Exploring Text-Guided Wildlife Counting in Aerial Imagery Without Additional Training
Open Access
Abstract
Reliable wildlife counts support population assessment and conservation planning, while aerial imagery enables surveys over large or inaccessible areas. Most automated counting systems are developed for predefined animal categories and require retraining when targets change. Text-guided zero-shot counting offers a flexible alternative by specifying the target through language without category-specific retraining, but how such methods transfer to aerial wildlife imagery remains underexplored. Existing aerial animal datasets vary widely in tasks, categories, environments, resolution, and acquisition conditions, making consistent evaluation difficult. We therefore construct WZSC-5K by consolidating, cleaning, and harmonizing existing resources into a standardized 5000-image benchmark covering 28 animal categories. Existing zero-shot counters developed on natural images face challenges on the aerial wildlife imagery represented in WZSC-5K. Small targets and cluttered backgrounds complicate spatial localization, while top-down views can weaken the correspondence between generic text concepts and animal appearance. We therefore develop a training-free adaptation that uses spatial correspondence from a frozen vision foundation model to improve spatial coherence and incorporates aerial context to improve visual-text alignment. Without additional aerial-domain training, the proposed method reduces MAE and RMSE by 13.82% and 5.35% relative to the baseline model, demonstrating improved transfer under the standardized WZSC-5K evaluation setting.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFF1302700)
- National Forestry and Grassland Administration (202303)
- Outstanding Youth Team Project of Central Universities (QNTD202504)
This publication has 36 references indexed in Scilit:
- Wildlife detection, counting and survey using satellite imagery: are we there yet?GIScience & Remote Sensing, 2024
- CherryChèvre: A fine-grained dataset for goat detection in natural environmentsScientific Data, 2023
- Counting animals in aerial images with a density map estimation modelEcology and Evolution, 2023
- From crowd to herd counting: How to precisely detect and count African mammals using aerial imagery and deep learning?ISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Few-shot Object Counting with Similarity-Aware Feature Enhancement2023
- Multispecies detection and identification of African mammals in aerial imagery using convolutional neural networksRemote Sensing in Ecology and Conservation, 2021
- Graph Regularized Flow Attention Network for Video Animal Counting From DronesIEEE Transactions on Image Processing, 2021
- Detecting mammals in UAV images: Best practices to address a substantially imbalanced dataset with deep learningRemote Sensing of Environment, 2018
- Unmanned aircraft systems in wildlife research: current and future applications of a transformative technologyFrontiers in Ecology and the Environment, 2016
- Precision wildlife monitoring using unmanned aerial vehiclesScientific Reports, 2016