CattleEyeView: A Multi-task Top-down View Cattle Dataset for Smarter Precision Livestock Farming

TL;DR

CattleEyeView introduces a comprehensive top-down view cattle video dataset designed to improve automated livestock monitoring through multi-task learning, enabling better counting, detection, pose estimation, and tracking of cattle.

Contribution

This paper presents the first multi-task, top-down view cattle dataset, addressing limitations of existing datasets and facilitating the development of smarter precision livestock farming systems.

Findings

Benchmark results demonstrate the dataset's utility across multiple tasks.

The dataset enables improved model performance for cattle counting and tracking.

Provides a valuable resource for future research in automated livestock monitoring.

Abstract

Cattle farming is one of the important and profitable agricultural industries. Employing intelligent automated precision livestock farming systems that can count animals, track the animals and their poses will raise productivity and significantly reduce the heavy burden on its already limited labor pool. To achieve such intelligent systems, a large cattle video dataset is essential in developing and training such models. However, many current animal datasets are tailored to few tasks or other types of animals, which result in poorer model performance when applied to cattle. Moreover, they do not provide top-down views of cattle. To address such limitations, we introduce CattleEyeView dataset, the first top-down view multi-task cattle video dataset for a variety of inter-related tasks (i.e., counting, detection, pose estimation, tracking, instance segmentation) that are useful to count the number of cows and assess their growth and well-being. The dataset contains 753 distinct top-down cow instances in 30,703 frames (14 video sequences). We perform benchmark experiments to evaluate the model's performance for each task. The dataset and codes can be found at https://github.com/AnimalEyeQ/CattleEyeView.