Modeling for Deformable Body and Motion Analysis: A Review

Pan, Hailang; Huo, Hongwen; Cui, Guoqin; Chen, Shengyong

doi:10.1155/2013/786749

Cited by 6 publications

(3 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The point cloud is rigged using the extracted skeleton information for animating it. First, the skeleton (or bones) of the rigged keyframe is animated to the location of the skeleton of the non-key frame and deformed in the form of the point cloud of the non-key frame [ 20 ]. The result of animating the point cloud is the deformed point cloud.…”

Section: Temporal Prediction Of Dynamic Point Cloudmentioning

confidence: 99%

Temporal Estimation of Non-Rigid Dynamic Human Point Cloud Sequence Using 3D Skeleton-Based Deformation for Compression

Kim

Jang

Lee

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper proposes an algorithm for transmitting and reconstructing the estimated point cloud by temporally estimating a dynamic point cloud sequence. When a non-rigid 3D point cloud sequence (PCS) is input, the sequence is divided into groups of point cloud frames (PCFs), and a key PCF is selected. The 3D skeleton is predicted through 3D pose estimation, and the motion of the skeleton is estimated by analyzing the joints and bones of the 3D skeleton. For the deformation of the non-rigid human PC, the 3D PC model is transformed into a mesh model, and the key PCF is rigged using the 3D skeleton. After deforming the key PCF into the target PCF utilizing the motion vector of the estimated skeleton, the residual PC between the motion compensation PCF and the target PCF is generated. If there is a key PCF, the motion vector of the target PCF, and a residual PC, the target PCF can be reconstructed. Just as compression is performed using pixel correlation between frames in a 2D video, this paper compresses 3D PCFs by estimating the non-rigid 3D motion of a 3D object in a 3D PC. The proposed algorithm can be regarded as an extension of the 2D motion estimation of a rigid local region in a 2D plane to the 3D motion estimation of a non-rigid object (human) in 3D space. Experimental results show that the proposed method can successfully compress 3D PC sequences. If it is used together with a PC compression technique such as MPEG PCC (point cloud compression) in the future, a system with high compression efficiency may be configured.

show abstract

Section: Temporal Prediction Of Dynamic Point Cloudmentioning

confidence: 99%

Temporal Estimation of Non-Rigid Dynamic Human Point Cloud Sequence Using 3D Skeleton-Based Deformation for Compression

Kim

Jang

Lee

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…A review by Pan et al [27] presents some of metaballs' applications in the modeling of the human body, but more specific organic objects can also be represented (e.g., tumors [2] or 1 http://algorithmicbotany.org/lstudio/ organs [28]). To the best of our knowledge, there have been no attempt to model FaVs from metaballs.…”

Section: A Skeletal Structures Generalized Cylinders and Metaballsmentioning

confidence: 99%

Generation of variability in shape, aspect and time of 3D Fruits and Vegetables

Verhulst

Normand

Moreau

2017

2017 23rd International Conference on Virtual System &Amp; Multimedia (VSMM)

View full text Add to dashboard Cite

“…Since previous generative methods only take the entire appearance as input, it is difficult for the model to understand the structural relationship between joints without supervision. As a result, a large deformation occurs during the movement process (Pan and Liu, 2008 ; Pan et al, 2013 ; Pan, 2015 ), and the quality of the generated video is far from satisfactory. The use of human skeleton motion data can well extract motion information.…”

Section: Introductionmentioning

confidence: 99%

Skeleton-based motion prediction: A survey

Usman

Zhong²

2022

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Human motion prediction based on 3D skeleton data is an active research topic in computer vision and multimedia analysis, which involves many disciplines, such as image processing, pattern recognition, and artificial intelligence. As an effective representation of human motion, human 3D skeleton data is favored by researchers because it provide resistant to light effects, scene changes, etc. earlier studies on human motion prediction focuses mainly on RBG data-based techniques. In recent years, researchers have proposed the fusion of human skeleton data and depth learning methods for human motion prediction and achieved good results. We first introduced human motion prediction research background and significance in this survey. We then summarized the latest deep learning-based techniques for predicting human motion in recent years. Finally, a detailed paper review and future development discussion are provided.

show abstract

Modeling for Deformable Body and Motion Analysis: A Review

Cited by 6 publications

References 57 publications

Temporal Estimation of Non-Rigid Dynamic Human Point Cloud Sequence Using 3D Skeleton-Based Deformation for Compression

Temporal Estimation of Non-Rigid Dynamic Human Point Cloud Sequence Using 3D Skeleton-Based Deformation for Compression

Generation of variability in shape, aspect and time of 3D Fruits and Vegetables

Skeleton-based motion prediction: A survey

Contact Info

Product

Resources

About