Instance segmentation of pigs in infrared images based on INPC model

文献类型： 外文期刊

第一作者： Wang, Ge

作者： Wang, Ge;Ma, Yong;Huang, Jun;Fan, Fan;Li, Hao;Li, Zipeng

作者机构：

关键词： Infrared image; Pig instance segmentation; INPC model; Deep learning

期刊名称：INFRARED PHYSICS & TECHNOLOGY （ 影响因子：3.1； 五年影响因子：3.0 ）

ISSN： 1350-4495

年卷期： 2024 年 141 卷

页码：

收录情况： SCI

摘要： Conventional segmentation methods based on visible images in intensive pig farming face various challenges. Examples include color 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 utilizes 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 largescale standardized infrared pig dataset. Experimental results demonstrate that INPC outperforms mainstream segmentation models in terms of average precision (AP), except for AP(0.5). Specifically, INPC achieves AP(0.5), AP(0.75), AP(0.5:0.95), AP(0.5:0.95s), and AP(0.5:0.95l) 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.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序