Evaluation of Model based Tracking with TrakMark Dataset

نویسندگان

  • Antoine Petit
  • Guillaume Caron
  • Hideaki Uchiyama
  • Eric Marchand
چکیده

We benchmark two tracking methods developed in the INRIA Lagadic team with a TrakMark dataset. Since these methods are based on a 3D model based approach, we selected a dataset named “Conference Venue Package 01” that includes a 3D textured model of a scene. For the evaluation. we compute the error of 3D rotation and translation with the ground truth transformation matrix. Through these evaluations, we confirmed that the provided dataset was suitable for quantitative evaluations of 3D visual tracking.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Projective indices for AR/MR benchmarking in TrakMark

We propose to exploit “projective indices” to compare camera tracking methods for augmented reality (AR) and mixed reality (MR). Projective indices are calculated by projection error of virtual points that are placed in the scene. The number of virtual points, their positions, and how to calculate the indices are important to compare different camera tracking methods as these parameters largely...

متن کامل

Proposal of international voluntary activities on establishing benchmark test schemes for AR/MR geometric registration and tracking methods

We collectively term the framework for the proposed benchmark test, as well as evaluation software now in the pipeline and the body of evaluation data as TrakMark, with the group assigned to work thereon as the TrakMark WG. This title borrows from terms often found in the PC field, such as PCMark and 3DMark. Establishment of the TrakMark WG was approved at the 33rd SIG-MR Committee Meeting held...

متن کامل

An intermediate report of TrakMark WG - international voluntary activities on establishing benchmark test schemes for AR/MR geometric registration and tracking methods

In the study of ARlMR field, tracking and geometric registration methods are very important topics that are actively discussed. Especially, the study on tracking is flourishing and many algorithms are being proposed every year. With this trend in mind, we, the TrakMark WG, had proposed benchmark test schemes for geometric registration and tracking in ARlMR at ISM AR 2009 [1]. This paper is an i...

متن کامل

A Framework for Optimal Attribute Evaluation and Selection in Hesitant Fuzzy Environment Based on Enhanced Ordered Weighted Entropy Approach for Medical Dataset

Background: In this paper, a generic hesitant fuzzy set (HFS) model for clustering various ECG beats according to weights of attributes is proposed. A comprehensive review of the electrocardiogram signal classification and segmentation methodologies indicates that algorithms which are able to effectively handle the nonstationary and uncertainty of the signals should be used for ECG analysis. Ex...

متن کامل

Test and Evaluation of Patient Tracking Platform: Use of Near Field Communication

In an earthquake situation, medical response communities such as field and referral hospitals are being challenged with injured victims’ identification and tracking. In our project, we developed a patient tracking platform (PTP). In this platform, first responders triage the patients with an electronic tag that reports the location and some information of each patient during his or her movement...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011