Individual minke whale recognition using deep learning convolutional neural networks

• Published in: Journal of Geoscience and Environment Protection
• Main Authors: Konovalov, Dmitry A., Hillcoat, Suzanne, Williams, Genevieve, Birtles, R. Alastair, Gardiner, Naomi, Curnock, Matthew I.
• Format: Article in Journal/Newspaper
• Language: unknown
• Published: Scientific Research 2018
• Subjects: Balaenoptera acutorostrata; minke whale
• Online Access: https://researchonline.jcu.edu.au/54297/1/GEP_2018051813434517.pdf

The only known predictable aggregation of dwarf minke whales (Balaenoptera acutorostrata subsp.) occurs in the Australian offshore waters of the northern Great Barrier Reef in May-August each year. The identification of individual whales is required for research on the whales’ population characteristics and for monitoring the potential impacts of tourism activities, including commercial swims with the whales. At present, it is not cost-effective for researchers to manually process and analyze the tens of thousands of underwater images collated after each observation/tourist season, and a large data base of historical non-identified imagery exists. This study reports the first proof of concept for recognizing individual dwarf minke whales using the Deep Learning Convolutional Neural Networks (CNN).The “off-the-shelf” Image net-trained VGG16 CNN was used as the feature-encoder of the perpixel sematic segmentation Automatic Minke Whale Recognizer (AMWR). The most frequently photographed whale in a sample of 76 individual whales (MW1020) was identified in 179 images out of the total 1320 images provided. Training and image augmentation procedures were developed to compensate for the small number of available images. The trained AMWR achieved 93% prediction accuracy on the testing subset of 36 positive/MW1020 and 228 negative/not-MW1020 images, where each negative image contained at least one of the other 75 whales. Furthermore on the test subset, AMWR achieved 74% precision, 80% recall, and 4% false-positive rate, making the presented approach comparable or better to other state-of-the-art individual animal recognition results.