Behavioral segmentation for human motion capture data based on graph cut method

Yu, Xiaomin; Liu, Weibin; Xing, Weiwei

doi:10.1016/j.jvlc.2017.09.001

Cited by 18 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At first, we perform segmentation experiments on Subject 86 dataset and we also do contrast experiments using TMM [11], Nystrom [12], HACA [7], ACA [2] and GMM [6] method. As shown in Fig.…”

Section: Experiments Results and Analysesmentioning

confidence: 99%

“…This method requires no interaction for the segmentation. Yu et al [12] deal with the human motion segmentation problem based on graph partition method. They construct an undirected weighted graph according to motion data and apply the t-nearest neighbors and Nystrom method for clustering motion data to finish motion segmentation.…”

Section: B Methods Based On Statistical Characteristicsmentioning

confidence: 99%

“…Finally, the lower right corner of is normalized according to Eq. (12). In this way, we get the value of DTAK of the two time-series: ( , ) = 11 13 = 0.85.…”

Section: Dynamic Time Alignment Kernelmentioning

confidence: 99%

See 2 more Smart Citations

A Framework for Human Motion Segmentation Based on Multiple Information of Motion Data

2019

KSII TIIS

View full text Add to dashboard Cite

With the development of films, games and animation industry, analysis and reuse of human motion capture data become more and more important. Human motion segmentation, which divides a long motion sequence into different types of fragments, is a key part of mocap-based techniques. However, most of the segmentation methods only take into account low-level physical information (motion characteristics) or high-level data information (statistical characteristics) of motion data. They cannot use the data information fully. In this paper, we propose an unsupervised framework using both low-level physical information and high-level data information of human motion data to solve the human segmentation problem. First, we introduce the algorithm of CFSFDP and optimize it to carry out initial segmentation and obtain a good result quickly. Second, we use the ACA method to perform optimized segmentation for improving the result of segmentation. The experiments demonstrate that our framework has an excellent performance.

show abstract

Section: Experiments Results and Analysesmentioning

confidence: 99%

Section: B Methods Based On Statistical Characteristicsmentioning

confidence: 99%

See 1 more Smart Citation

A Framework for Human Motion Segmentation Based on Multiple Information of Motion Data

2019

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…However, there are some phenomena that the division point is increased, lost, or erroneous on different motion data sequences. Yu et al 13 have recently proposed the t-nearest and Nyström algorithm based on the graph cut, and the segmentation effect is ideal. As shown in Table 2, our algorithm is only better than t-nearest in the recall indicator, whereas the other indicators are slightly worse, but the results are very close.…”

Section: Experiments Analysismentioning

confidence: 99%

Motion capture data segmentation using Riemannian manifold learning

Wang

Liu

Xing

2019

Computer Animation & Virtual

View full text Add to dashboard Cite

Due to the inherent nonlinear nature of data, traditional linear methods have some limitations in finding the intrinsic dimensions of motion capture (Mo‐cap) data. Mo‐cap data are more in line with the characteristics of the manifold. Assuming that the data are initially a low‐dimensional manifold and uniformly sampled in high‐dimensional Euclidean space, manifold learning recovers low‐dimensional manifold structures from high‐dimensional sampled data. This paper proposes an automatic segmentation method based on geodesics by introducing a Riemannian manifold. We convert Mo‐cap data from Euler angles into quaternions, calculate the intrinsic mean of the motion sequence, hemispherize quaternions, and use logarithmic and exponential mapping to calculate geodesic distances instead of quaternions. The experimental results show that the algorithms can achieve automatic segmentation and have a better segmentation effect.

show abstract

“…The retrieved sets of similar frames are then ranked in temporal order to identify queryrelevant subsequences [26]. Since searching in frame-based features needn't be so effective, the segment-based features are extracted from overlapping [25] or disjoint [28] segments, which are detected in an unsupervised way [13,37] from both the long motion and query. To identify query-relevant segments, sequential search can be used, such as the A-LTK method in [9] or string-matching-based algorithm in [5].…”

Section: Similarity Searchingmentioning

confidence: 99%

Similarity-Based Processing of Motion Capture Data

Sedmidubský

Zezula

2018

Proceedings of the 26th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Motion capture technologies digitize human movements by tracking 3D positions of specific skeleton joints in time. Such spatiotemporal data have an enormous application potential in many fields, ranging from computer animation, through security and sports to medicine, but their computerized processing is a difficult problem. The recorded data can be imprecise, voluminous, and the same movement action can be performed by various subjects in a number of alternatives that can vary in speed, timing or a position in space. This requires employing completely different data-processing paradigms compared to the traditional domains such as attributes, text or images. The objective of this tutorial is to explain fundamental principles and technologies designed for similarity comparison, searching, subsequence matching, classification and action detection in the motion capture data. Specifically, we emphasize the importance of similarity needed to express the degree of accordance between pairs of motion sequences and also discuss the machine-learning approaches able to automatically acquire content-descriptive movement features. We explain how the concept of similarity together with the learned features can be employed for searching similar occurrences of interested actions within a long motion sequence. Assuming a user-provided categorization of example motions, we discuss techniques able to recognize types of specific movement actions and detect such kinds of actions within continuous motion sequences. Selected operations will be demonstrated by on-line web applications. CCS CONCEPTS • Information systems → Similarity measures; Clustering and classification; Multimedia and multimodal retrieval; • Computing methodologies → Supervised learning by classification;

show abstract

Behavioral segmentation for human motion capture data based on graph cut method

Cited by 18 publications

References 14 publications

A Framework for Human Motion Segmentation Based on Multiple Information of Motion Data

A Framework for Human Motion Segmentation Based on Multiple Information of Motion Data

Motion capture data segmentation using Riemannian manifold learning

Similarity-Based Processing of Motion Capture Data

Contact Info

Product

Resources

About