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

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

cs.CVMar 17, 2026

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

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

Organizations: Beijing Jiaotong University · NERCITA · Tsinghua University · Griffith University

Abstract

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.

Figures & tables

Figure 1: Left : keypoint annotation scheme for cattle. Right : real-world dense environments for cattle mounting pose estimation by FSMC-Pose, based on self-collected MOUNT-Cattle dataset.

Figure 2: Architecture of FSMC-Pose framework, including the proposed lightweight backbone CattleMountNet (SFEBlock and RABlock) (Figure 3 ) and self-calibration SC2Head (Figure 4 ). Following the top-down design of RTMPose [ 10 ] , and employing MobileNet [ 24 ] .

Split	Invisible	Partial	Visible	Total
Train	7,493 (11.51%)	4,646 (7.14%)	52,965 (81.35%)	65,104
Val	929 (11.14%)	564 (6.77%)	6,843 (82.09%)	8,336
Test	1,066 (12.81%)	572 (6.88%)	6,682 (80.31%)	8,320
Total	9,488 (11.60%)	5,782 (7.07%)	66,490 (81.32%)	81,760

Table 1: Statistics of keypoint visibility categories across dataset splits. Values are counts with proportions in parentheses.

Figure 3: Architectures of the proposed CattleMountNet components: SFEBlock and RABlock.

Figure 4: Architecture of the proposed SC2Head module for spatial–channel co-calibrated keypoint prediction. The improved visualization is shown in Figure 6 .

Methods	Backbone	Head	AP/%	AP 50 /%	AP 75 /%	AR/%	AR 50 /%	AR 75 /%	FLOPs/G	Params/M
DEKR [ 7 ]	HRNet	DEKRHead	87.2	95.8	90.3	89.0	96.7	91.9	44.416	29.548
CID [ 26 ]	HRNet	CIDHead	88.0	96.4	90.8	89.0	97.1	91.7	44.160	29.363
CoupledEmbedding [ 28 ]	HRNet	AEHead	72.2	90.5	75.4	78.0	95.0	77.2	41.100	28.641
CoupledEmbedding [ 28 ]	HRNet	HAEHead	73.9	90.1	74.0	80.4	96.6	82.5	40.500	28.541
SimCC [ 12 ]	ResNet50	SimCCHead	87.4	96.0	91.0	89.9	96.7	92.9	5.493	36.753
SimCC [ 12 ]	ResNet101	SimCCHead	87.4	97.0	91.6	89.8	97.5	91.7	9.140	55.745

Table 2: Quantitative results across different pose estimation baselines. HigherAssociativeEmbeddingHead is abbreviated as HAEHead. AssociativeEmbeddingHead is abbreviated as AEHead.

Figure 5: Qualitative comparison of mounting pose estimation results on challenging real-world scenes. FSMC-Pose produces more accurate pose than CID [ 26 ] , SimCC [ 12 ] , and RTMPose [ 10 ] , especially under occlusion, cluttered backgrounds, and dense herd scenarios.

Figure 6: Qualitative comparison of predicted keypoint heatmaps under complex herd scenes. FSMC-Pose produces more concentrated and well-localized responses, especially around limbs and joints, compared with other top-down methods [ 26 , 12 , 10 ] .

CattleMountNet		Head	Metrics (%)				Params/M
SFEBlock	RABlock	SC2Head	AP	AP 75	AR	AR 75	Params/M
Baseline			88.4	90.6	89.0	92.7	13.55
Baseline w/ MobileNet			87.8	89.5	89.0	91.3	1.609
✓			88.2	91.7	89.6	92.3	1.903
	✓		88.0	90.8	89.0	91.7	2.393
		✓	87.5	90.7	89.3	91.9	1.620

Table 3: Ablation study of the proposed modules. We ablate SFEBlock, RABlock, and SC2Head individually and in combination. The baseline is RTMPose [ 10 ] with CSPNext backbone. The best results are highlighted in bold .

Attention Mechanisms	AP/%	AP 75 /%	AR/%	AR 75 /%
CSA	88.5	91.4	89.4	92.1
ECA	88.1	90.3	89.3	91.0
SAM	88.4	91.6	89.1	91.3
EMA	88.1	89.0	89.2	90.5
CBAM	88.4	90.8	89.4	91.2
SCAM	88.2	90.4	89.6	91.7

Table 4: Comparison of different attention mechanisms. Channel-only: CSA and ECA. Spatial-only: SAM and EMA. Joint spatial–channel: CBAM, SCAM and GCSA. Best performance is highlighted in bold .

Methods	FLOPs/G	Params/M	FPS
DEKR	8.328	29.548	37.57
CID	8.093	29.363	184.09
CoupledEmbedding	7.590	28.541	89.90
RTMO	31.656	22.475	78.23
Ours (FSMC-Pose)	0.354	2.698	216.58

Table 5: Comparison of inference speed. FLOPs/G, Params/M, and FPS denote computation, model size, and runtime speed, respectively. Best results are highlighted in bold .

Object Pose Estimation

Object pose estimation recovers an object's 3D position and orientation from images, depth, point clouds, or contact sensing.

See all 187 papers

Real-Time Localisation of Dorsal Anatomical Regions on Dairy Cows in Commercial Rotary Parlours from RGB-D
Oct 23, 2026Vineet Prasad, Shiron Melvin, Sheikh Azid +1Anatomical Landmark Detection Precision Livestock Farming
School of Engineering and Energy, Murdoch University, Perth, Australia
CowCare: A Unified Visual Framework for Viewpoint-Robust Cattle Tracking and Spatiotemporal Heat-Stress Analysis
Oct 10, 2026Xin Liu, Weiran Li, Minghao Zhu +2Precision Livestock Farming Agricultural Image Analysis
College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China · National Innovation Center for Digital Fishery, Ministry of Agriculture and Rural Affairs, Beijing, 100083, China · Key Laboratory of Smart Farming Technologies for Aquatic Animal and Livestock, Ministry of Agriculture and Rural Affairs, Beijing, 100083, China +1
Promptable Animal Pose Tracking Across Species
Aug 5, 2026Le Li, Daniela Ivanova, Nicolas PugeaultKeypoint Detection
School of Computing Science University of Glasgow

Oct 23, 2026J/K move · Enter open · S save

Real-Time Localisation of Dorsal Anatomical Regions on Dairy Cows in Commercial Rotary Parlours from RGB-D

Vineet Prasad, Shiron Melvin, Sheikh Azid, Hai Wang

School of Engineering and Energy, Murdoch University, Perth, Australia

Anatomical Landmark Detection Precision Livestock Farming Image Segmentation

Open paper AskPDF arXiv

Automated monitoring of dairy cows increasingly measures one part of the body, such as the rump for temperature or the back for posture, yet the region itself is usually placed by hand. Existing systems either score the cow as a whole or detect sparse keypoints, often in controlled walkways, and neither yields the named region masks that such measurements need on a crowded commercial rotary platform. We present a perception front end that finds the target cow, ten bony landmarks and four named dorsal regions (withers, back, rump and tail-head) in a single forward pass over a whole RGB-D frame from a commercial rotary parlour. Two encoders, one for colour and one for depth, are fused late and share one decoder with three heads. On an anatomical region dataset that we built on public rotary-parlour RGB-D images (538 annotated frames, cow-disjoint test set), the network reaches PCK@10 0.905 for landmarks and region IoU 0.70 to 0.91, and runs end to end in 26.4 ms per frame on a T4 GPU, against an 11 fps camera. Dense region supervision is what makes the landmarks accurate: removing the region head costs 0.15 PCK@10. Agreement between the two heads flags unreliable frames without labels. On our own rig at the largest dairy farm in Western Australia, the model transfers with ten labelled frames (PCK@10 0.84), and its regions are carried through depth into a radiometric thermal camera, giving one repeatable temperature per region and cow.

Abstract

Object Pose Estimation

Explore similar work

Real-Time Localisation of Dorsal Anatomical Regions on Dairy Cows in Commercial Rotary Parlours from RGB-D

CowCare: A Unified Visual Framework for Viewpoint-Robust Cattle Tracking and Spatiotemporal Heat-Stress Analysis

Promptable Animal Pose Tracking Across Species