arXiv 2603.165962026-03-17cs.CVcs.AI

FSMC-Pose：基于多尺度自校准的频率与空间融合用于牛交配姿态估计

FSMC-Pose: Frequency and Spatial Fusion with Multiscale Self-calibration for Cattle Mounting Pose Estimation

Beijing Jiaotong University（北京交通大学）；NERCITA；Tsinghua University（清华大学）；Griffith University（格里菲斯大学）

Fangjing Li, Zhihai Wang, Xinxin Ding, Haiyang Liu, Ronghua Gao, Rong Wang, Yao Zhu, Ming Jin

备注：: 10 pages, 6 figures. Accept by CVPR2026 Findings

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出FSMC-Pose框架，通过轻量级频率-空间融合骨干网络、CattleMountNet和多尺度自校准头SC2Head，有效解决牛交配姿态估计中的复杂背景和动物遮挡问题，实现高精度低开销的实时估计。

摘要：

交配姿态是奶牛发情的重要视觉指标，但实际环境中由于杂乱背景和频繁的动物遮挡，实现可靠的交配姿态估计仍具挑战性。本文提出FSMC-Pose，一种自上而下的框架，整合了轻量级频率-空间融合骨干网络CattleMountNet和多尺度自校准头SC2Head。具体而言，我们为CattleMountNet设计了两个算法组件：空间频率增强块（SFEBlock）和感受野聚合块（RABlock）。SFEBlock用于分离牛只与杂乱背景，RABlock则捕获多尺度上下文信息。空间-通道自校准头（SC2Head）处理空间和通道依赖性，并引入自校准分支以缓解动物重叠下的结构偏移。我们构建了一个包含1176个交配实例的交配数据集MOUNT-Cattle，遵循COCO格式并支持在各种姿态估计模型中直接使用。通过结合MOUNT-Cattle与公开的NWAFU-Cattle数据集，FSMC-Pose在准确率上优于强基线模型，同时具有显著更低的计算和参数成本，并能在商用GPU上实现实时推理。大量实验和定性分析表明，FSMC-Pose能有效捕捉和估计复杂和杂乱环境中的牛交配姿态。数据集和代码可在https://github.com/elianafang/FSMC-Pose获取。

英文摘要：

Mounting posture is an important visual indicator of estrus in dairy cattle. However, achieving reliable mounting pose estimation in real-world environments remains challenging due to cluttered backgrounds and frequent inter-animal occlusion. We present FSMC-Pose, a top-down framework that integrates a lightweight frequency-spatial fusion backbone, CattleMountNet, and a multiscale self-calibration head, SC2Head. Specifically, we design two algorithmic components for CattleMountNet: the Spatial Frequency Enhancement Block (SFEBlock) and the Receptive Aggregation Block (RABlock). SFEBlock separates cattle from cluttered backgrounds, while RABlock captures multiscale contextual information. The Spatial-Channel Self-Calibration Head (SC2Head) attends to spatial and channel dependencies and introduces a self-calibration branch to mitigate structural misalignment under inter-animal overlap. We construct a mounting dataset, MOUNT-Cattle, covering 1176 mounting instances, which follows the COCO format and supports drop-in training across pose estimation models. Using a comprehensive dataset that combines MOUNT-Cattle with the public NWAFU-Cattle dataset, FSMC-Pose achieves higher accuracy than strong baselines, with markedly lower computational and parameter costs, while maintaining real-time inference on commodity GPUs. Extensive experiments and qualitative analyses show that FSMC-Pose effectively captures and estimates cattle mounting pose in complex and cluttered environments. Dataset and code are available at https://github.com/elianafang/FSMC-Pose.

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。