Shape from silhouette using Dempster–Shafer theory

Diaz-Mas, L.; Muñoz-Salinas, Rafael; Madrid-Cuevas, F. J.; Medina-Carnicer, R.

doi:10.1016/j.patcog.2010.01.001

Cited by 36 publications

(15 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Section 4, we solve this problem by applying a 3D reconstruction method, called shape-from-silhouette 10) , which reconstructs the 3D shape of target objects by combining silhouette images generated from multiple-view images. When the shuttle moves very quickly and anomalously, we estimate its 3D position as a 3D trajectory, rather than an individual position, and we observe it as a single curved-line by the motion blur in the captured images.…”

Section: Related Workmentioning

confidence: 99%

[Paper] Visual Tracking Method of a Quick and Anomalously Moving Badminton Shuttlecock

Shishido

Kameda

Ohta

et al. 2017

MTA

View full text Add to dashboard Cite

This paper introduces a method that uses multiple-view videos to estimate the 3D position of a badminton shuttle that moves quickly and anomalously. When an object moves quickly, it is observed with a motion blur effect. By utilizing the information provided by the shape of the motion blur region, we propose a visual tracking method for objects that have an erratic and drastically changing moving speed. When the speed increases tremendously, we propose another method, which applies the shape-from-silhouette technique, to estimate the 3D position of a moving shuttlecock using unsynchronized multiple-view videos. We confirmed the effectiveness of our proposed technique using video sequences and a CG simulation image set.

show abstract

Section: Related Workmentioning

confidence: 99%

[Paper] Visual Tracking Method of a Quick and Anomalously Moving Badminton Shuttlecock

Shishido

Kameda

Ohta

et al. 2017

MTA

View full text Add to dashboard Cite

show abstract

“…2. 3D reconstruction from silhouettes captured from several viewpoints, by Shape from Silhouette algorithm [10]. 3.…”

Section: View-independent Approachesmentioning

confidence: 99%

“…As described in more detail in [10], SfS method examine voxel projections in the foreground images in order to determine whether they belong to the shape of objects or not. Each voxel is projected in all the foreground images and if its projection lays completely into a silhouette in all the foreground images, then it is considered occupied.…”

Section: D Reconstructionmentioning

confidence: 99%

Entropy volumes for viewpoint-independent gait recognition

López-Fernández

Madrid-Cuevas

Carmona-Poyato

et al. 2015

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

Gait as biometrics has been widely used for human identification. However, direction changes cause difficulties for most of the gait recognition systems, due to appearance changes. This study presents an efficient multi-view gait recognition method that allows curved trajectories on completely unconstrained paths for indoor environments. Our method is based on volumetric reconstructions of humans, aligned along their way. A new gait descriptor, termed as Gait Entropy Volume (GEnV), is also proposed. GEnV focuses on capturing 3D dynamical information of walking humans through the concept of entropy. Our approach does not require the sequence to be split into gait cycles. A GEnV based signature is computed on the basis of the previous 3D gait volumes. Each signature is classified by a Support Vector Machine, and a majority voting policy is used to smooth and reinforce the classifications results. The proposed approach is experimentally validated on the "AVA Multi-View Gait Dataset (AVAMVG)" and on the "Kyushu University 4D Gait Database (KY4D)". The results show that this new approach achieves promising results in the problem of gait recognition on unconstrained paths.

show abstract

“…However, the use of volumetric reconstruction (based on foreground silhouettes) has the problem of propagating the segmentation errors to the 3D space. 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%

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

Shape from silhouette using Dempster–Shafer theory

Cited by 36 publications

References 34 publications

[Paper] Visual Tracking Method of a Quick and Anomalously Moving Badminton Shuttlecock

[Paper] Visual Tracking Method of a Quick and Anomalously Moving Badminton Shuttlecock

Entropy volumes for viewpoint-independent gait recognition

Parallelization strategies for markerless human motion capture

Contact Info

Product

Resources

About