3D human motion tracking based on a progressive particle filter

Chang, I-Cheng; Lin, Shih-Yao

doi:10.1016/j.patcog.2010.05.003

Cited by 41 publications

(19 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chang et al [21] proposed a progressive particle filter. The main idea was to combine a standard particle filter with the mean shift strategy [22] and a hierarchical search.…”

Section: Computer Vision Approachesmentioning

confidence: 99%

Comparing evolutionary algorithms and particle filters for Markerless Human Motion Capture

Yeguas-Bolivar

Muñoz-Salinas

Medina-Carnicer

et al. 2014

Applied Soft Computing

View full text Add to dashboard Cite

Markerless Human Motion Capture is the problem of determining the joints' angles of a three-dimensional articulated body model that best matches current and past observations acquired by video cameras. The problem of Markerless Human Motion Capture is high-dimensional and requires the use of models with a considerable number of degrees of freedom to appropriately adapt to the human anatomy.Particle filters have become the most popular approach for Markerless Human Motion Capture, despite their difficulty to cope with high-dimensional problems. Although several solutions have been proposed to improve their performance, they still suffer from the curse of dimensionality. As a consequence, it is normally required to impose mobility limitations in the body models employed, or to exploit the hierarchical nature of the human skeleton by partitioning the problem into smaller ones.Evolutionary algorithms, though, are powerful methods for solving continuous optimization problems, specially the highdimensional ones. Yet, few works have tackled Markerless Human Motion Capture using them. This paper evaluates the performance of three of the most competitive algorithms in continuous optimization -Covariance Matrix Adaptation Evolutionary Strategy, Differential Evolution and Particle Swarm Optimization -with two of the most relevant particle filters proposed in the literature namely, the Annealed Particle Filter, and the Partitioned Sampling Annealed Particle Filter.The algorithms have been experimentally compared in the public dataset HumanEva-I by employing two body models with different complexities. Our work also analyzes the performance of the algorithms in hierarchical and holistic approaches, i.e., with and without partitioning the search space. Non-parametric tests run on the results have shown that: (i) the evolutionary algorithms employed outperform their particle filter counterparts in all the cases tested; (ii) they can deal with high-dimensional models thus leading to better accuracy; and (iii) that the hierarchical strategy surpasses the holistic one.

show abstract

“…Chang et al [21] proposed a progressive particle filter. The main idea was to combine a standard particle filter with the mean shift strategy [22] and a hierarchical search.…”

Section: Computer Vision Approachesmentioning

confidence: 99%

Comparing evolutionary algorithms and particle filters for Markerless Human Motion Capture

Yeguas-Bolivar

Muñoz-Salinas

Medina-Carnicer

et al. 2014

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…Chang et al described a 3D base tracking algorithm that utilises a video camera filming several points on a moving subject. 13 The computer algorithm is able to estimate the position of all the points based on the observed video images, and converts these to digital images creating an articulated digital model. The clear advantage over other techniques is that no markers nor cameras nor any form of radiation are required.…”

Section: Discussionmentioning

confidence: 99%

The effects of a semi-rigid soled shoe compared to walking barefoot on knee adduction moment

Ghosh

Robati

Sharp

2016

Journal of Orthopaedics

View full text Add to dashboard Cite

“…For instance, there are works [4,13,16,22] which employ models with no more than 32 degrees of freedom (DOF) and assume no mobility in dorsal spine, hands and feet. This simplification of the human anatomy allows a tractable computation of the model while achieving acceptable results for some applications.…”

Section: Optimization Approachesmentioning

confidence: 99%

“…So, almost perfect segmentations or robust methods to deal with inconsistent silhouettes [14,15,31] are required to obtain correct volumetric reconstructions. In contrast, other authors evaluate the foreground images directly [1,4,13] to deal with segmentation errors.…”

Section: Parallelization Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Parallelization strategies for markerless human motion capture

Cano

Yeguas-Bolivar

Muñoz-Salinas

et al. 2014

J Real-Time Image Proc

View full text Add to dashboard Cite

Markerless Motion Capture (MMOCAP) is the problem of determining the pose of a person from images captured by one or several cameras simultaneously without using markers on the subject. Evaluation of the solutions is frequently the most time-consuming task, making most of the proposed methods inapplicable in real-time scenarios. This paper presents an efficient approach to parallelize the evaluation of the solutions in CPUs and GPUs. Our proposal is experimentally compared on six sequences of the HumanEva-I dataset using the CMAES algorithm. Multiple algorithm's configurations were tested to analyze the best trade-off in regard to the accuracy and computing time. The proposed methods obtain speedups of 8× in multi-core CPUs, 30× in a single GPU and up to 110× using 4 GPUs.

show abstract

3D human motion tracking based on a progressive particle filter

Cited by 41 publications

References 13 publications

Comparing evolutionary algorithms and particle filters for Markerless Human Motion Capture

Comparing evolutionary algorithms and particle filters for Markerless Human Motion Capture

The effects of a semi-rigid soled shoe compared to walking barefoot on knee adduction moment

Parallelization strategies for markerless human motion capture

Contact Info

Product

Resources

About