One-Shot Learning with Pseudo-Labeling for Cattle Video Segmentation in Smart Livestock Farming

Abstract

Computer vision-based technologies play a key role in precision livestock farming, and video-based analysis approaches have been advocated as useful tools for automatic animal monitoring, behavior analysis, and efficient welfare measurement management. Accurately and efficiently segmenting animals’ contours from their backgrounds is a prerequisite for vision-based technologies. Deep learning-based segmentation methods have shown good performance through training models on a large amount of pixel-labeled images. However, it is challenging and time-consuming to label animal images due to their irregular contours and changing postures. In order to reduce the reliance on the number of labeled images, one-shot learning with a pseudo-labeling approach is proposed using only one labeled image frame to segment animals in videos. The proposed approach is mainly comprised of an Xception-based Fully Convolutional Neural Network (Xception-FCN) module and a pseudo-labeling (PL) module. Xception-FCN utilizes depth-wise separable convolutions to learn different-level visual features and localize dense prediction based on the one single labeled frame. Then, PL leverages the segmentation results of the Xception-FCN model to fine-tune the model, leading to performance boosts in cattle video segmentation. Systematic experiments were conducted on a challenging feedlot cattle video dataset acquired by the authors, and the proposed approach achieved a mean intersection-over-union score of 88.7% and a contour accuracy of 80.8%, outperforming state-of-the-art methods (OSVOS and OSMN). Our proposed one-shot learning approach could serve as an enabling component for livestock farming-related segmentation and detection applications.

Precision Livestock Farming Research: A Global Scientometric Review

“…In order to clarify the connotation of PLF, it is necessary to further explore the concepts of SLF and DLF. In much of the literature, SLF is often attributed to PLF [ 31 , 32 ], but recent research proposes that SLF should be considered more of a successor to PLF [ 33 ]. PLF focuses on the digital processing of specific information to support stakeholder decision-making, while SLF is a knowledge-based concept that leverages information and communication technology (ICT) to manage cyber-physical livestock farms [ 33 , 34 ].…”

Using pseudo-labeling to improve performance of deep neural networks for animal identification

“…Pseudo-labeling allows for a simple and effective way to improve the predictive performance of trained machine learning models when labeling more data is costly and large amounts of unlabeled data are available. Pseudo-labeling can be easily implemented with various machine learning algorithms applied to different datasets (if unlabeled data is available) and domains, including applications in agriculture 12 , 13 , medicine 14 , person re-identification 15 , and remote sensing 16 for example. The simplicity and versatility of pseudo-labeling were our main motivations for evaluating the application of this technique for training deep neural networks for animal identification.…”