3D Ground-Truth Systems for Object/Human Recognition and Tracking

Godil, Afzal; Bostelman, Roger V.; Saidi, Kamel S.; Shackleford, Will; Cheok, Geraldine S.; Shneier, Michael O.; Hong, Tsai Hong

doi:10.1109/cvprw.2013.109

Cited by 8 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Godil, et al [24], describe four types of ground truth data for object detection and tracking: annotation/label-based systems that rely on humans to outline regions in the data, fixture-based systems that use physical positioning constraints to locate items precisely, physics-based simulations that depend on models of the objects and their locations in the world, and sensorbased systems that use independent means to sense the world and locate the objects, ideally much more precisely than the system being evaluated. This report adopts the last of these methods, making use of two sensor-based ground truth systems, described in the following subsections.…”

Section: Measuring Ground Truthmentioning

confidence: 99%

Performance Evaluation Methods for Human Detection and Tracking Systems for Robotic Applications

Shneier¹,

Hong²,

Cheok³

et al. 2014

Self Cite

View full text Add to dashboard Cite

Detecting and tracking people is becoming more important in robotic applications because of the increasing demand for collaborative work in which people interact closely with and in the same workspace as robots. New safety standards allow people to work next to robots but require that they be protected from harm while they do so. Sensors that detect and track people are a natural way of implementing the necessary safety monitoring and have the added advantage that the information about where the people are and where they are going can be fed back into the application and used to give the robot greater situational awareness. This report describes work on defining and testing performance evaluation measures that provide quantitative information about how well a human detection and tracking system performs. The results should help users determine if such a system will provide sufficient protection for people to be able to work safely in collaborative applications with industrial robots.

show abstract

Section: Measuring Ground Truthmentioning

confidence: 99%

Performance Evaluation Methods for Human Detection and Tracking Systems for Robotic Applications

Shneier¹,

Hong²,

Cheok³

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…Reference [5,6] identifed Indoor Global Positioning System (iGPS) (see also Refs. [31][32][33][34]), laser trackers, and laser tracers as systems that could be applied to mobile manipulators for large-scale manufacturing scenarios to improve pose accuracy. Laser occlusion, linear error (in the case of laser trackers), and limited measurement DoF were identifed as potential challenges for such solutions [5,6].…”

Section: Introductionmentioning

confidence: 99%

Design and implementation of a closed-loop mobile manipulator control system

Aboul-Enein

2023

View full text Add to dashboard Cite

Mobile manipulators, which integrate a robotic manipulator with an automatic-autonomous mobile base, have the potential to augment automation by combining the capability of navigation with complex manipulation to support unstructured and dynamic environments. Targeted applications include manufacturing large-scale parts commonly encountered in the aerospace, energy, shipbuilding, and transportation sectors. While autonomous mobility no longer restricts the robotic manipulator to working at a single, rigidly fixtured workstation or work-piece, the increased flexibility introduces new sources of position and orientation uncertainty, and manufacturing processes of large-scale parts with complex, curved surfaces require high repeatability and accuracy. A standardized measurement methodology, including a configurable measurement artifact to simulate dynamic manufacturing operations, is being developed to identify and evaluate these sources of performance uncertainty. As part of this methodology and associated test methods development, this work details the design and prototype implementation of a closed-loop mobile manipulator control system that integrates feedback from an optical tracking system. Development of the control system presents a new test implementation to demonstrate the performance evaluation of mobile manipulation performance in application scenarios where the workstation or work-piece is physically disturbed during operation or where rapid registration between distant locations along the same work-piece is required. This work will promote advances in control scheme development by providing a standardized, reproducible test method for evaluation in a variety of simulated application spaces.

show abstract

“…The results can be used to develop new standards that will help enable the use of perception systems in manufacturing applications. Our previous efforts are reported in [24] [25].…”

Section: Introductionmentioning

confidence: 99%

“…In most previous work, the ground-truth was created in the sensor coordinate system by manually annotating the objects, for example by drawing a bounding box around each object in a sequence of images. In our case the 3D ground-truth is captured in world coordinates with the help of a tracking sensor (for more details, see [24] [25]). In the annotation-based case, matches are evaluated using the area of intersection of bounding boxes in the ground truth data and data from the system being evaluated.…”

Section: Introductionmentioning

confidence: 99%