2D Human pose estimation: a survey

Chen, Haoming; Feng, Runyang; Wu, Sifan; Xu, Hao; Zhou, Fengcheng; Liu, Zhenguang

doi:10.1007/s00530-022-01019-0

Cited by 29 publications

(12 citation statements)

References 173 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While leveraging Inception-v3 as a foundational model for yoga pose detection is promising, additional refinement steps such as data augmentation, regularization techniques [21], and post-processing algorithms may be warranted to optimize performance further. Additionally, optimizing the model for real-time inference in deployment scenarios may necessitate additional considerations for efficiency and speed.…”

Section: Algorithm a Inception V3mentioning

confidence: 99%

Advancing Yoga Practice : Leveraging Opencv and Mediapipe for Pose Detection

2024

IRJMETS

View full text Add to dashboard Cite

Yoga is a centuries-old practice that has become more popular all over the world due to its benefits for the body, mind, and spirit [1]. Nowadays, yoga is a popular kind of fitness all around the world. Proper posture is the cornerstone of yoga. Despite all of yoga's health benefits, bad posture can cause problems including sprains and soreness in the muscles. Over the past few years, working remotely has drawn more interest from people than working in person. Our approach is beneficial to people who are used to living online and struggle to find the time to visit yoga facilities. An increasing number of people are interested in automating the analysis of yoga postures in order to improve practitioners' performance and knowledge of the poses as a result of technological integration. Our technique is used by the suggested system to accurately extract features and estimate pose from input photos or video frames. The model classifies the yoga positions using our system's web cameras, and the image is used as input. The asana is improved by enhancing the input derived from the yoga postures through the application of multiple deep learning models.

show abstract

Section: Algorithm a Inception V3mentioning

confidence: 99%

Advancing Yoga Practice : Leveraging Opencv and Mediapipe for Pose Detection

2024

IRJMETS

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Networks (CNNs) have enabled impressive advances for human pose estimation [ 5 , 8 , 10 , 11 ]. Convolutional pose machines [ 2 ] utilize a CNN with stages that refine joint detection.…”

Section: Related Workmentioning

confidence: 99%

Full-BAPose: Bottom Up Framework for Full Body Pose Estimation

Artacho

Savakis

2023

Sensors

View full text Add to dashboard Cite

We present Full-BAPose, a novel bottom-up approach for full body pose estimation that achieves state-of-the-art results without relying on external people detectors. The Full-BAPose method addresses the broader task of full body pose estimation including hands, feet, and facial landmarks. Our deep learning architecture is end-to-end trainable based on an encoder-decoder configuration with HRNet backbone and multi-scale representations using a disentangled waterfall atrous spatial pooling module. The disentangled waterfall module leverages the efficiency of progressive filtering, while maintaining multi-scale fields-of-view comparable to spatial pyramid configurations. Additionally, it combines multi-scale features obtained from the waterfall flow with the person-detection capability of the disentangled adaptive regression and incorporates adaptive convolutions to infer keypoints more precisely in crowded scenes. Full-BAPose achieves state-of-the art performance on the challenging CrowdPose and COCO-WholeBody datasets, with AP of 72.2% and 68.4%, respectively, based on 133 keypoints. Our results demonstrate that Full-BAPose is efficient and robust when operating under a variety conditions, including multiple people, changes in scale, and occlusions.

show abstract

“…When integrated with robotics, DL models yielded significant contributions to HRI, enabling robots to recognize and interpret human cues such as body poses and hand gestures [25]. Human pose estimation involves detecting the body poses of individuals by identifying keypoints that represent important joints [9]. There are two common approaches to pose estimation: top-down and bottomup.…”

Section: Introductionmentioning

confidence: 99%

Improving Visual Perception of a Social Robot for Controlled and In-the-wild Human-robot Interaction

Zhong,

Tian,

et al. 2024

Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction

View full text Add to dashboard Cite

Social robots often rely on visual perception to understand their users and the environment. Recent advancements in data-driven approaches for computer vision have demonstrated great potentials for applying deep-learning models to enhance a social robot's visual perception. However, the high computational demands of deep-learning methods, as opposed to the more resource-efficient shallow-learning models, bring up important questions regarding their effects on real-world interaction and user experience. It is unclear how will the objective interaction performance and subjective user experience be influenced when a social robot adopts a deep-learning based visual perception model. We employed stateof-the-art human perception and tracking models to improve the visual perception function of the Pepper robot and conducted a controlled lab study and an in-the-wild human-robot interaction study to evaluate this novel perception function for following a specific user with other people present in the scene.

show abstract

2D Human pose estimation: a survey

Cited by 29 publications

References 173 publications

Advancing Yoga Practice : Leveraging Opencv and Mediapipe for Pose Detection

Advancing Yoga Practice : Leveraging Opencv and Mediapipe for Pose Detection

Full-BAPose: Bottom Up Framework for Full Body Pose Estimation

Improving Visual Perception of a Social Robot for Controlled and In-the-wild Human-robot Interaction

Contact Info

Product

Resources

About