Skeleton-aware multi-scale heatmap regression for 2D hand pose estimation

Kourbane, Ikram; Genç, Yakup

doi:10.48550/arxiv.2105.10904

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the accuracy, speed and other performance of hand pose estimation have been continuously improved. Although the 3D hand pose estimation [3,5,13,14] has attracted more and more attention, the 2D hand pose estimation [2,15,16] is still an essential research direction. A large number of 3D hand pose estimation algorithms rely on the corresponding 2D algorithms [3,17], which obtain the result of estimation by mapping the features of 2D space to 3D space.…”

Section: Background and Significancementioning

confidence: 99%

“…Goodfellow et al [28] proposed a Generative Adversarial Network (GAN) based on the core idea of synthesizing data in the skeleton space for outputting hand poses. Kourbane et al [29] proposed a new 2D hand pose estimation method, which has multi-scale heatmap regression performance, and adopts hand skeleton as additional information to constrain the regression problem.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Hand pose estimation based on improved NSRM network

Wang

et al. 2023

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Hand pose estimation is the basis of dynamic gesture recognition. In vision-based hand pose estimation, the performance of hand pose estimation is affected due to the high flexibility of hand joints, local similarity and severe occlusion among hand joints. In this paper, the structural relations between hand joints are established, and the improved nonparametric structure regularization machine (NSRM) is used to achieve more accurate estimation of hand pose. Based on the NSRM network, the backbone network is replaced by the new high-resolution net proposed in this paper to improve the network performance, and then the number of parameters is decreased by reducing the input and output channels of some convolutional layers. The experiment of hand pose estimation is carried out by using public dataset, the experimental results show that the improved NSRM network has higher accuracy and faster inference speed for hand pose estimation.

show abstract

Section: Background and Significancementioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Hand pose estimation based on improved NSRM network

Wang

et al. 2023

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Goodfellow et al [19] proposed a Generative Adversarial Network (GAN) based on the key idea of synthesising data in the skeleton space for outputting hand poses. Kourbane et al [20] proposed a new 2D hand pose estimation method, which has multi-scale heatmap regression performance, and adopts hand skeleton as additional information to constrain the regression problem.…”

Section: Related Workmentioning

confidence: 99%

“…By observing the NSRM network based on LPM_G1_6 mask, it can be found that the backbone Excellent HRNet [14,20] pose estimation network maps of different resolution may be connected in parallel, rather than simply in series, which makes the whole network structure keeps the high-resolution characterization, and network in the same depth and similar levels of low resolution said, with the help of repeat the multi-scale fusion in order to enhance the high resolution, to improve the accuracy of prediction. Therefore, the original backbone network is replaced by HRNet network.…”

Section: Optimized Nsrm Networkmentioning

confidence: 99%

Hand Pose Estimation Based on Improved NSRM Network

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Hand pose estimation is the basis of dynamic gesture recognition. In vision-based hand pose estimation, the joints of the human hand are highly flexible, and problems such as local similarity and severe occlusion have great influence on the estimation of hand posture. In order to identify the complicated hand posture, the structural relationship between the hand nodes is established, more accurate hand pose estimation can be achieved through the improved Nonparametric Structure Regularization Machine (NSRM) in this paper. Based on the NSRM network, the backbone network is replaced by New High-Resolution Net (NHRNet), then the input and output channels of some convolutional layers are reduced. Finally, a public dataset is used to conduct the hand pose estimation experiments. The experimental results show that the optimized NSRM network has higher accuracy and faster recognition speed for hand pose estimation.

show abstract

Skeleton-aware multi-scale heatmap regression for 2D hand pose estimation

Cited by 2 publications

References 0 publications

Hand pose estimation based on improved NSRM network

Hand pose estimation based on improved NSRM network

Hand Pose Estimation Based on Improved NSRM Network

Contact Info

Product

Resources

About