Image-Based Leopard Seal Recognition: Approaches and Challenges in Current Automated Systems

TL;DR

This paper reviews current machine learning-based methods for recognizing leopard seals in their natural habitat, emphasizing recent advancements like vision transformers and discussing ongoing challenges in automated species identification.

Contribution

It provides a comprehensive synthesis of existing approaches in seal recognition, highlighting the integration of vision transformers and identifying key challenges in the field.

Findings

Vision transformers improve recognition accuracy.

Traditional methods are labor-intensive and less effective.

Current challenges include occlusion and environmental variability.

Abstract

This paper examines the challenges and advancements in recognizing seals within their natural habitats using conventional photography, underscored by the emergence of machine learning technologies. We used the leopard seal, \emph{Hydrurga leptonyx}, a key species within Antarctic ecosystems, to review the different available methods found. As apex predators, Leopard seals are characterized by their significant ecological role and elusive nature so studying them is crucial to understand the health of their ecosystem. Traditional methods of monitoring seal species are often constrained by the labor-intensive and time-consuming processes required for collecting data, compounded by the limited insights these methods provide. The advent of machine learning, particularly through the application of vision transformers, heralds a new era of efficiency and precision in species monitoring. By leveraging state-of-the-art approaches in detection, segmentation, and recognition within digital imaging, this paper presents a synthesis of the current landscape, highlighting both the cutting-edge methodologies and the predominant challenges faced in accurately identifying seals through photographic data.