This paper proposes MFA-Pose, an improved YOLO11s-Pose framework that enhances contextual representation and cross-scale feature reconstruction that provides a favorable balance between pose estimation accuracy and model complexity for industrial surveillance applications.
Abstract
Human pose estimation in factory surveillance is challenged by scale variation, limb occlusion, complex backgrounds, and spatial detail loss during upsampling. This paper proposes MFA-Pose, an improved YOLO11s-Pose framework that enhances contextual representation and cross-scale feature reconstruction. The Multi-Scale Context Fusion (MSCF) module preserves directional positional information and models multi-range cross-channel dependencies using parallel one-dimensional convolutions with kernel sizes of 3, 5, and 7. The complete C2MSCF module contains approximately 0.790 M learnable parameters, compared with approximately 0.991 M parameters in the original C2PSA module. The Multi-Receptive-Field Adaptive Gated Upsampling (MRAG) module predicts sampling offsets through standard and dilated convolution branches, suppresses unreliable offsets using gating mechanisms, and combines dynamic resampling with a stable bilinear interpolation reference. The two MRAG modules used in MFA-Pose contain approximately 0.457 M and 0.130 M learnable parameters, respectively, corresponding to approximately 0.587 M parameters in total. On COCO 2017, MFA-Pose achieves 89.0% AP50pose and 61.7% AP50:95pose, outperforming YOLO11s-Pose by 2.7 and 1.6 percentage points, respectively, with only 0.40 M additional parameters. Quantitative evaluation on the annotated industrial surveillance test set further shows that MFA-Pose achieves 87.2% Precision, 77.0% Recall, 81.8% F1-score, 88.7% AP50pose, and 61.1% AP50:95pose, outperforming the YOLO11s-Pose baseline across all evaluated accuracy metrics. Qualitative comparisons further show more coherent pose predictions under self-occlusion, non-standard working postures, and cluttered equipment backgrounds. Overall, MFA-Pose provides a favorable balance between pose estimation accuracy and model complexity for industrial surveillance applications.
An HGDS-YOLOv8-Pose algorithm embedded with HSAN, GL-CRM, DySample and SCAM modules for robust outdoor human pose estimation, outperforming competing methods including KAPAO-s and YOLOv8n-Pose.
Xin Geng, Xiao-Wei Zhang, Dong-Hui Wu et al.· Signal, Image and Video Proc...· 0 citations
This paper proposes a lightweight high-resolution pose estimation network, UG-HRNet, which significantly reduces model complexity while maintaining competitive performance, serving as a practical alternative to existing popular lightweight networks.
Yong-Feng Qi, Jun-Teng Zhang· International Journal of Mac...· 0 citations
CL-HPE is presented, a lightweight framework for competitive and efficient pose estimation that provides a practical solution in resource-constrained environments and suggests a favorable accuracy–efficiency trade-off among lightweight pose estimators.
Yue-Han Liu, Shu-Yi She, Ya-Ting Li et al.· The Visual Computer· 0 citations
This work presents FunFlow6D, a novel flow matching-based formulation that leverages features from geometric and appearance foundation models for pose estimation, eliminating the need for task-specific encoders supervised on object-scene overlap and reducing supervision requirements and memory overhead.
Amir Hamza, Davide Boscaini, Fabio Poiesi· 0 citations
The method demonstrates the feasibility of a lightweight dual-attention synergistic mechanism that significantly improves vertical boundary localization at the cost of a slight decrease in general detection accuracy, providing a new approach for fine-grained measurement in structured scenarios with a fixed monocular ca...
Cheng-Fei Shi, Hai-Qing Liu, Zhi-Yong Zou et al.· International Conference on...· 0 citations
Human pose estimation in real-world indoor environments remains challenging due to privacy concerns, occlusions, varying numbers of people, and noisy sensor data. In this work, we investigate pose estimation from depth images captured over an extended period in a nursing home setting. We explore multiple input represen...
Rinu Elizabeth Paul, Tanja Schultz· Italian National Conference...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.