Multi-camera Finger Tracking and 3D Trajectory Reconstruction for HCI Studies

@inproceedings{Lyubanenko2017MulticameraFT,
  title={Multi-camera Finger Tracking and 3D Trajectory Reconstruction for HCI Studies},
  author={Vadim Lyubanenko and Toni Kuronen and Tuomas Eerola and Lasse Lensu and Heikki K{\"a}lvi{\"a}inen and Jukka H{\"a}kkinen},
  booktitle={ACIVS},
  year={2017}
}
Three-dimensional human-computer interaction has the potential to form the next generation of user interfaces and to replace the current 2D touch displays. To study and to develop such user interfaces, it is essential to be able to measure how a human behaves while interacting with them. In practice, this can be achieved by accurately measuring hand movements in 3D by using a camera-based system and computer vision. In this work, a framework for multi-camera finger movement measurements in 3D… 

3D Hand Movement Measurement Framework for Studying Human-Computer Interaction

This paper proposes a complete framework to measure hand movements in 3D in human-computer interaction situations and demonstrates the framework in a context where 3D touch screen usability is studied with 3D stimuli.

Two-Camera Synchronization and Trajectory Reconstruction for a Touch Screen Usability Experiment

A method for automatic video synchronization for the two cameras to enable 3D trajectory reconstruction and proper finger tracking and trajectory processing techniques form a fully automated measurement framework for hand movements, which can be utilized in other similar HCI studies.

A Method for Measuring Contact Points in Human–Object Interaction Utilizing Infrared Cameras

A novel method for measuring contact points in human–object interaction that solves the occlusion problem by exploiting thermal energy transfer from the subject’s hand to the object surface during interaction and is extendable to measuring surface contact areas, or patches, instead of contact points.

Corrective Filter Based on Kinematics of Human Hand for Pose Estimation

A novel “anatomical filter” that accepts a hand pose from a hand tracker and generates the closest possible pose within the real human hand’s anatomical bounds, achieves the lowest prediction error when used with state-of-the-art trackers at 10% correction.

Single Shot Corrective CNN for Anatomically Correct 3D Hand Pose Estimation

The Single Shot Corrective CNN (SSC-CNN) is presented to tackle the problem of enforcing anatomical correctness at the architecture level and shows zero anatomical errors along with comparable accuracy to the state-of-the-art models as measured by the ground truth pose.

References

SHOWING 1-10 OF 33 REFERENCES

High-Speed Hand Tracking for Studying Human-Computer Interaction

Experimental results showed that Kernelized Correlation Filters and Spatio-Temporal Context Learning tracking were the best tracking methods obtaining reasonable accuracy and high processing speed while Local Regression filtering and Unscented Kalman Smoother were the most suitable filtering techniques.

Vision-based hand pose estimation: A review

Comparison of General Object Trackers for Hand Tracking in High-Speed Videos

This work provides the first solid comparison of state-of-the-art general object trackers on hand tracking with a primary focus on grey-scale high-speed videos.

Estimating uncertainty in SSD-based feature tracking

Performance measures for video object segmentation and tracking

Measurements to evaluate quantitatively the performance of video object segmentation and tracking methods without ground-truth (GT) segmentation maps based on spatial differences of color and motion along the boundary of the estimated video object plane.

Good features to track

  • Jianbo ShiCarlo Tomasi
  • Computer Science
    1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
  • 1994
A feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world are proposed.

Touching the void: direct-touch interaction for intangible displays

The challenges in applying and investigate methodologies to improve direct-touch interaction on intangible displays are explored, and the pseudo-shadow visual feedback was shown to be helpful both in improving user performance and satisfaction.

Real-time tracking of non-rigid objects using mean shift

The theoretical analysis of the approach shows that it relates to the Bayesian framework while providing a practical, fast and efficient solution for real time tracking of non-rigid objects seen from a moving camera.

The Visual Object Tracking VOT2016 Challenge Results

The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.

Incremental Learning for Robust Visual Tracking

A tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target, and includes a method for correctly updating the sample mean and a forgetting factor to ensure less modeling power is expended fitting older observations.