Single-View Place Recognition under Seasonal Changes

Single-view place recognition, that we can define as finding an image that corresponds to the same place as a given query image, is a key capability for autonomous navigation and mapping. Although there has been a considerable amount of research in the topic, the high degree of image variability (with viewpoint, illumination or occlusions for example) makes it a research challenge. One of the particular challenges, that we address in this work, is weather variation. Seasonal changes can produce drastic appearance changes, that classic low-level features do not model properly. Our contributions in this paper are twofold. First we pre-process and propose a partition for the Nordland dataset, frequently used for place recognition research without consensus on the partitions. And second, we evaluate several neural network architectures such as pre-trained, siamese and triplet for this problem. Our best results outperform the state of the art of the field. A video showing our results can be found in this https URL. The partitioned version of the Nordland dataset at this http URL.

[1]  Vincent Lepetit,et al.  TILDE: A Temporally Invariant Learned DEtector , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Dorian Gálvez-López,et al.  Bags of Binary Words for Fast Place Recognition in Image Sequences , 2012, IEEE Transactions on Robotics.

[3]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[4]  Francesc Moreno-Noguer,et al.  DaLI: Deformation and Light Invariant Descriptor , 2015, International Journal of Computer Vision.

[5]  Michael Milford,et al.  Deep learning features at scale for visual place recognition , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[6]  Jana Kosecka,et al.  Localization in Urban Environments Using a Panoramic Gist Descriptor , 2013, IEEE Transactions on Robotics.

[7]  Paul Newman,et al.  FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance , 2008, Int. J. Robotics Res..

[8]  Javier González,et al.  Training a Convolutional Neural Network for Appearance-Invariant Place Recognition , 2015, ArXiv.

[9]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[10]  Michael Bosse,et al.  The gist of maps - summarizing experience for lifelong localization , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Vincent Lepetit,et al.  Learning descriptors for object recognition and 3D pose estimation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Peer Neubert,et al.  Local region detector + CNN based landmarks for practical place recognition in changing environments , 2015, 2015 European Conference on Mobile Robots (ECMR).

[13]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[14]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[15]  Niko Sünderhauf,et al.  On the performance of ConvNet features for place recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[16]  Cédric Pradalier,et al.  Evaluation of Off-The-Shelf CNNs for the Representation of Natural Scenes with Large Seasonal Variations , 2017 .

[17]  Michael Milford,et al.  Supervised and Unsupervised Linear Learning Techniques for Visual Place Recognition in Changing Environments , 2016, IEEE Transactions on Robotics.

[18]  Alberto Ortiz,et al.  Hierarchical Place Recognition for Topological Mapping , 2017, IEEE Transactions on Robotics.

[19]  Niko Sünderhauf,et al.  BRIEF-Gist - closing the loop by simple means , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.