Conventional segmentation methods based on visible images in intensive pig farming face various challenges. Examples include colour differences between pig breeds, background interference and lighting conditions. To overcome these issues, we designed the infrared pig cascade segmentation (INPC) model for the first time on infrared images. The model uses a cascade structure. Each stage utilises higher resolution feature maps to better preserve fine details. It also solves the problem of poor segmentation of small objects due to low resolution of infrared images. At the same time, the model’s cross-guidance strategy enhances the interaction between bounding box regression and mask prediction. This reduces errors caused by interference like feces and urine. Additionally, a progressive mask branch refines mask prediction, improving segmentation in scenarios like imaging haze or pig adhesion. To facilitate model training and evaluation, we built the first large-scale standardised infrared pig dataset. Experimental results demonstrate that INPC outperforms mainstream segmentation models in terms of average precision (AP), except for AP0.5. Specifically, INPC achieves AP0.5, AP0.75, AP0.5:0.95, AP0.5:0.95s, and AP0.5:0.95l of 97.9%, 97.1%, 88.2%, 71.5%, and 90.1% respectively. Inference for a single image on a GPU takes only 0.197 s. Some datasets are available at https://github.com/HUBUwg96/INPC.