Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
68,396
result(s) for
"Human motion"
Sort by:
Superhydrophobic Photocatalytic Self‐Cleaning Nanocellulose‐Based Strain Sensor for Full‐Range Human Motion Monitoring
Nanocellulose‐based strain sensor (NBSS) have been a subject of growing interest for wearable electronics. However, these electronic devices are susceptible to damage when they come into contact with water and organic contaminants. Recently, researchers have developed a superhydrophobic NBSS. Unfortunately, it does not treat organic pollutants in water when used in an underwater environment. In this paper, a new solution: a superhydrophobic photocatalytic self‐cleaning NBSS created through scrape coating and dip coating methods is proposed. This new method shows outstanding self‐cleaning capabilities against water and organic contaminants due to the synergistic effects of the superhydrophobicity and photocatalysis of MnO2 nanoparticles. Furthermore, the superhydrophobic photocatalytic self‐cleaning NBSS has an exceptional response time of 0.66 s, a fast recovery time of 0.81 s, a sensitivity ≈66.53 at a strain of 0.5%. It is expect that the superhydrophobic photocatalytic self‐cleaning NBSS can monitor human movements, including finger twists, wrist movements, elbow bends, and knee movements. Not only is the fabrication method cost‐effective and scalable, but the new NBSS holds great promise in a wide range of fields, including human‐machine interactive systems, smart systems, and human‐body monitoring. Overall, the study provides significant guidance for future designs for wearable strain sensors. A superhydrophobic photocatalytic self‐cleaning nanocellulose‐based strain sensors (NBSS) is created through scrape coating and dip coating methods. Not only is this fabrication method cost‐effective and scalable, but the new NBSS holds great promise in a wide range of fields, including human‐machine interactive systems, smart systems. Overall, this research provides significant guidance for future designs for wearable strain sensors.
Journal Article
Multi-level Motion Attention for Human Motion Prediction
Human motion prediction aims to forecast future human poses given a historical motion. Whether based on recurrent or feed-forward neural networks, existing learning based methods fail to model the observation that human motion tends to repeat itself, even for complex sports actions and cooking activities. Here, we introduce an attention based feed-forward network that explicitly leverages this observation. In particular, instead of modeling frame-wise attention via pose similarity, we propose to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences. In this context, we study the use of different types of attention, computed at joint, body part, and full pose levels. Aggregating the relevant past motions and processing the result with a graph convolutional network allows us to effectively exploit motion patterns from the long-term history to predict the future poses. Our experiments on Human3.6M, AMASS and 3DPW validate the benefits of our approach for both periodical and non-periodical actions. Thanks to our attention model, it yields state-of-the-art results on all three datasets. Our code is available at https://github.com/wei-mao-2019/HisRepItself.
Journal Article
Modeling Human Motion with Quaternion-Based Neural Networks
Previous work on predicting or generating 3D human pose sequences regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuities when using Euler angles or exponential maps as parameterizations. The latter requires re-projection onto skeleton constraints to avoid bone stretching and invalid configurations. This work addresses both limitations. QuaterNet represents rotations with quaternions and our loss function performs forward kinematics on a skeleton to penalize absolute position errors instead of angle errors. We investigate both recurrent and convolutional architectures and evaluate on short-term prediction and long-term generation. For the latter, our approach is qualitatively judged as realistic as recent neural strategies from the graphics literature. Our experiments compare quaternions to Euler angles as well as exponential maps and show that only a very short context is required to make reliable future predictions. Finally, we show that the standard evaluation protocol for Human3.6M produces high variance results and we propose a simple solution.
Journal Article
Natural polymers based triboelectric nanogenerator for harvesting biomechanical energy and monitoring human motion
Triboelectric nanogenerator (TENG) has been proved as a promising energy harvester in recent years, but the challenges of exploring economically triboelectric materials still exist and have aroused interests of many researchers. In this paper, chitosansilk fibroin-airlaid paper composite film (CSA film) was fabricated and then the CSA film based-triboelectric nanogenerator (CSA-TENG) was constructed, which presents an opportunity for natural polymers to be applied in triboelectric materials. Due to the excellent electron donating ability of CSA film, the CSA-TENG can harvest environmental energy with a high efficiency. More importantly, the as-designed CSA film based dual-electrode triboelectric nanogenerator (CSA-D-TENG) is successfully assembled into hand clapper and trampoline to harvest mechanical energies generated by human bodies, it is also capable of monitoring human movement while harvesting biomechanical energies. This work provides a simple and environmental-friendly way to develop TENG for biomechanical energies harvesting and human motion monitoring.
Journal Article
Markerless motion capture provides accurate predictions of ground reaction forces across a range of movement tasks
Measuring or estimating the forces acting on the human body during movement is critical for determining the biomechanical aspects relating to injury, disease and healthy ageing. In this study we examined whether quantifying whole-body motion (segmental accelerations) using a commercial markerless motion capture system could accurately predict three-dimensional ground reaction force during a diverse range of human movements: walking, running, jumping and cutting. We synchronously recorded 3D ground reaction forces (force instrumented treadmill or in-ground plates) with high-resolution video from eight cameras that were spatially calibrated relative to a common coordinate system. We used a commercially available software to reconstruct whole body motion, along with a geometric skeletal model to calculate the acceleration of each segment and hence the whole-body centre of mass and ground reaction force across each movement task. The average root mean square difference (RMSD) across all three dimensions and all tasks was 0.75 N/kg, with the maximum average RMSD being 1.85 N/kg for running vertical force (7.89 % of maximum). There was very strong agreement between peak forces across tasks, with R2 values indicating that the markerless prediction algorithm was able to predict approximately 95–99 % of the variance in peak force across all axes and movements. The results were comparable to previous reports using whole-body marker-based approaches and hence this provides strong proof-of-principle evidence that markerless motion capture can be used to predict ground reaction forces and therefore potentially assess movement kinetics with limited requirements for participant preparation.
Journal Article