No abstract

No abstract

Determining which species are at greatest risk, where they are most vulnerable, and what are the trajectories of their communities and populations is critical for conservation and management. Globally distributed, wide-ranging whales and dolphins present a particular challenge in data collection because no single research team can record data over biologically meaningful areas. Flukebook.org is an open-source web platform that addresses these gaps by providing researchers with the latest computational tools. It integrates photo-identification algorithms with data management, sharing, and privacy infrastructure for whale and dolphin research, enabling the global collaborative study of these global species. With seven automatic identification algorithms trained for 15 different species, resulting in 37 species-specific identification pipelines, Flukebook is an extensible foundation that continually incorporates emerging AI techniques and applies them to cetacean photo identification through continued collaboration between computer vision researchers, software engineers, and biologists. With over 2.0 million photos of over 52,000 identified individual animals submitted by over 250 researchers, the platform enables a comprehensive understanding of cetacean populations, fostering international and cross-institutional collaboration while respecting data ownership and privacy. We outline the technology stack and architecture of Flukebook, its performance on real-world cetacean imagery, and its development as an example of scalable, extensible, and reusable open-source conservation software. Flukebook is a step change in our ability to conduct large-scale research on cetaceans across biologically meaningful geographic ranges, to rapidly iterate population assessments and abundance trajectories, and engage the public in actions to protect them.

No abstract

No abstract

Photo identification is an important tool in the conservation management of endangered species, and recent developments in artificial intelligence are revolutionizing existing workflows to identify individual animals. In 2015, the National Oceanic and Atmospheric Administration hosted a Kaggle data science competition to automate the identification of endangered North Atlantic right whales (Eubalaena glacialis). The winning algorithms developed by Deepsense.ai were able to identify individuals with 87% accuracy using a series of convolutional neural networks to identify the region of interest, create standardized photographs of uniform size and orientation, and then identify the correct individual. Since that time, we have brought in many more collaborators as we moved from prototype to production. Leveraging the existing infrastructure by Wild Me, the developers of Flukebook, we have created a web-based platform that allows biologists with no machine learning expertise to utilize semi-automated photo identification of right whales. New models were generated on an updated dataset using the winning Deepsense.ai algorithms. Given the morphological similarity between the North Atlantic right whale and closely related southern right whale (Eubalaena australis), we expanded the system to incorporate the largest long-term photo identification catalogs around the world including the United States, Canada, Australia, South Africa, Argentina, Brazil, and New Zealand. The system is now fully operational with multi-feature matching for both North Atlantic right whales and southern right whales from aerial photos of their heads (Deepsense), lateral photos of their heads (Pose Invariant Embeddings), flukes (CurvRank v2), and peduncle scarring (HotSpotter). We hope to encourage researchers to embrace both broad data collaborations and artificial intelligence to increase our understanding of wild populations and aid conservation efforts.

Photo-identification of individual sperm whales (Physeter macrocephalus) is the primary technique for mark-recapture-based population analyses for the species The visual appearance of the fluke - with its distinct nicks and notches - often serves as the primary visual differentiator, allowing humans to make recorded sightings of specific individuals. However, the advent of digital photography and the significant increase in volume of images from multiple projects in combination with pre-existing historical catalogs has made applying the method more challenging.with the required human labor for de-duplication (reduction of Type II errors) and reconciliation of sightings between large datasets too cost- and time- prohibitive. To address this, we trained and evaluated the accuracy of PIE v2 (a triplet loss network) along with two existing fluke trailing edge-matching algorithms, CurvRank v2 and Dynamic Time Warping (DTW), as a mean to speed comparison among a high volume of photographs. Analyzed data were collected from a curated catalog of well-known sperm whales sighted across years (2005-2018) off the island of Dominica. The newly-trained PIE model outperformed the older CurvRank and DTW algorithms, and PIE provided the following top-k individual ID matching accuracy on a standard min-3/max-10 sighting training data set: Rank-1: 87.0%, Rank-5: 90.5%, and Rank-12: 92.5%. An essential aspect of PIE is that it can learn new individuals without network retraining, which can be immediately applied in the presence of (and for the resolution of) duplicate individuals in overlapping catalogs. Overall, our results recommend the use of PIE v2 and CurvRank v2 for ID reconciliation in combination due to their complementary performance.

Photographic-identification (photo-ID) of bottlenose dolphins using individually distinctive features on the dorsal fin is a well-established and useful tool for tracking individuals; however, this method can be labor-intensive, especially when dealing with large catalogs and/or infrequently surveyed populations. Computer vision algorithms have been developed that can find a fin in an image, characterize the features of the fin, and compare the fin to a catalog of known individuals to generate a ranking of potential matches based on dorsal fin similarity. We examined if and how researchers use computer vision systems in their photo-ID process and developed an experiment to evaluate the performance of the most commonly used, recently developed, systems to date using a long-term photo-ID database of known individuals curated by the Chicago Zoological Society’s Sarasota Dolphin Research Program. Survey results obtained for the “Rise of the machines – Application of automated systems for matching dolphin dorsal fins: current status and future directions” workshop held at the 2019 World Marine Mammal Conference indicated that most researchers still rely on manual methods for comparing unknown dorsal fin images to reference catalogs of known individuals. Experimental evaluation of the finFindR R application, as well as the CurvRank, CurvRank v2, and finFindR implementations in Flukebook suggest that high match rates can be achieved with these systems, with the highest match rates found when only good to excellent quality images of fins with average to high distinctiveness are included in the matching process: for the finFindR R application and the CurvRank and CurvRank v2 algorithms within Flukebook more than 98.92% of correct matches were in the top 50-ranked positions, and more than 91.94% of correct matches were returned in the first ranked position. Our results offer the first comprehensive examination into the performance and accuracy of computer vision algorithms designed to assist with the photo-ID process of bottlenose dolphins and can be used to build trust by researchers hesitant to use these systems. Based on our findings and discussions from the “Rise of the Machines” workshop we provide recommendations for best practices for using computer vision systems for dorsal fin photo-ID.