in the center (holed triangle, filled triangle, holed circle and filled
circle). Using a massive labelled dataset; we extract local features based on the ORB
descriptor. These features are a posteriori clustered, and we construct a Bag of Visual
Words feature vector per animal. This approximation yields us invariance to rotation
and translation. A SVM classifier achieves generalization results above 99%. In
a second contribution, we will make the code and training data publically available.