MPOSE2021: a Dataset for Short-Time Pose-Based Human Action Recognition

<p>This repository contains the MPOSE2021 Dataset for short-time pose-based Human Action Recognition (HAR). MPOSE2021 is specifically designed to perform short-time Human Action Recognition.</p> <p>MPOSE2021 is developed as an evolution of the MPOSE Dataset [1-3]. It is made by human pose data detected by&nbsp;<a href="https://github.com/CMU-Perceptual-Computing-Lab/openpose">OpenPose</a>&nbsp;[4] and&nbsp;<a href="https://github.com/tensorflow/tfjs-models/tree/master/posenet">Posenet</a>&nbsp;[11] on popular datasets for HAR, i.e. Weizmann [5], i3DPost [6], IXMAS [7], KTH [8], UTKinetic-Action3D (RGB only) [9] and UTD-MHAD (RGB only) [10], alongside original video datasets, i.e. ISLD and ISLD-Additional-Sequences [1]. Since these datasets have heterogenous action labels, each dataset labels are remapped to a common and homogeneous list of actions. Generated sequences have a number of frames between 20 and 30. Sequences are obtained by cutting the so-called Precursor videos (video&nbsp;from the above-mentioned datasets), with non-overlapping sliding windows. Frames where OpenPose/PoseNet cannot detect any subject are automatically discarded. Resulting samples contain one subject at the time, performing a fraction of a single action. Overall, MPOSE2021 contains 15429 samples, divided into 20 actions, performed by 100 subjects.</p> <p>More information about the dataset&nbsp;can be found in the&nbsp;<a href="https://github.com/PIC4SeRCentre/MPOSE2021_Dataset">MPOSE2021 repository</a>, also providing a user-friendly Python package to import and use the dataset by just running the command</p> <pre><code>pip install mpose</code></pre> <p>&nbsp;</p> <p><strong>Data Structure</strong></p> <p>The repository contains 3 datasets for each pose extractor&nbsp;(namely 1, 2 and&nbsp;3) which consist of the same data divided in different train/test splits. Each dataset contains X and y numpy arrays for both training and testing. X&nbsp;has the following shape:</p> <pre>(B, T, K, C)</pre> <p>where</p> <ul> <li>B is the batch number;</li> <li>T (= 30) is the duration of the sequences in frames&nbsp;(zero-padded in the case of shorter sequences);</li> <li>K (= 17 for PoseNet&nbsp;and&nbsp;25 for OpenPose) is the number of pose keypoints;</li> <li>C (= 3) is the number of channels, comprehending 2D keypoint coordinates (x,y) in the original video reference frame and the&nbsp;keypoint confidence (p &lt;= 1)</li> </ul> <p>The .txt files specifying the metadata associated with the split samples are also included.</p> <p><strong>References</strong></p> <p>MPOSE2021 is part of a&nbsp;<a href="https://authors.elsevier.com/a/1eH6s77nKcvmg">paper published by the Pattern Recognition Journal</a>&nbsp;(Elsevier), and is intended for scientific research purposes. If you want to use MPOSE2021 for your research work, please also cite [1-11].</p> <pre><code>@article{mazzia2021action, title={Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition}, author={Mazzia, Vittorio and Angarano, Simone and Salvetti, Francesco and Angelini, Federico and Chiaberge, Marcello}, journal={Pattern Recognition}, pages={108487}, year={2021}, publisher={Elsevier} } </code></pre> <p>[1] Angelini, F., Fu, Z., Long, Y., Shao, L., &amp; Naqvi, S. M. (2019). 2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling. IEEE Transactions on Multimedia, 22(6), 1433-1446.</p> <p>[2] Angelini, F., Yan, J., &amp; Naqvi, S. M. (2019, May). Privacy-preserving Online Human Behaviour Anomaly Detection Based on Body Movements and Objects Positions. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 8444-8448). IEEE.</p> <p>[3] Angelini, F., &amp; Naqvi, S. M. (2019, July). Joint RGB-Pose Based Human Action Recognition for Anomaly Detection Applications. In 2019 22th International Conference on Information Fusion (FUSION) (pp. 1-7). IEEE.</p> <p>[4] Cao, Z., Hidalgo, G., Simon, T., Wei, S. E., &amp; Sheikh, Y. (2019). OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields. IEEE transactions on pattern analysis and machine intelligence, 43(1), 172-186.</p> <p>[5] Gorelick, L., Blank, M., Shechtman, E., Irani, M., &amp; Basri, R. (2007). Actions as Space-Time Shapes. IEEE transactions on pattern analysis and machine intelligence, 29(12), 2247-2253.</p> <p>[6] Starck, J., &amp; Hilton, A. (2007). Surface Capture for Performance-Based Animation. IEEE computer graphics and applications, 27(3), 21-31.</p> <p>[7] Weinland, D., &Ouml;zuysal, M., &amp; Fua, P. (2010, September). Making Action Recognition Robust to Occlusions and Viewpoint Changes. In European Conference on Computer Vision (pp. 635-648). Springer, Berlin, Heidelberg.</p> <p>[8] Schuldt, C., Laptev, I., &amp; Caputo, B. (2004, August). Recognizing Human Actions: a Local SVM Approach. In Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. (Vol. 3, pp. 32-36). IEEE.</p> <p>[9] Xia, L., Chen, C. C., &amp; Aggarwal, J. K. (2012, June). View Invariant Human Action Recognition using Histograms of 3D Joints. In 2012 IEEE computer society conference on computer vision and pattern recognition workshops (pp. 20-27). IEEE.</p> <p>[10] Chen, C., Jafari, R., &amp; Kehtarnavaz, N. (2015, September). UTD-MHAD: A Multimodal Dataset for Human Action Recognition utilizing a Depth Camera and a Wearable Inertial Sensor. In 2015 IEEE International conference on image processing (ICIP) (pp. 168-172). IEEE.</p> <p>[11] Papandreou, G., Zhu, T., Chen, L. C., Gidaris, S., Tompson, J., &amp; Murphy, K. (2018). Personlab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 269-286).</p>