A Multi-Camera Active-Vision System for Deformable-Object-Motion Capture

Schacter, David; Donnici, Mario; Nuger, Evgeny; Mackay, Matthew; Benhabib, B.

doi:10.1007/s10846-013-9961-0

Cited by 10 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MCR for a priori unknown, deforming objects, has applications in the fields of medicine [26]- [28], surveillance [11], [29], [30], and entertainment [31], [32]. Surgical applications could implement an MCR method to capture the shape of deforming tissue during robot-assisted surgery.…”

Section: Motivationmentioning

confidence: 99%

“…An improved MCR method for the motion capture of deformable objects was proposed in [30], [158]. The method required an a priori known polygon object model with distinct object markers for correct detection and association.…”

Section: Multi-camera Reconfiguration For 3d Tasksmentioning

confidence: 99%

“…This process works for tracking starting from Demand Instant 0, as all triangulated points will be labeled as new in comparison with other methods that require an a priori demand-instant measurement [30], [158].…”

Section: Trackingmentioning

confidence: 99%

“…Direct comparisons between the developed methods and methods such as dense-passive [5], [49], [51], [198], [199], dense-active [45], [46], [200]- [202], structure from motion [52]- [54], and model-based [16], [29], [30], [157], [158] could not be conducted, but discussed herein. Dense passive methods focus on maximizing the stereo-correspondence density in narrow-baseline stereo configurations.…”

Section: Appendix Cmentioning

confidence: 99%

“…Model-based shaper recovery techniques, or motion capture techniques [16], [29], [30], [157], [158] rely on a priori known skeleton or mesh model of the target object before deployment. The advantage of these methods is that shape recovery is improved under poor camera placement conditions as the known model can be accurately fit to the observed data.…”

Section: Appendix Cmentioning

confidence: 99%

See 4 more Smart Citations

Multi-Camera Active-Vision for Markerless Shape Recovery of Unknown Deforming Objects

Nuger

Benhabib

2018

J Intell Robot Syst

Self Cite

View full text Add to dashboard Cite

This thesis proposes a multi-camera active-vision reconfiguration system which selects camera poses online to improve the shape recovery of a priori unknown, markerless, deforming objects in dynamic environments. The objectives of shape recovery are defined as surface sampling accuracy, and shape completeness. The completeness objective is generalized for both solid and surface-based objects as the maximization of surface visibility. Thus, improving the recovered shape of target objects is shown to be analogous to maximizing the surface area visibility. This improvement is achieved through the on-line reconfiguration of multiple cameras. The system developed herein is composed of a shape recovery method, a robust tracking algorithm, and a multi-camera reconfiguration method.The shape recovery method is based on a modular fusion technique that produces a complete 3D mesh-model of the target object. The method fuses triangulation data with a visual hull to maximize recovery accuracy. The modularity of the method lies in the ability to modify data filtering techniques to improve modelling accuracy, and interchange stereo correspondence features. The adaptive particle filtering algorithm produces a deformation estimation of the recovered model from the tracking data. The algorithm automatically adapts to the quantity of tracking data available and changes in the object's dynamics. The modularity of the algorithm allows modifications in terms of the number of particles and motion models for task-specific implementations. The reconfiguration method consists of a robust stereovisibility objective function, workspace discretization, and a path planner. The complete system can iii improve the shape recovery of a priori unknown deforming objects in obstacle-laden environments when compared to static camera methods.To validate the proposed system, extensive simulations and experiments were conducted. The simulations tested the system in comparison to static multi-camera systems, and ideal camera placement where the object model was a priori known and the camera's dynamics were unconstrained. Simulation results showed the proposed methodology outperformed static cameras and approached the performance of ideal camera placement in a dynamic, obstacle-laden environment. The experimental results showed similar improvement in shape recovery when comparison to a static camera system in an obstacle-laden environment.iv

show abstract

Section: Motivationmentioning

confidence: 99%

Section: Multi-camera Reconfiguration For 3d Tasksmentioning

confidence: 99%

Section: Trackingmentioning

confidence: 99%

Section: Appendix Cmentioning

confidence: 99%

Section: Appendix Cmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Camera Active-Vision for Markerless Shape Recovery of Unknown Deforming Objects

Nuger

Benhabib

2018

J Intell Robot Syst

Self Cite

View full text Add to dashboard Cite

show abstract

Assessing Spatiotemporal Behavior of Human Gait: A Comparative Study Between Low-Cost Smartphone-Based Mocap and OptiTrack Systems

Castillo,

Riascos,

Franco

et al. 2024

Exp Tech

View full text Add to dashboard Cite

This study assessed the accuracy of a low-cost marker-based motion capture system with smartphone devices to estimate the spatiotemporal behavior of human gait in comparison with the performance of the commercial OptiTrack system. Initially, three test subjects were selected for the study, and after equipping them with passive retroreflective markers, they were recorded for gait velocities of 1.50, 1.90, and 2.30 $$m\bullet {s}^{-1}$$ m ∙ s - 1 while collecting kinematic data and videos. The results showed that the smartphone motion capture system exhibited significant spatiotemporal tracking and accuracy in the x-y trajectories and estimation of joint relative angles of the hip, knee, and ankle joints (θ1, θ2, and θ3, respectively) compared to the commercial OptiTrack system. In this comparison, an average goodness-of-FIT and normalized root mean square error of over 88.93% and 2.71% were obtained, respectively, for the joint relative angles of the hip and knee (θ1 and θ2) in all tests performed. However, the accuracy of the joint relative angle of the ankle (θ3, average FIT: 71.04% and nRMSE: 4.26%) was lower because of the low capture rate of the retroreflective markers in the smartphone system and the higher relative velocity in the lower extremities of the test subjects, which generated noise in the calculation of x-y trajectories. This decrease in accuracy has been reported in other studies. However, both motion capture systems experienced marker data loss at the hip, highlighting the need for improvement in the spatial distribution of the optical devices. The OptiTrack system demonstrated better optical redundancy but still required improvements. In contrast, the smartphone system, with its inherent limitations in terms of optical redundancy and spatial distribution, can be enhanced by incorporating multiple cameras for a three-dimensional view. Despite these limitations, the low-cost smartphone system showed optimal performance with minimal errors compared with the commercial system, making it a cost-effective option with potential for further development. The rapid advancement of smartphone technology and its accessibility make it an attractive choice for motion capture applications.

show abstract