Behaviour can be used to infer animal welfare states. Poultry birds tend to move less under conditions of thermal stress; hence the hypothesis of this research is that this unrest behaviour can be used as an indicator of thermal comfort. The objective was to develop an Unrest Index for poultry bird's sensitive to changes in this behaviour under different air temperature conditions. The proposed Unrest Index was based on the Hausdorff distance measure and was tested on recorded videos of laying hens and broilers breeders, obtained in different experiments. The index was efficient in detecting the unrest of poultry birds in different thermal conditions and, in conditions above thermoneutrality, the birds moved significantly less. The distribution Unrest Index of data for each thermal condition tested was shown to be asymmetric. However, there seems to be a tendency to reverse this asymmetry when the conditions are thermal comfort and heat stress. It is suggested that the Unrest Index can be used to estimate the thermal comfort of poultry birds and that further studies on the asymmetry of the index data should be carried out in order to identify of the thermoneutrality zone of birds in a non-invasive way. The Unrest Index and the computer vision techniques adopted to assess poultry thermal comfort automatically were efficient in demonstrating differences in bird agitation in distinct thermal stress conditions. The low computational effort and the mathematical simplicity of the model allows the Unrest Index to incorporate bird surveillance systems and estimate thermal comfort automatically.

行为可以用来推断动物福利状态。家禽在热应激条件下往往活动较少。因此，这项研究的假设是，这种动荡行为可以用作热舒适度的指标。目的是为家禽在不同的空气温度条件下对这种行为的变化敏感而制定一个动荡指数。拟议的动荡指数基于Hausdorff距离测度，并通过在不同实验中获得的蛋鸡和肉鸡育种家的录制视频进行了测试。该指数可有效检测不同温度条件下的禽鸟动荡，并且在高于热中性的条件下，禽鸟的活动明显减少。对于每个测试的热条件，数据的不稳定性指数分布显示为不对称的。然而，当条件是热舒适性和热应力时，似乎有逆转这种不对称的趋势。建议可以使用“动荡指数”来估计家禽的热舒适性，并且应该对指数数据的不对称性进行进一步研究，以便以非侵入性的方式识别禽类的热中性区。自动评估家禽热舒适度的不安定指数和计算机视觉技术可以有效地证明在不同的热应激条件下禽类搅动的差异。该模型的低计算量和数学简单性使Unrest Index可以结合鸟类监视系统并自动估算热舒适度。