CVMay 28, 2021

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

arXiv:2105.13979v28 citations
Originality Incremental advance
AI Analysis

This work addresses animal monitoring and conservation by enabling efficient re-identification of Saimaa ringed seals, though it is incremental as it builds on existing feature pooling techniques for a specific domain.

The paper tackled the problem of individual re-identification of Saimaa ringed seals using pelage pattern matching, proposing a novel feature pooling method that aggregates local pattern features into fixed-size embedding vectors by considering spatial distributions, and it outperformed existing methods on this challenging dataset.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes