Effective Descriptors for Human Action Retrieval from 3D Mesh Sequences

Abstract

Two novel methods for fully unsupervised human action retrieval using 3D mesh sequences are presented. The first achieves high accuracy but is suitable for sequences consisting of clean meshes, such as artificial sequences or highly post-processed real sequences, while the second one is robust and suitable for noisy meshes, such as those that often result from unprocessed scanning or 3D surface reconstruction errors. The first method uses a spatio-temporal descriptor based on the trajectories of 6 salient points of the human body (i.e. the centroid, the top of the head and the ends of the two upper and two lower limbs) from which a set of kinematic features are extracted. The resulting features are transformed using the wavelet transformation in different scales and a set of statistics are used to obtain the descriptor. An important characteristic of this descriptor is that its length is constant independent of the number of frames in the sequence. The second descriptor consists of two complementary sub-descriptors, one based on the trajectory of the centroid of the human body across frames and the other based on the Hybrid static shape descriptor adapted for mesh sequences. The robustness of the second descriptor derives from the robustness involved in extracting the centroid and the Hybrid sub-descriptors. Performance figures on publicly available real and artificial datasets demonstrate our accuracy and robustness claims and in most cases the results outperform the state-of-the-art.

RETRACTED: Based on spatio-temporal graph convolution networks with residual connection for intelligence behavior recognition

“…Most of these methods learn motion features from RGB-D image sequences. The work of Veinidis et al 7 proposes to construct a spherical histogram using the 3D position of the joint. After reprojecting and clustering into a vocabulary using LDA, the encoded features are fed to a hidden Markov model (HMM) for classification.…”

Three-Dimensional Image Analysis and Training Method of Action Characteristics of Sanda Whip Leg Technique Based on Wavelet Transform

“…But the analysis found that the score rate and usage rate are not proportional. It shows that there are still problems that need to be improved and improved in the teaching and training of whipping [6].…”

A Riemannian Framework for Analysis of Human Body Surface

“…The Figure 3 clearly evidences that the 3D human with similar poses belong to very close distributions. These results show the assumption that given a = 0, λ = 0, c = 1 (normal field L 2 metric), the metric is preserved under shape change, and could be used in pose and motion analysis application [18,28]. The figure 4 shows that 3D human with similar shape belong to very close distribution.…”