Deep Learning Based Place Recognition for Challenging Environments

Visual based place recognition involves recognising familiar locations despite changes in environment or view-point of the camera(s) at the locations. There are existing methods that deal with these seasonal changes or view-point changes separately, but few methods exist that deal with these kind of changes simultaneously. Such robust place recognition systems are essential to long term localization and autonomy. Such systems should be able to deal both with conditional and viewpoint changes simultaneously. In recent times Convolutional Neural Networks (CNNs) have shown to outperform other state-of-the art method in task related to classification and recognition including place recognition. In this thesis, we present a deep learning based planar omni-directional place recognition approach that can deal with conditional and viewpoint variations together. The proposed method is able to deal with large viewpoint changes, where current methods fail. We evaluate the proposed method on two real world datasets dealing with four different seasons through out the year along with illumination changes and changes occurred in the environment across a period of 1 year respectively. We provide both quantitative (recall at 100% precision) and qualitative (confusion matrices) comparison of the basic pipeline for place recognition for the omni-directional approach with single-view and side-view camera approaches. The proposed approach is also shown to work very well across different seasons. The results prove the efficacy of the proposed method over the single-view and side-view cameras in dealing with conditional and large viewpoint changes in different conditions including illumination, weather, structural changes etc.