Online human-assisted learning using Random Ferns

We present an Online Random Ferns (ORFs) classifier that progressively learns and builds enhanced models of object appearances. During the learning process, we allow the human intervention to assist the classifier and discard false positive training samples. The amount of human intervention is minimized and integrated within the online learning, such that in a few seconds, complex object appearances can be learned. After the assisted learning stage, the classifier is able to detect the object under severe changing conditions. The system runs at a few frames per second, and has been validated for face and object detection tasks on a mobile robot platform. We show that with minimal human assistance we are able to build a detector robust to viewpoint changes, partial occlusions, varying lighting and cluttered backgrounds.

[1]  D. Feil-Seifer,et al.  Defining socially assistive robotics , 2005, 9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005..

[2]  Francesc Moreno-Noguer,et al.  Discrete time motion model for guiding people in urban areas using multiple robots , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Francesc Moreno-Noguer,et al.  Shared Random Ferns for Efficient Detection of Multiple Categories , 2010, 2010 20th International Conference on Pattern Recognition.

[4]  Francesc Moreno-Noguer,et al.  Dependent Multiple Cue Integration for Robust Tracking , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Francesc Moreno-Noguer,et al.  Efficient 3D Object Detection using Multiple Pose-Specific Classifiers , 2011, BMVC.

[6]  Vincent Lepetit,et al.  Fast Keypoint Recognition Using Random Ferns , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Francesc Moreno-Noguer,et al.  Bootstrapping Boosted Random Ferns for discriminative and efficient object classification , 2012, Pattern Recognit..

[8]  Kazuhiko Kawamura,et al.  HuDL, A Design Philosophy for Socially Intelligent Service Robots , 1997 .

[9]  Luc Van Gool,et al.  On-line Adaption of Class-specific Codebooks for Instance Tracking , 2010, BMVC.

[10]  Jiri Matas,et al.  P-N learning: Bootstrapping binary classifiers by structural constraints , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  David A. McAllester,et al.  Cascade object detection with deformable part models , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Francesc Moreno-Noguer,et al.  Integration of conditionally dependent object features for robust figure/background segmentation , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Heiko Wersing,et al.  Active 3D Object Localization Using a Humanoid Robot , 2011, IEEE Transactions on Robotics.

[14]  Francesc Moreno-Noguer,et al.  Efficient rotation invariant object detection using boosted Random Ferns , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Horst Bischof,et al.  On-line Boosting and Vision , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Horst Bischof,et al.  On-Line Random Naive Bayes for Tracking , 2010, 2010 20th International Conference on Pattern Recognition.

[17]  Christoph H. Lampert,et al.  Beyond sliding windows: Object localization by efficient subwindow search , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.