Computer vision enables the development of new approaches to monitor the behavior, health, and welfare of animals. Instance segmentation is a high-precision method in computer vision for detecting individual animals of interest. This method can be used for in-depth analysis of animals, such as examining their subtle interactive behaviors, from videos and images. However, existing deep-learning-based instance segmentation methods have been mostly developed based on public datasets, which largely omit heavy occlusion problems; therefore, these methods have limitations in real-world applications involving object occlusions, such as farrowing pen systems used on pig farms in which the farrowing crates often impede the sow and piglets. In this paper, we propose a novel occlusion-resistant Center Clustering Network for instance segmentation, dubbed as CClusnet-Inseg. Specifically, CClusnet-Inseg uses each pixel to predict object centers and trace these centers to form masks based on clustering results, which consists of a network for segmentation and center offset vector map, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, Centers-to-Mask (C2M) and Remain-Centers-to-Mask (RC2M) algorithms, and a pseudo-occlusion generator (POG). In all, 4,600 images were extracted from six videos collected from six farrowing pens to train and validate our method. CClusnet-Inseg achieves a mean average precision (mAP) of 83.6; it outperformed YOLACT++ and Mask R-CNN, which had mAP values of 81.2 and 74.7, respectively. We conduct comprehensive ablation studies to demonstrate the advantages and effectiveness of core modules of our method. In addition, we apply CClusnet-Inseg to multi-object tracking for animal monitoring, and the predicted object center that is a conjunct output could serve as an occlusion-resistant representation of the location of an object.

翻译：计算机视觉技术为监测动物行为、健康及福利提供了新方法。实例分割是计算机视觉中用于检测目标个体的高精度方法，可通过视频和图像深入分析动物行为，例如研究其细微的互动行为。然而，现有基于深度学习的实例分割方法大多基于公开数据集开发，严重忽略了遮挡问题，因此在涉及物体遮挡的实际应用中存在局限性，例如养猪场使用的产栏系统中，分娩栏常会阻碍母猪和仔猪。本文提出一种新型抗遮挡中心聚类网络（CClusnet-Inseg）用于实例分割。具体而言，CClusnet-Inseg利用每个像素预测物体中心，并基于聚类结果追踪这些中心以生成掩膜，其核心组件包括：用于分割和中心偏移向量图的网络、基于密度的噪声应用空间聚类（DBSCAN）算法、中心转掩膜（C2M）与剩余中心转掩膜（RC2M）算法，以及伪遮挡生成器（POG）。我们从六个产栏采集的六段视频中提取4600张图像进行训练与验证。CClusnet-Inseg的均值平均精度（mAP）达到83.6，优于YOLACT++（81.2）和Mask R-CNN（74.7）。通过全面的消融实验，我们证明了该方法核心模块的优势与有效性。此外，我们将CClusnet-Inseg应用于动物监测中的多目标跟踪，其预测的物体中心作为联合输出，可作为物体位置的一种抗遮挡表示。