Real Time Body Pose Tracking in an Immersive Training Environment

Zhuo

et al. 2015

Multimed Tools Appl

During the last decade, the development of the immersive virtual reality (VR) has achieved a great progress in different application areas. For more advanced large-scale immersive VR environments or systems, one of the most challenge is to accurately track the position of the user's body part such as head when he/she is immersived in the environment to feel the changes among the synthetic stereoscopic image sequences. Unfortunately, accurate tracking is not easy in the virtual reality scenarios due to the variety types of existing intrinsic and extrinsic changes when tracking is on-the-fly. Especially for the single tracker, a long time accurate tracking is usually not possible because of the model adaption problem in different environments. Recent trend of research in tracking is to incorporate multiple trackers into a compositive learning framework and utilize the advantages of different trackers for more effective tracking. Therefore, in this paper, we propose a novel Bayesian tracking fusion framework with online classifier ensemble strategy. The proposed tracking formulates a fusion framework for online learning of multiple trackers by modeling a cumulative loss minimization process. With an optimal pair-wise sampling Multimed Tools Appl scheme for the SVM classifier, the proposed fusion framework can achieve more accurate tracking performance when compared with the other state-of-art trackers. In addition, the experiments on the standard benchmark database also verify that the proposed tracking is able to handle the challenges in many immersive VR applications and environments.

Section: Introductionmentioning

confidence: 99%

Bayesian tracking fusion framework with online classifier ensemble for immersive visual applications

Zhuo

et al. 2015

Multimed Tools Appl

2012 18th International Conference on Virtual Systems and Multimedia

“…The configuration uses a top down approach, approximating the user's position and mass by segmenting them from the ground, using a bounding volume placed around the user's mass aids in cal- Segmentation of individual body parts for recognition is one of many tasks that have to be overcome in a system that requires it. Firstly, it is usually more efficient to work with processed images where the background has been removed, this aids in defining movement amongst elements, as described by Maes et al [36], Chu et al [13] and Carbini et al [9]. Each technique differs in gesture processing but all are facilitated by background removal techniques.…”

Section: Wireless Recognitionmentioning

confidence: 99%

“…Image processing was researched by Chu et al [13] where compiled image informa- The latter uses a more advanced method of facial and hand recognition, defined by Carbini et al [9] in which the left and right hand are treated separately, the first for (main hand) is used for selection and the other hand for manipulation. The image is divided into 16 segments, discarding those that do not contain facial or extremity information or any sign of movement.…”

Section: Wireless Recognitionmentioning

confidence: 99%

Interactive exploration of historic information via gesture recognition

Bailey

Powell

Laycock

et al. 2012

Developers of interactive exhibits often struggle to find appropriate input devices that enable intuitive control, permitting the visitors to engage effectively with the content. Recently motion sensing input devices like the Microsoft Kinect or Panasonic D-Imager have become available enabling gesture based control of computer systems. These devices present an attractive input device for exhibits since the user can interact with their hands and they are not required to physically touch any part of the system. In this thesis we investigate techniques to enable the raw data coming from these types of devices to be used to control an interactive exhibit. Object recognition and tracking techniques are used to analyse the user's hand where movement and clicks are processed. To show the effectiveness of the techniques the gesture system is used to control an interactive system designed to inform the public about iconic buildings in the centre of Norwich, UK. We evaluate two methods of making selections in the test environment.At the time of experimentation the technologies were relatively new to the image processing environment. As a result of the research presented in this thesis, the techniques and methods used have been detailed and published [3] at the VSMM (Virtual Systems and Multimedia 2012) conference with the intention of further forwarding the area.

Lecture Notes in Computer Science

“…This is a substantial enhancement over previous capabilities [5] which focused on upright body tracking and rigid arm movements. The increased degrees of freedom pose severe difficulties, both in achieving robust and accurate tracking and in maintaining real-time operation.…”

Section: Introductionmentioning

confidence: 96%

Real-Time 3D Body Pose Tracking from Multiple 2D Images

Chu

Nevatia

Self Cite

Abstract. We present a human body motion tracking system for an interactive virtual simulation training environment. This system captures images using IR illumination and near-IR cameras to overcome limitations of a dimly lit environment. Features, such as silhouettes and medial axis of blobs are extracted from the images which lack much internal texture. We use a combination of a 2D ICP and particle filtering method to estimate the articulated body configuration of a trainee from image features. The method allows articulation of the arms at elbows and shoulders and of the body at the waist; this is a considerable improvement over previous such methods. Our system works in real-time and is robust to temporary errors in image acquisition or tracking. The system serves as part of a multi-modal user-input device for interactive simulation.