sensitivity evaluation of embedded code detection in
play

Sensitivity Evaluation of Embedded Code Detection in Imperceptible - PowerPoint PPT Presentation

Sensitivity Evaluation of Embedded Code Detection in Imperceptible Structured Light Sensing Jingwen Dai Ronald Chung Computer Vision Laboratory Dept. of Mech. and Automation Engineering The Chinese University of Hong Kong WoRV2013, Clearwater,


  1. Sensitivity Evaluation of Embedded Code Detection in Imperceptible Structured Light Sensing Jingwen Dai Ronald Chung Computer Vision Laboratory Dept. of Mech. and Automation Engineering The Chinese University of Hong Kong WoRV2013, Clearwater, FL, USA, 16 Jan 2013

  2. Introduction & Motivation  Projector ‐ Camera Systems in Robotics  Augmented Reality  Human ‐ Robot Interaction  Some Other Applications  Imperceptible Structured Light Sensing (ISL) Display Device Show Video Content 3D Sensor Derive the 3D information 01/16/2013 2 WoRV2013

  3. Introduction & Motivation J. Dai and R. Chung, On Making Projector both a Display Device and a 3D Sensor, In Proc. of ISVC12, pages 654 ‐ 664, 2012. Coding  specifically designed shapes  large hamming distance Decoding  Pre ‐ trained shape detector 01/16/2013 3 WoRV2013

  4. Robotic Applications – Sensing Surrounding Environment J. Dai and R. Chung, Embedding Imperceptible Codes into Video Projection and Applications in Robotics, In Proc. of IROS12, pages 4399 ‐ 4404, 2012. 01/16/2013 4 WoRV2013

  5. Robotic Applications – Natural Human ‐ Robot Interaction J. Dai and R. Chung, Embedding Imperceptible Codes into Video Projection and Applications in Robotics, In Proc. of IROS12, pages 4399 ‐ 4404, 2012. 01/16/2013 5 WoRV2013

  6. Sensitivity Evaluation Scenarios Training Operation Stage Stage Differences Sensor ‐ Object Localization Projection Surfaces Surrounding Environment Hardware Platforms 01/16/2013 6 WoRV2013

  7. System Setup PROCAMS‐B PROCAMS‐A 01/16/2013 7 WoRV2013

  8. Hardware Configuration PROCAMS ‐ A PROCAMS ‐ B Projector Mitsubishi EX240U Projector TI DLP Pico Projector Development Kit 2 1024 * 768 640 * 480 Camera Point Grey Flea3 FL3‐U3‐13S2C Point Grey Flea3 FL3‐FW‐03S1C 1328 * 1048@120fps 648 * 488@120fps Lens Myutron FV1520 f15mm Myutron FV0622 f6mm lens Pro ‐ PC VGA HDMI Cam ‐ PC IEEE‐1394 USB 3.0 01/16/2013 8 WoRV2013

  9. Benchmark Training Sample Collection Scenario Distance 800mm 500mm 1200mm 1600mm 0 ° 10 ° 20 ° 30 ° 40 ° 50 ° Orientation Shape Planar Convex Concave Free‐Form Texture White Green Cork Poster PROCAMS A B When the scenarios of training stage and operation stage are almost the same , about 95% primitive shapes can be detected and identified correctly. 01/16/2013 9 WoRV2013

  10. In training data collection: Sensitivity Evaluation: Working Distance: 800mm Working Distance 500mm 1200mm 1600mm 01/16/2013 10 WoRV2013

  11. In training data collection: Sensitivity Evaluation: Surface Orientation: θ � 0 ° Projection Surface Orientation � � �� ° � � �� ° � � �� ° � � �� ° � � �� ° 01/16/2013 11 WoRV2013

  12. In training data collection: Sensitivity Evaluation: Projection Surface: Planar Projection Surface Shape Convex Surface Concave Surface Plaster Statue 01/16/2013 12 WoRV2013

  13. In training data collection: Sensitivity Evaluation: Surface Texture: White Paper Projection Surface Texture Green Paper Cork Board Poster 01/16/2013 13 WoRV2013

  14. In training data collection: Sensitivity Evaluation: PROCAMS: PROCAMS‐A PROCAMS Captured Image Cropped Patt. Resized Patt. 01/16/2013 14 WoRV2013

  15. Sensitivity Evaluation: Conclusion Condition Hits (%) Missed (%) False (%) Ed (pixel) Benchmark 94.53 3.95 1.52 1.632 Distance 86.21 11.63 2.16 1.814 (500mm) Orientation 85.91 12.03 2.06 2.728 (50 degree) Surface 84.81 13.33 1.86 2.028 (Plaster Statue) Texture 91.74 6.63 1.63 2.024 (Poster) PROCAMS 80.23 14.43 5.34 3.028 (Cropped Pattern) For more detailed sensitivity evaluation results, please refer to the paper 01/16/2013 15 WoRV2013

  16. Conclusion and Future Works Sensitivity evaluation of embedded code detection in imperceptible structured light sensing. Distance Surface PROCAMS Orientation Surface Surface Texture Shape Future Works  Extending imperceptible structured light sensing to a variety of robotic applications. 01/16/2013 16 WoRV2013

  17. THANK YOU!! If you have any questions, please contact Dr. Jingwen Dai dai@cs.unc.edu 01/16/2013 17 WoRV2013

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend