Rights statement: ©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Accepted author manuscript, 11.1 MB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Structured Context Enhancement Network for Mouse Pose Estimation
AU - Zhou, F.
AU - Jiang, Z.
AU - Liu, Z.
AU - Chen, F.
AU - Chen, L.
AU - Tong, L.
AU - Yang, Z.
AU - Wang, H.
AU - Fei, M.
AU - Li, L.
AU - Zhou, H.
N1 - ©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
PY - 2022/5/31
Y1 - 2022/5/31
N2 - Automated analysis of mouse behaviours is crucial for many applications in neuroscience. However, quantifying mouse behaviours from videos or images remains a challenging problem, where pose estimation plays an important role in describing mouse behaviours. Although deep learning based methods have made promising advances in human pose estimation, they cannot be directly applied to pose estimation of mice due to different physiological natures. Particularly, since mouse body is highly deformable, it is a challenge to accurately locate different keypoints on the mouse body. In this paper, we propose a novel Hourglass network based model, namely Graphical Model based Structured Context Enhancement Network (GMSCENet) where two effective modules, i.e., Structured Context Mixer (SCM) and Cascaded Multi-level Supervision (CMLS) are subsequently implemented. SCM can adaptively learn and enhance the proposed structured context information of each mouse part by a novel graphical model that takes into account the motion difference between body parts. Then, the CMLS module is designed to jointly train the proposed SCM and the Hourglass network by generating multi-level information, increasing the robustness of the whole network. Using the multi-level prediction information from SCM and CMLS, we develop an inference method to ensure the accuracy of the localisation results. Finally, we evaluate our proposed approach against several baselines on our Parkinson’s Disease Mouse Behaviour (PDMB) and the standard DeepLabCut Mouse Pose datasets. The experimental results show that our method achieves better or competitive performance against the other state-of-the-art approaches.
AB - Automated analysis of mouse behaviours is crucial for many applications in neuroscience. However, quantifying mouse behaviours from videos or images remains a challenging problem, where pose estimation plays an important role in describing mouse behaviours. Although deep learning based methods have made promising advances in human pose estimation, they cannot be directly applied to pose estimation of mice due to different physiological natures. Particularly, since mouse body is highly deformable, it is a challenge to accurately locate different keypoints on the mouse body. In this paper, we propose a novel Hourglass network based model, namely Graphical Model based Structured Context Enhancement Network (GMSCENet) where two effective modules, i.e., Structured Context Mixer (SCM) and Cascaded Multi-level Supervision (CMLS) are subsequently implemented. SCM can adaptively learn and enhance the proposed structured context information of each mouse part by a novel graphical model that takes into account the motion difference between body parts. Then, the CMLS module is designed to jointly train the proposed SCM and the Hourglass network by generating multi-level information, increasing the robustness of the whole network. Using the multi-level prediction information from SCM and CMLS, we develop an inference method to ensure the accuracy of the localisation results. Finally, we evaluate our proposed approach against several baselines on our Parkinson’s Disease Mouse Behaviour (PDMB) and the standard DeepLabCut Mouse Pose datasets. The experimental results show that our method achieves better or competitive performance against the other state-of-the-art approaches.
KW - Context modeling
KW - Diseases
KW - graphical model
KW - Graphical models
KW - Mice
KW - Mixers
KW - Mouse Behaviour dataset
KW - multi-level information
KW - Parkinson’s Disease
KW - Pose estimation
KW - Standards
KW - Graphic methods
KW - Mammals
KW - Automated analysis
KW - Competitive performance
KW - Context information
KW - Human pose estimations
KW - Learning-based methods
KW - Network-based modeling
KW - Prediction informations
KW - State-of-the-art approach
KW - Deep learning
U2 - 10.1109/TCSVT.2021.3098497
DO - 10.1109/TCSVT.2021.3098497
M3 - Journal article
VL - 32
SP - 2787
EP - 2801
JO - IEEE Transactions on Circuits and Systems for Video Technology
JF - IEEE Transactions on Circuits and Systems for Video Technology
SN - 1051-8215
IS - 5
ER -