|Deep learning has become the state of the art in many computer vision tasks, such as place recognition, localization, image segmentation and classification, etc.|
In our research, we focuses on the following topics:
Deep Image Enhancement for VO in HDR Environments: In One of the main open challenges in visual odometry (VO) is the robustness to difficult illumination conditions or high dynamic range (HDR) environments. We address this problem from a deep learning perspective, for which we propose two different deep networks: a very deep model consisting of both CNNs and LSTM, and another one of small size capable of executing in real-time on a GPU. Both networks transform a sequence of RGB images into more informative ones, while also being robust to changes in illumination, exposure time, gamma correction, etc. We validate the enhanced representations by evaluating the sequences produced by the two architectures in several state-of-art VO algorithms, such as ORB-SLAM and DSO.
Arxiv draft: https://arxiv.org/abs/1707.01274
Deep Place Recognition: Place recognition is still an open problem in computer vision, and its difficulty increases under changes in the scenario, viewpoint, illumination or weather condition. We propose a Convolutional Neural Network (CNN) with the purpose of recognize the same location under severe weather or illumination variations, seasonal changes, etc. In contrast to previous approaches which rely on visual descriptors, our algorithm works with the complete image, reducing unnecessary errors induced by posterior feature matching processes by providing a better estimate of place similarity.