View Independent Human Gait Recognition Using Markerless 3D Human Motion Capture

Krzeszowski, Tomasz; Kwolek, Bogdan; Michalczuk, Agnieszka; Świtoński, Adam; Josiński, Henryk

doi:10.1007/978-3-642-33564-8_59

Cited by 12 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research teams solve the abovementioned issues in many different ways. The most common method is making use of simplified human body models (Deutscher and Reid, 2005;John et al, 2010;Krzeszowski et al, 2012), uniform background (Deutscher and Reid, 2005), and also properly selected clothes of the tracked human body in order to facilitate the determination of distinctive features. In the process of tracking, the particle filter algorithm (Sidenbladh et al, 2000) or its modified versions are often used (Deutscher and Reid, 2005).…”

Section: Articulated Human Motion Trackingmentioning

confidence: 99%

“…position and orientation in space as well as the angles between the joints. The model used in this research is based on the kinematic tree structure consisting of 11 segments; each of them is represented using a truncated cone (Krzeszowski et al, 2012;Deutscher and Reid, 2005), Fig. 1.…”

Section: D Human Body Modelmentioning

confidence: 99%

“…Each segment can include up to three DoFs that define its orientation; an exception is the pelvis that can contain three additional segments defining the model translation. For tracking the human body motion, models for which the number of DoFs ranges from 26 (Krzeszowski et al, 2012;Kwolek et al, 2012) to over 30 (Deutscher and Reid, 2005) are usually used; the model suggested in this paper includes 17 DoFs. Restriction of the search space is possible, since a concrete problem is considered, i.e.…”

Section: D Human Body Modelmentioning

confidence: 99%

“…In the motion tracking process, the particle swarm optimization algorithm (PSO) (Kennedy and Eberhart, 1995), was used; its usefulness in solving problems related to the estimation of human pose has been repeatedly confirmed (John et al, 2010;Krzeszowski et al, 2012;Kwolek et al, 2012). In that algorithm, particle swarm is used in order to find the best solution; each of the particles represents a hypothetical solution of the problem.…”

Section: Tracking Algorithmmentioning

confidence: 99%

“…The fitness function used in this study is based on two sum components. The first of them is determined based on the extracted human silhouette, whereas the other one was based on the edge distance map (John et al, 2010;Krzeszowski et al, 2012). The value of the function is determined based on the following equation:…”

Section: Fitness Functionmentioning

confidence: 99%

See 4 more Smart Citations

Markerless Motion Tracking in Evaluation of Hurdle Clearance Parameters

Przednówek

Krzeszowski

Iskra³

et al. 2014

Proceedings of the 2nd International Congress on Sports Sciences Research and Technology Support

Self Cite

View full text Add to dashboard Cite

In this study, implementation of markerless method of human body motion tracking as a tool of measurement of hurdle clearance kinematic parameters was presented. The analysis involved 5 hurdle runners at various training levels. Recording of video sequences was carried out under simulated starting conditions of a 110 m hurdle race. Kinematic parameters were determined based on the analysis of images recorded with a 100 Hz monocular camera. The suggested method does not involve using any special clothes, markers or estimation support techniques. In the study, the basic numerical characteristics of twenty estimated parameters were presented. The accuracy of determined hurdle clearance parameters was verified by comparison of estimated poses with the ground truth pose. As the quality criterion, the MAE (Mean Absolute Error) was adopted. In the distance parameters, the least error was obtained for the distance between the center of mass (CM) and the hurdle at the first hurdle clearance phase (MAE = 22.0 mm). For the angular parameters, the least error was obtained for the leg angle at the first hurdle clearance phase (MAE = 3.1 •). The level of computed errors showed that the presented method can be used for estimation of hurdle clearance kinematic parameters.

show abstract