Ground Truth Systems for Object Recognition and Tracking

Published

March 29, 2013

Author(s)

Afzal A. Godil, Roger D. Eastman, Tsai H. Hong

Abstract

In this report we discuss different types of ground-truth systems used for evaluation of object recognition and tracking systems in industrial manufacturing environments. We discuss three main ways for acquiring ground truth for object recognition and tracking: 1) physics based simulation ground-truth systems, 2) annotation/labeling ground-truth systems, 3) autonomous ground-truth systems, 4) platform-based ground-truth systems, 5) physically sensed ground-truth systems, and 6) optically based motion capture ground-truth systems. We discuss previous efforts and discuss the different physical quantities used for ground-truth systems. At this point there does not seem to be solid, universal solutions to ground truth for human and object detection and tracking. There are a number of partial solutions suitable for particular applications, with varying drawbacks

Citation

NIST Interagency/Internal Report (NISTIR) - 7923

Report Number

7923

NIST Pub Series

NIST Interagency/Internal Report (NISTIR)

Pub Type

NIST Pubs

Download Paper

https://doi.org/10.6028/NIST.IR.7923

Local Download

Keywords

pose estimation, Ground truth, object recognition, object tracking

Citation

Godil, A. , Eastman, R. and Hong, T. (2013), Ground Truth Systems for Object Recognition and Tracking, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.IR.7923, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=913121 (Accessed October 8, 2025)