YogNet: A two-stream network for realtime multiperson yoga action recognition and posture correction
نویسندگان
چکیده
Yoga is a traditional Indian exercise. It specifies various body postures called asanas, practicing them beneficial for the physical, mental, and spiritual well-being. To support yoga practitioners, there need of an expert asanas recognition system that can automatically analyze practitioner’s could provide suitable posture correction instructions. This paper proposes YogNet, multi-person 20 using two-stream deep spatiotemporal neural network architecture. The first stream utilizes keypoint detection approach to detect pose, followed by formation bounding boxes across subject. model then applies time distributed convolutional networks (CNNs) extract frame-wise postural features, regularized long short-term memory (LSTM) give temporal predictions. second 3D-CNNs feature extraction from RGB videos. Finally, scores two streams are fused multiple fusion techniques. A asana database (YAR) containing 1206 videos collected single 2D web camera 367 min with help 16 participants contains four view variations i.e. front, back, left, right sides. proposed novel as this earliest learning-based perform in realtime. Simulation result reveals YogNet achieved 77.29%, 89.29%, 96.31% accuracies pose stream, via both streams, respectively. These results impressive sufficiently high recommendation towards general adaption system.
منابع مشابه
Two-Stream SR-CNNs for Action Recognition in Videos
Human action is a high-level concept in computer vision research and understanding it may benefit from different semantics, such as human pose, interacting objects, and scene context. In this paper, we explicitly exploit semantic cues with aid of existing human/object detectors for action recognition in videos, and thoroughly study their effect on the recognition performance for different types...
متن کاملTwo-Stream convolutional nets for action recognition in untrimmed video
We extend the two-stream convolutional net architecture developed by Simonyan for action recognition in untrimmed video clips. The main challenges of this project are first replicating the results of Simonyan et al, and then extending the pipeline to apply it to much longer video clips in which no actions of interest are taking place most of the time. We explore aspects of the performance of th...
متن کاملTwo-Stream Convolutional Networks for Action Recognition in Videos
We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we ...
متن کاملHidden Two-Stream Convolutional Networks for Action Recognition
Analyzing videos of human actions involves understanding the temporal relationships among video frames. CNNs are the current state-of-the-art methods for action recognition in videos. However, the CNN architectures currently being used have difficulty in capturing these relationships. State-of-the-art action recognition approaches rely on traditional local optical flow estimation methods to pre...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Knowledge Based Systems
سال: 2022
ISSN: ['1872-7409', '0950-7051']
DOI: https://doi.org/10.1016/j.knosys.2022.109097