Yoga Pose Classification Using Transfer Learning

• URL: http://arxiv.org/abs/2411.00833v1
• Date: Tue, 29 Oct 2024 14:34:18 GMT
• Title: Yoga Pose Classification Using Transfer Learning
• Authors: M. M. Akash, Rahul Deb Mohalder, Md. Al Mamun Khan, Laboni Paul, Ferdous Bin Ali,
• Abstract summary: Yoga-82, a benchmark dataset for large-scale yoga pose recognition with 82 classes, has challenging positions that could make precise annotations impossible. We have used VGG-16, ResNet-50, ResNet-101, and DenseNet-121 and finetuned them in different ways to get better results. The experimental result shows the best performance of DenseNet-121 having the top-1 accuracy of 85% and top-5 accuracy of 96%.
• Score: 0.0
• License:
• Abstract: Yoga has recently become an essential aspect of human existence for maintaining a healthy body and mind. People find it tough to devote time to the gym for workouts as their lives get more hectic and they work from home. This kind of human pose estimation is one of the notable problems as it has to deal with locating body key points or joints. Yoga-82, a benchmark dataset for large-scale yoga pose recognition with 82 classes, has challenging positions that could make precise annotations impossible. We have used VGG-16, ResNet-50, ResNet-101, and DenseNet-121 and finetuned them in different ways to get better results. We also used Neural Architecture Search to add more layers on top of this pre-trained architecture. The experimental result shows the best performance of DenseNet-121 having the top-1 accuracy of 85% and top-5 accuracy of 96% outperforming the current state-of-the-art result.

Related papers

• 3DYoga90: A Hierarchical Video Dataset for Yoga Pose Understanding [0.0]
  3DYoga901 is organized within a three-level label hierarchy. Our dataset includes meticulously curated RGB yoga pose videos and 3D skeleton sequences.
  arXiv  Detail & Related papers  (2023-10-16T07:15:31Z)
• Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis [24.276782804825846]
  Human body-pose estimation is a complex problem in computer vision. Recent research interests have been widened specifically on the Sports, Yoga, and Dance postures. CNNs have attained significantly improved performance in solving various human body-pose estimation problems.
  arXiv  Detail & Related papers  (2023-08-01T07:00:13Z)
• Effective Whole-body Pose Estimation with Two-stages Distillation [52.92064408970796]
  Whole-body pose estimation localizes the human body, hand, face, and foot keypoints in an image. We present a two-stage pose textbfDistillation for textbfWhole-body textbfPose estimators, named textbfDWPose, to improve their effectiveness and efficiency.
  arXiv  Detail & Related papers  (2023-07-29T03:49:28Z)
• 3D Pose Based Feedback for Physical Exercises [87.35086507661227]
  We introduce a learning-based framework that identifies the mistakes made by a user. Our framework does not rely on hard-coded rules, instead, it learns them from data. Our approach yields 90.9% mistake identification accuracy and successfully corrects 94.2% of the mistakes.
  arXiv  Detail & Related papers  (2022-08-05T16:15:02Z)
• A View Independent Classification Framework for Yoga Postures [2.922683311119656]
  We employ transfer learning from Human Pose Estimation models for extracting 136 key-points spread all over the body to train a Random Forest classifier. Results are evaluated on an in-house collected extensive yoga video database of 51 subjects recorded from 4 different camera angles.
  arXiv  Detail & Related papers  (2022-06-27T18:40:34Z)
• Real-time Recognition of Yoga Poses using computer Vision for Smart Health Care [13.709260905038624]
  The work also presents Yoga-hand mudra (hand gestures) identification. The YOGI dataset has been developed which include 10 Yoga postures with around 400-900 images of each pose. XGBoost with RandomSearch CV is most accurate and gives 99.2% accuracy.
  arXiv  Detail & Related papers  (2022-01-19T13:41:58Z)
• How Do Adam and Training Strategies Help BNNs Optimization? [50.22482900678071]
  We show that Adam is better equipped to handle the rugged loss surface of BNNs and reaches a better optimum with higher generalization ability. We derive a simple training scheme, building on existing Adam-based optimization, which achieves 70.5% top-1 accuracy on the ImageNet dataset.
  arXiv  Detail & Related papers  (2021-06-21T17:59:51Z)
• MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks [57.69809561405253]
  We introduce a framework that is able to boost the vanilla ResNet-50 to 80%+ Top-1 accuracy on ImageNet without tricks. Our method obtains 80.67% top-1 accuracy on ImageNet using a single crop-size of 224x224 with vanilla ResNet-50. Our framework consistently improves from 69.76% to 73.19% on smaller ResNet-18.
  arXiv  Detail & Related papers  (2020-09-17T17:59:33Z)
• Whole-Body Human Pose Estimation in the Wild [88.09875133989155]
  COCO-WholeBody extends COCO dataset with whole-body annotations. It is the first benchmark that has manual annotations on the entire human body. A single-network model, named ZoomNet, is devised to take into account the hierarchical structure of the full human body.
  arXiv  Detail & Related papers  (2020-07-23T08:35:26Z)
• Yoga-82: A New Dataset for Fine-grained Classification of Human Poses [46.319423568714505]
  We present a dataset, Yoga-82, for large-scale yoga pose recognition with 82 classes. Yoga-82 consists of complex poses where fine annotations may not be possible. The dataset contains a three-level hierarchy including body positions, variations in body positions, and the actual pose names.
  arXiv  Detail & Related papers  (2020-04-22T01:43:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.