fast prototyping of embedded image processing application
play

FAST PROTOTYPING OF EMBEDDED IMAGE PROCESSING APPLICATION ON - PowerPoint PPT Presentation

FAST PROTOTYPING OF EMBEDDED IMAGE PROCESSING APPLICATION ON HOMOGENOUS SYSTEM


  1. FAST PROTOTYPING OF EMBEDDED IMAGE PROCESSING APPLICATION ON HOMOGENOUS SYSTEM ���������������������������������������������������������� ������������������������������������������������ ������ Hanen Chenini, Loïc Sieler, Mohamed Amine Boussadi, Thierry Tixier, Jean-Pierre Dérutin, Alexis Landrault and Romuald Aufrére 1

  2. 1. Context 2. Real time parallel implementation on SoPC (System on Programmable Chip) ` 3. Model-driven approach for real-time road recognition 4. Experiments && Conclusion 2

  3. ` 3

  4. 1. Context ��������������������� � CMOS imager � Embedded treatment � SoC approach �������������������� �������������������� ` 4

  5. 1. Context �������� �������� ����������� ����������� �������������������������� ������� ������� ����������������������� ���� ���������� �������� ` ����������������������������� �������������������� ���� ����������������������� �� ������������������������ ��� �������� ����! �� �� ��� ����������� !���"����!���� �� ���#� 5

  6. ` 6

  7. 2. Real time parallel implementation on SoPC (System on Programmable Chip) � Homogeneous Network of Communicating Processors on SoPC. hardware hardware � The generic architecture model Number of Routeur Routeur links=dimension of chosen is the type MIMDDM. HyperCube µBlaze µBlaze Mem Mem Soft Core Soft Core � The static topology choice is the hypercube . ` � This parametrizable architecture is regular and homogeneous. � Direct point to point links and the other using a hardware router. � Parametrization of the HNCP via the CubeGen Framework (dimension, communication ,Size of memory, Configurations of softcore…). 7

  8. 2. Real time parallel implementation on SoPC (System on Programmable Chip) �����#������� ������%���&� ������ ��$������� ��#������ �������� ������������ �+������� #��������� ��%�*�� �������� ���#������# �-��� ���������� ��%���'����������������� ` ,��� ���������,� ����������� �'������� *�� ISE/EDK ����������(�)��� ����� �� ����� 8

  9. ` 9

  10. ` 10

  11. 3. Model-driven approach for real-time road recognition ������ ` The steps contained in our proposed recognition process are : � Learning phase � Recognition phase. 11

  12. 3. Model-driven approach for real-time road recognition This method is based on recursive recognition driven by a probabilistic model of the road edges in the image. � The model used is based on image data and camera parameters. � Our statistical model is composed of n image parameters. � This model is represented by a vector and its covariance matrix : ` 12

  13. 3. Model-driven approach for real-time road recognition ` 13

  14. 3. Model-driven approach for real-time road recognition � � � � � RoI RoI Regions of Regions of Interest Interest Hypothesis 1 Hypothesis 2 Hypothesis 3 1 ` 2 3 2 3 4 3 4 5 4 5 1 5 1 2 Score of Score of Score of 14 recognition 3 recognition 1 recognition 2

  15. 3. Model-driven approach for real-time road recognition Learning phase Definition of the best interest zone Detection step ` NO Detection? YES Updating Road Recognition 15

  16. ` 16

  17. ` 17

  18. ` 18

  19. ` 19

  20. Road recognition Demo ` 20

  21. � Some research of Institut Pascal groups focus their work in development of autonomous robot navigation. � As a consequence, we propose : ����������������������������������������������� o �������������������������������������������������������������������������������� o ����������� ����������������������������������������������� o ` ������������������������������������������������ !�"#$�������%&'���������������������( o 21

  22. ` 22

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