Multimodal Digital Sensing of Early-Life Laying Hens: A Pilot Study Integrating Thermal, Acoustic, Optical-Flow and Environmental Data

TL;DR

This pilot study demonstrates the feasibility of a multimodal sensing framework combining thermal, acoustic, optical-flow, and environmental data to monitor early-life development in laying hens, revealing age-related physiological and behavioral patterns.

Contribution

It introduces an integrated multimodal sensing approach for tracking physiological and behavioral development in hens, providing baseline data for welfare monitoring.

Findings

Thermal imaging showed age-related increases and stabilization of peripheral temperatures.

Acoustic features exhibited systematic changes consistent with vocal maturation.

Optical-flow analysis indicated early reactivity to caretaker presence that declined with age.

Abstract

Early-life development strongly influences long-term welfare in laying hens, yet monitoring remains limited by subjective assessment and single-modality tools. This pilot study evaluated the feasibility of a multimodal sensing framework integrating thermal imaging, acoustic recording, optical-flow-based video analysis, and environmental monitoring to characterize physiological and behavioural development from hatch to 20 weeks. One hundred fifty Lohmann LSL-Lite chicks were housed across five controlled rooms; thermal and environmental data were collected system-wide, while detailed audio and video analyses focused on one representative room. Weekly aggregated features included head and foot surface temperatures, acoustic spectral descriptors, optical-flow movement responses to caretaker entry, and ambient conditions. Thermal imaging showed age-related increases and stabilization of peripheral temperatures, with foot temperature exhibiting a strong developmental effect (eta squared = 0.51). Acoustic features changed systematically across weeks (p < 0.001), consistent with vocal maturation. Optical-flow analysis revealed pronounced early reactivity to caretaker presence that declined with age (weeks 5 to 10 versus 11 to 20: t = 28.12, p = 0.00126). Z-score-normalized multimodal trajectories and correlation analysis (false discovery rate q < 0.05) showed strong within-modality consistency (r = 0.85 to 0.96) and selective associations between humidity and acoustic features (r = 0.65 to 0.70), while thermal, acoustic, and behavioural domains remained largely independent. This pilot establishes baseline multimodal developmental patterns and supports parallel sensing for welfare-relevant monitoring in precision poultry farming.