1 / 17

Video-Based Behavior Analysis for ADHD Diagnosis in Children

Feasibility study on ADHD indicators modeling through Dynamic Time Warping from RGB data, focusing on inattention, hyperactivity, and impulsivity in children aged 8-11. The methodology includes data acquisition via Microsoft's Kinect, feature extraction of human pose, and gesture detection using DTW algorithm. Results and conclusions drawn from gesture segmentation and recognition support the feasibility of the approach. Future work involves automatic calibration and feature weighting.

kuper
Télécharger la présentation

Video-Based Behavior Analysis for ADHD Diagnosis in Children

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. ADHD indicatorsmodellingbasedonDynamic Time Warpingfrom RGB data: A feasibilitystudy Antonio Hernández-Vela, Miguel Reyes, Laura Igual, Josep Moya, Verónica Violant, and Sergio Escalera

  2. ADHD: Attentiondeficithyperactivitydisorder Inattention Hyperactivity Impulsivity

  3. Outline • Introduction • Methodology • Results • Conclusion

  4. Introduction • Video-based behavior analysis for ADHD diagnosis in children between 8-11 years.

  5. Introduction • Behavior analysis  Human pose information along time Inattention Head Body Hands time Hyperactivity Gestures Impulsivity 2. Featureextraction: Human Pose 1. Data acquisition 3. Gesturedetection

  6. Outline • Introduction • Methodology • Data acquisition • Featureextraction • Gesturedetection • Results • Conclusion

  7. Data aqcuisition • Microsoft’s Kinect • Invariant to color, texture and lighting conditions • Human pose directly obtained • RGB + Depth

  8. Featureextraction: Human Pose • Body skeleton • 42-dimensional vector: 14 joints × 3 spatial dimensions • RGB + Depth

  9. Gesturedetection • Dynamic Time Warping (DTW)

  10. Thresholdcomputing • G11 Different samples • Leave-one-outsimilarity measure between different samples and gestures Differentgestures

  11. Outline • Introduction • Methodology • Results • Conclusion

  12. Results

  13. Results

  14. Outline • Introduction • Methodology • Results • Conclusion

  15. Outline • Introduction • Methodology • Results • Conclusion

  16. Conclusion • Methodologyforgesturesegmentation and recognition at thesame time. • Firstresultsindicatetheobjectives are feasible. • Futurework: • Automaticcallibration • Featureweighting (bodyjoints)

  17. ThankYou! ADHD indicatorsmodellingbasedonDynamic Time Warpingfrom RGB data: A feasibilitystudy Antonio Hernández-Vela, Miguel Reyes, Laura Igual, Josep Moya, Verónica Violant, and Sergio Escalera Questions?

More Related