Bird Species Detection Net: Bird Species Detection Based on the Extraction of Local Details and Global Information Using a Dual-Feature Mixer

Sensors, Journal Year: 2025, Volume and Issue: 25(1), P. 291 - 291

Published: Jan. 6, 2025

Bird species detection is critical for applications such as the analysis of bird population dynamics and diversity. However, this task remains challenging due to local structural similarities class imbalances among species. Currently, most deep learning algorithms focus on designing feature extraction modules while ignoring importance global information. information essential accurate detection. To address limitation, we propose BSD-Net, a network. BSD-Net efficiently learns in pixels accurately detect consists two main components: dual-branch mixer (DBFM) prediction balancing module (PBM). The extracts features from dichotomous segments using attention convolution, expanding network’s receptive field achieving strong inductive bias, allowing network distinguish between similar details. balance balances difference space based pixel values each category, thereby resolving category improving accuracy. experimental results public benchmarks self-constructed Poyang Lake dataset demonstrate that outperforms existing methods, 45.71% 80.00% mAP50 with CUB-200-2011 datasets, respectively, 66.03% AP FBD-SV-2024, more location tasks video surveillance.

Language: Английский

Progress and prospect of biomimetic optical materials: a review

Biogeotechnics, Journal Year: 2025, Volume and Issue: unknown, P. 100167 - 100167

Published: Feb. 1, 2025

Language: Английский