EDEN: Deep Feature Distribution Pooling for Saimaa Ringed Seals Pattern Matching

TL;DR

This paper introduces EDEN, a novel deep feature pooling method that improves individual re-identification of Saimaa ringed seals by effectively capturing global and local pattern features for conservation efforts.

Contribution

The paper presents a new feature pooling approach using eigen decomposition of covariance matrices to enhance animal re-identification accuracy.

Findings

Outperforms existing methods on Saimaa seal data

Effective aggregation of local and global features

Improves accuracy of individual identification

Abstract

In this paper, pelage pattern matching is considered to solve the individual re-identification of the Saimaa ringed seals. Animal re-identification together with the access to large amount of image material through camera traps and crowd-sourcing provide novel possibilities for animal monitoring and conservation. We propose a novel feature pooling approach that allow aggregating the local pattern features to get a fixed size embedding vector that incorporate global features by taking into account the spatial distribution of features. This is obtained by eigen decomposition of covariances computed for probability mass functions representing feature maps. Embedding vectors can then be used to find the best match in the database of known individuals allowing animal re-identification. The results show that the proposed pooling method outperforms the existing methods on the challenging Saimaa ringed seal image data.