Autonomous Learning of Robust Visual Object Detection & Identification on a Humanoid #icdl/epirob2012
0 likes839 views
The document discusses advancements in autonomous learning for robust visual object detection using machine intelligence techniques. It highlights the use of Cartesian Genetic Programming and a combination of salient object detection and rough segmentation for automatic training set generation. The research is developed through collaborations within the robotics community and is exemplified in various publications and projects.
![icImage GreenTeaBoxDetector::runFilter() {
! icImage node0 = InputImages[6];
! icImage node1 = InputImages[1];
! icImage node2 = node0.absdiff(node1);
! icImage node5 = node2.SmoothBilateral(11);
! icImage node12 = InputImages[0];
! icImage node16 = node12.Sqrt();
! icImage node33 = node16.erode(6);
! icImage node34 = node33.log();
! icImage node36 = node34.min(node5);
! icImage node49 = node36.Normalize();
//cleanup
...
icImage out = node49.threshold(230.7218f);
! return out;
}
detection](https://image.slidesharecdn.com/icdl2012-121120075019-phpapp02/85/Autonomous-Learning-of-Robust-Visual-Object-Detection-Identification-on-a-Humanoid-icdl-epirob2012-11-320.jpg)
Autonomous Learning of Robust Visual Object Detection & Identification on a Humanoid #icdl/epirob2012
- 1. Jürgen ’Juxi’ Leitner S. Harding, P. Chandrashekhariah M. Frank, G. Spina, A. Förster, J. Triesch, J. Schmidhuber idsia / usi / supsi, machine intelligence, fias autonomous learning of robust visual object detection & identification on a humanoid #icdl/epirob 2012
- 2. our iCub setup is for manipulation
- 3. thanks to G. Metta and IIT for this picture visual perception
- 5. IDSIA’s three parts Harding et al., GPTP 2012, Leitner et al., IROS 2012 Leitner et al., BICA 2012 Leitner et al., ICDL 2012
- 7. detecting objects Harding et al., GPTP 2012
- 8. our learning approach
- 9. INP INP INP + dilate min avg cartesian genetic programming
- 10. INP INP INP + dilate min avg Func,on" 3" Connec,on"1" "#2" Connec,on"2" A"real"number" "#1" 4.3" cartesian genetic """ " programming
- 11. icImage GreenTeaBoxDetector::runFilter() { ! icImage node0 = InputImages[6]; ! icImage node1 = InputImages[1]; ! icImage node2 = node0.absdiff(node1); ! icImage node5 = node2.SmoothBilateral(11); ! icImage node12 = InputImages[0]; ! icImage node16 = node12.Sqrt(); ! icImage node33 = node16.erode(6); ! icImage node34 = node33.log(); ! icImage node36 = node34.min(node5); ! icImage node49 = node36.Normalize(); //cleanup ... icImage out = node49.threshold(230.7218f); ! return out; } detection
- 12. detect
- 13. detect
- 14. BUT: supervised learning approach
- 15. FIAScollaboration saliency map feature segmentation
- 16. pre segmentation
- 18. MoBeE framework Frank et al., ICINCO, 2012.
- 19. conclusion salient object detection + rough feature-based segmentation = automatic training set generation for cgp-based, robust filter-learning
- 20. thanks for listening juxi@idsia.ch http://Juxi.net/projects http://robotics.idsia.ch video at http://robotics.idsia.ch/im-clever/