Animal Re-Identification on Microcontrollers

2025-12-08

AI Summary

Deploying animal re-identification (Re-ID) models on resource-constrained edge devices—such as microcontrollers—in wild and livestock settings is challenging due to stringent memory, compute, and input-resolution constraints. Method: We propose a lightweight Animal Re-ID system tailored for low-resolution inputs. It employs a scalable CNN backbone derived from MobileNetV2 with aggressive depth compression; integrates knowledge distillation–guided model pruning and quantization; and adopts a data-efficient fine-tuning strategy requiring only three images per class. Contribution/Results: On six public benchmarks, our model achieves over 100× reduction in parameter count while maintaining state-of-the-art retrieval accuracy. Evaluated on a newly collected cattle dataset, it enables full on-device deployment—achieving zero Top-1 accuracy degradation, sub-512 KB memory footprint, and, for the first time, real-time inference on MCU-class hardware.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Image and Video Retrieval
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Camera-based animal re-identification (Animal Re-ID) can support wildlife monitoring and precision livestock management in large outdoor environments with limited wireless connectivity. In these settings, inference must run directly on collar tags or low-power edge nodes built around microcontrollers (MCUs), yet most Animal Re-ID models are designed for workstations or servers and are too large for devices with small memory and low-resolution inputs. We propose an on-device framework. First, we characterise the gap between state-of-the-art Animal Re-ID models and MCU-class hardware, showing that straightforward knowledge distillation from large teachers offers limited benefit once memory and input resolution are constrained. Second, guided by this analysis, we design a high-accuracy Animal Re-ID architecture by systematically scaling a CNN-based MobileNetV2 backbone for low-resolution inputs. Third, we evaluate the framework with a real-world dataset and introduce a data-efficient fine-tuning strategy to enable fast adaptation with just three images per animal identity at a new site. Across six public Animal Re-ID datasets, our compact model achieves competitive retrieval accuracy while reducing model size by over two orders of magnitude. On a self-collected cattle dataset, the deployed model performs fully on-device inference with only a small accuracy drop and unchanged Top-1 accuracy relative to its cluster version. We demonstrate that practical, adaptable Animal Re-ID is achievable on MCU-class devices, paving the way for scalable deployment in real field environments.

Problem

• Develops microcontroller-compatible animal re-identification models for edge deployment
• Addresses memory and resolution constraints of wildlife monitoring devices
• Enables on-device inference with minimal accuracy loss for field applications

Innovation

• MobileNetV2 backbone scaled for low-resolution inputs
• Data-efficient fine-tuning with only three images per identity
• Compact model reduces size by over two orders of magnitude