A Key-Pose Similarity Algorithm for Motion Data Retrieval

Sedmidubský, Jan; Valčík, Jakub; Zezula, Pavel

doi:10.1007/978-3-319-02895-8_60

Cited by 17 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human pose mining: Both works in [16] and [20] cluster 3D motion capture data and determine algorithmically similar motion sequences for database retrieval, while [18] develops a similarity algorithm for comparing key-poses, subsequently allowing for indexing motion features in human motion databases. For the task of action recognition, [11] and [2] perform clustering on shape based representations of 2d human poses and learn weights to favor distinctive key-poses.…”

Section: Related Workmentioning

confidence: 99%

Mining Automatically Estimated Poses from Video Recordings of Top Athletes

Lienhart

Einfalt

Zecha

2018

International Journal of Computer Science in Sport

View full text Add to dashboard Cite

Human pose detection systems based on state-of-the-art DNNs are on the go to be extended, adapted and re-trained to fit the application domain of specific sports. Therefore, plenty of noisy pose data will soon be available from videos recorded at a regular and frequent basis. This work is among the first to develop mining algorithms that can mine the expected abundance of noisy and annotationfree pose data from video recordings in individual sports. Using swimming as an example of a sport with dominant cyclic motion, we show how to determine unsupervised time-continuous cycle speeds and temporally striking poses as well as measure unsupervised cycle stability over time. Additionally, we use long jump as an example of a sport with a rigid phase-based motion to present a technique to automatically partition the temporally estimated pose sequences into their respective phases. This enables the extraction of performance relevant, pose-based metrics currently used by national professional sports associations. Experimental results prove the effectiveness of our mining algorithms, which can also be applied to other cycle-based or phase-based types of sport.

show abstract

Section: Related Workmentioning

confidence: 99%

Mining Automatically Estimated Poses from Video Recordings of Top Athletes

Lienhart

Einfalt

Zecha

2018

International Journal of Computer Science in Sport

View full text Add to dashboard Cite

show abstract

“…Similarity of motions is then determined by the DTW function that exploits the L 1 metric as the local cost measure for comparing particular pose vectors. Another system for sub‐motion retrieval is proposed by Sedmidubsky et al . This approach does not already require a query motion to be specified by several positive examples.…”

Section: Case Studiesmentioning

confidence: 99%

“…These applications require to process motion data effectively and efficiently. To do that, they usually exploit specialized techniques for annotating segments of motions by textual descriptions or retrieving motions or their sub‐motions that are similar to a query motion example . Such retrieval and annotation (classification) techniques require to process characteristic aspects of motion data, rather than raw spatio‐temporal 3D coordinates.…”

Section: Introductionmentioning

confidence: 99%

“…We primarily focus on a more general approach of nearest‐neighbor search that does not require any learning phase and can be additionally extended to classify the retrieved set of the most similar motions to the same output as the result of machine learning and probabilistic methods. The nearest‐neighbor search can be utilized for a wide scale of applications where similarity of motions plays the fundamental role, such as retrieval of analogous movements. Similarity is usually evaluated by a distance function (e.g., dynamic time warping (DTW)) applied to the extracted features of two motions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessing similarity models for human‐motion retrieval applications

Valčík

Sedmidubský

Zezula

2015

Computer Animation & Virtual

Self Cite

View full text Add to dashboard Cite

The development of motion capturing devices poses new challenges in the exploitation of human-motion data for various application fields, such as computer animation, visual surveillance, sports, or physical medicine. Recently, a number of approaches dealing with motion data have been proposed, suggesting characteristic motion features to be extracted and compared on the basis of similarity. Unfortunately, almost each approach defines its own set of motion features and comparison methods; thus, it is hard to fairly decide which similarity model is the most suitable for a given kind of human-motion retrieval application. To cope with this problem, we propose the human motion model evaluator, which is a generic framework for assessing candidate similarity models with respect to the purpose of the target application. The application purpose is specified by a user in form of a representative sample of categorized motion data. Respecting such categorization, the similarity models are assessed from the effectiveness and efficiency points of view using a set of space-complexity, information-retrieval, and performance measures. The usability of the framework is demonstrated by case studies of three practical examples of retrieval applications focusing on recognition of actions, detection of similar events, and identification of subjects.

show abstract

“…For the former case, the discriminative representation about the spatial and temporal characteristics of motion sequences can be used to increase the separability of different motions. In the past, much effort has been done to extract representative features and many different feature representations have been designed to characterize the human behaviors, e.g., the sequences of the most informative joints [1], a dynemes and forward differences representation [2], joint-angle rotations of the important joints [3] and joint distance matrix representation [4]. For the latter case, the classification scheme incorporating the training process was specifically designed to differentiate the diverse motions.…”

Section: Introductionmentioning

confidence: 99%

Motion Capture Behavior Recognition via Neighborhood Preserving Dictionary Learning

Peng

Liu

2015

2015 IEEE International Conference on Systems, Man, and Cybernetics

View full text Add to dashboard Cite

Behavior recognition from large available motion capture data has received wide attention in the computer animation community and is growing increasingly important in recent years. In this paper, we present an efficient motion capture behavior recognition approach via neighborhood preserving dictionary learning. First, we normalize all the motion sequences in the database to make the motion to be comparable. Then, the neighborhood preserving property is exploited using Iterative Nearest Neighbors algorithm and subsequently added as a constraint condition for discriminative dictionary learning, whereby the raw motion frame can be represented as a compact set of atoms consisting of neighborhood preserving characteristics. Finally, the recognition result can be efficiently obtained by sparse coding based classification scheme. Extensive experiments tested on publicly available motion capture databases have demonstrated the accuracy and effectiveness of the proposed approach.

show abstract

A Key-Pose Similarity Algorithm for Motion Data Retrieval

Cited by 17 publications

References 16 publications

Mining Automatically Estimated Poses from Video Recordings of Top Athletes

Mining Automatically Estimated Poses from Video Recordings of Top Athletes

Assessing similarity models for human‐motion retrieval applications

Motion Capture Behavior Recognition via Neighborhood Preserving Dictionary Learning

Contact Info

Product

Resources

About