Active Random Forests: An Application to Autonomous Unfolding of Clothes
Abstract
We present Active Random Forests, a novel framework to address active vision problems. State of the art focuses on best viewing parameters selection based on single view classifiers. We propose a multi-view classifier where the decision mechanism of optimally changing viewing parameters is inherent to the classification process. This has many advantages: a) the classifier exploits the entire set of captured images and does not simply aggregate probabilistically per view hypotheses; b) actions are based on learnt disambiguating features from all views and are optimally selected using the powerful voting scheme of Random Forests and c) the classifier can take into account the costs of actions. The proposed framework is applied to the task of autonomously unfolding clothes by a robot, addressing the problem of best viewpoint selection in classification, grasp point and pose estimation of garments. We show great performance improvement compared to state of the art methods.
Keywords
Active Vision Active Random Forests Deformable Object Recognition Robotic VisionSupplementary material
References
- 1.Arble, T., Ferrie, F.P.: Viewpoint selection by navigation through entropy maps. In: ICCV (1999)Google Scholar
- 2.Arble, T., Ferrie, F.P.: On the sequential accumulation of evidence. IJCV (2001)Google Scholar
- 3.Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
- 4.Callari, F.G., Ferrie, F.P.: Recognizing large 3-d objects through next view planning using an uncalibrated camera. In: ICCV (2001)Google Scholar
- 5.Criminisi, A.: Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and Trends in Computer Graphics and Vision 7(2-3), 81–227 (2011)Google Scholar
- 6.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 1, pp. 886–893 (2005)Google Scholar
- 7.Denzler, J., Brown, C.M.: Information theoretic sensor data selection for active object recognition and state estimation. PAMI (2002)Google Scholar
- 8.Doumanoglou, A., Kargakos, A., Kim, T.K., Malassiotis, S.: Autonomous active recognition and unfolding of clothes using random decision forests and probabilistic planning. In: ICRA (2014)Google Scholar
- 9.Girshick, R., Shotton, J., Kohli, P., Criminisi, A., Fitzgibbon, A.: Efficient regression of general-activity human poses from depth images. In: ICCV (2011)Google Scholar
- 10.Guo, G., Fu, Y., Dyer, C.R., Huang, T.S.: Head pose estimation: Classification or regression? In: ICPR (2008)Google Scholar
- 11.Hastie, T., Tibshirani, R., Friedman, J., Hastie, T., Friedman, J., Tibshirani, R.: The elements of statistical learning, vol. 2. Springer, Heidelberg (2009)CrossRefzbMATHGoogle Scholar
- 12.Jia, Z., Chang, Y.-J., Chen, T.: A general boosting-based framework for active object recognition. In: BMVC (2010)Google Scholar
- 13.Laporte, C., Arbel, T.: Efficient discriminant viewpoint selection for active bayesian recognition. IJCV (2006)Google Scholar
- 14.Meger, D., Gupta, A., Little, J.J.: Viewpoint detection models for sequential embodied object category recognition. In: ICRA (2010)Google Scholar
- 15.Ozuysa, M., Lepetit, V., Fua, P.: Pose estimation for category specific multiview object localization. In: CVPR (2009)Google Scholar
- 16.Pardo, L.: Statistical inference based on divergence measures. CRC Press (2005)Google Scholar
- 17.Rasolzadeh, B., Bjorkman, M., Huebner, K., Kragic, D.: An active vision system for detecting, fixating and manipulating objects in the real world. IJRR (2010)Google Scholar
- 18.Schiele, B., Crowley, J.L.: Transinformation for active object recognition. In: ICCV, pp. 249–254 (1998)Google Scholar
- 19.Sipe, M.A., Casasent, D.: Feature space trajectory methods for active computer vision. PAMI (2002)Google Scholar
- 20.Sommerlade, E., Reid, I.: Information-theoretic active scene exploration. In: CVPR (2008)Google Scholar
- 21.Tang, D., Yu, T., Kim, T.K.: Real-time articulated hand pose estimation using semi-supervised transductive regression forests. In: ICCV (2013)Google Scholar
- 22.Vogel, J., de Freitas, N.: Target-directed attention: Sequential decision-making for gaze planning. In: ICRA (2008)Google Scholar
- 23.Welke, K., Issac, J., Schiebener, D., Asfour, T., Dillmann, R.: Autonomous acquisition of visual multi-view object representations for object recognition on a humanoid robot. In: ICRA (2010)Google Scholar
- 24.Zhao, X., Kim, T.K., Luo, W.: Unified face analysis by iterative multi-output random forests. In: CVPR (2014)Google Scholar