arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.03426cs.CV
收藏

基于基础模型的群养猪自动分割与跟踪

Automated Segmentation and Tracking of Group Housed Pigs Using Foundation Models

Iowa State University(爱荷华州立大学)

Ye Bi, Bimala Acharya, David Rosero, Juan Steibel

AI总结:

本文提出基于基础模型的群养猪自动化监测流程,利用预训练的视觉-语言基础模型作为通用视觉骨干,并通过模块化后处理实现农场特定适应,通过Grounded-SAM2进行视频分割并结合长时间跟踪管道实现稳定的身份一致性。

摘要:

基础模型(FM)通过减少对任务特定监督学习的依赖,并利用大规模学习的通用视觉表示,正在重塑计算机视觉。在精准畜牧业中,大多数流程仍由需要大量标注数据、重复重新训练和农场特定调整的监督学习模型主导。本研究提出一个以基础模型为中心的工作流程,用于群养猪的自动化监测,其中预训练的视觉-语言基础模型用作通用视觉骨干,农场特定的适应通过模块化后处理实现。Grounding-DINO首次应用于1,418张标注图像以建立基线检测性能。尽管在白天条件下检测准确率较高,但在夜间视觉和重叠情况下性能下降,促使集成时间跟踪逻辑。在这些检测基础上,使用Grounded-SAM2对550个一分钟视频片段进行短期视频分割;后处理后,4,927个活跃轨迹中有超过80%完全正确,大部分错误源于不准确的掩码或重复标签。为了支持长时间内身份一致性,我们进一步开发了一个长时间跟踪管道,整合初始化、跟踪、匹配、掩码细化、重新识别和事后质量控制。该系统在连续132分钟的视频上进行了评估,并在整个过程中保持了稳定的标识。在132个均匀采样的真实帧上,系统实现了平均区域相似度(J)为0.83,轮廓精度(F)为0.92,J&F为0.87,MOTA为0.99,MOTP为90.7%,无身份切换。总体而言,本文展示了如何将基础模型的先验知识与轻量级、任务特定的逻辑结合,以实现规模化、标签高效和长时间监控在养猪生产中的应用。

英文摘要:

Foundation models (FM) are reshaping computer vision by reducing reliance on task-specific supervised learning and leveraging general visual representations learned at scale. In precision livestock farming, most pipelines remain dominated by supervised learning models that require extensive labeled data, repeated retraining, and farm-specific tuning. This study presents an FM-centered workflow for automated monitoring of group-housed nursery pigs, in which pretrained vision-language FM serve as general visual backbones and farm-specific adaptation is achieved through modular post-processing. Grounding-DINO was first applied to 1,418 annotated images to establish a baseline detection performance. While detection accuracy was high under daytime conditions, performance degraded under night-vision and heavy occlusion, motivating the integration of temporal tracking logic. Building on these detections, short-term video segmentation with Grounded-SAM2 was evaluated on 550 one-minute video clips; after post-processing, over 80% of 4,927 active tracks were fully correct, with most remaining errors arising from inaccurate masks or duplicated labels. To support identity consistency over an extended time, we further developed a long-term tracking pipeline integrating initialization, tracking, matching, mask refinement, re-identification, and post-hoc quality control. This system was evaluated on a continuous 132-minute video and maintained stable identities throughout. On 132 uniformly sampled ground-truth frames, the system achieved a mean region similarity (J) of 0.83, contour accuracy (F) of 0.92, J&F of 0.87, MOTA of 0.99, and MOTP of 90.7%, with no identity switches. Overall, this work demonstrates how FM prior knowledge can be combined with lightweight, task-specific logic to enable scalable, label-efficient, and long-duration monitoring in pig production.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑