Bayesian Viewpoint-Dependent Robust Classification Under Model and Localization Uncertainty

We propose an algorithm for robust visual classification of an object of interest observed from multiple views using a black-box Bayesian classifier which provides a measure of uncertainty, in the presence of significant ambiguity and classifier noise, and of localization error. The fusion of classifier outputs takes into account viewpoint dependency and spatial correlation among observations, as well as pose uncertainty when these observations are taken and a measure of confidence provided by the classifier itself. Our experiments confirm an improvement in robustness over state-of-the-art.

[1]  Jonathan P. How,et al.  SLAM with objects using a nonparametric pose graph , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  Jonathan P. How,et al.  Hierarchical Bayesian Noise Inference for Robust Real-time Probabilistic Object Classification , 2016, ArXiv.

[3]  Roberto Cipolla,et al.  Modelling uncertainty in deep learning for camera relocalization , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Alex Kendall,et al.  What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? , 2017, NIPS.

[5]  Yarin Gal,et al.  Uncertainty in Deep Learning , 2016 .

[6]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[7]  John J. Leonard,et al.  Monocular SLAM Supported Object Recognition , 2015, Robotics: Science and Systems.

[8]  Jean-Claude Latombe,et al.  Appearance-based motion strategies for object detection , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Jean-Claude Latombe,et al.  Reliable confirmation of an object identity by a mobile robot: A mixed appearance/localization-driven motion approach , 2016, Int. J. Robotics Res..

[10]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[11]  Simon Julier,et al.  Posterior distribution analysis for Bayesian inference in neural networks , 2016 .

[12]  Markus Vincze,et al.  Viewpoint Evaluation for Online 3-D Active Object Classification , 2016, IEEE Robotics and Automation Letters.

[13]  Lior Wolf,et al.  Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Albert S. Huang,et al.  Modelling Observation Correlations for Active Exploration and Robust Object Detection , 2012, J. Artif. Intell. Res..

[15]  Nicholas R. Jennings,et al.  Observation Modelling for Vision-Based Target Search by Unmanned Aerial Vehicles , 2015, AAMAS.

[16]  George J. Pappas,et al.  Nonmyopic View Planning for Active Object Classification and Pose Estimation , 2014, IEEE Transactions on Robotics.

[17]  Zoubin Ghahramani,et al.  Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference , 2015, ArXiv.

[18]  Frank Dellaert,et al.  iSAM2: Incremental smoothing and mapping using the Bayes tree , 2012, Int. J. Robotics Res..

[19]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.