LIDAR semantic segmentation is an essential task that provides 3D semantic information about the environment to robots. Fast and efficient semantic segmentation methods are needed to match the strong computational and temporal restrictions of many real-world robotic applications. This work presents 3D-MiniNet, a novel approach for LIDAR semantic segmentation that combines 3D and 2D learning layers. It first learns a 2D representation from the raw points through a novel projection which extracts local and global information from the 3D data. This representation is fed to an efficient 2D Fully Convolutional Neural Network (FCNN) that produces a 2D semantic segmentation. These 2D semantic labels are re-projected back to the 3D space and enhanced through a post-processing module. The main novelty in our strategy relies on the projection learning module. Our detailed ablation study shows how each component contributes to the final performance of 3D-MiniNet. We validate our approach on well known public benchmarks (SemanticKITTI and KITTI), where 3D-MiniNet gets state-of-the-art results while being faster and more parameter-efficient than previous methods.

Many robotic applications work with visual reference maps, which usually consist of sets of more or less organized images. In these applications, there is a compromise between the density of reference data stored and the capacity to identify later the robot localization, when it is not exactly in the same position as one of the reference views. Here we propose the use of a recently developed feature, SURF, to improve the performance of appearance-based localization methods that perform image retrieval in large data sets. This feature is integrated with a vision-based algorithm that allows both topological and metric localization using omnidirectional images in a hierarchical approach. It uses pyramidal kernels for the topological localization and three-view geometric constraints for the metric one. Experiments with several omnidirectional images sets are shown, including comparisons with other typically used features (radial lines and SIFT). The advantages of this approach are proved, showing the use of SURF as the best compromise between efficiency and accuracy in the results.

Computer-assisted systems are becoming broadly used in medicine. In endoscopy, most research focuses on the automatic detection of polyps or other pathologies, but localization and navigation of the endoscope are completely performed manually by physicians. To broaden this research and bring spatial Artificial Intelligence to endoscopies, data from complete procedures is needed. This paper introduces the Endomapper dataset, the first collection of complete endoscopy sequences acquired during regular medical practice, making secondary use of medical data. Its main purpose is to facilitate the development and evaluation of Visual Simultaneous Localization and Mapping (VSLAM) methods in real endoscopy data. The dataset contains more than 24 hours of video. It is the first endoscopic dataset that includes endoscope calibration as well as the original calibration videos. Meta-data and annotations associated with the dataset vary from the anatomical landmarks, procedure labeling, segmentations, reconstructions, simulated sequences with ground truth and same patient procedures. The software used in this paper is publicly available.

Vision-based topological localization and mapping for autonomous robotic systems have received increased research interest in recent years. The need to map larger environments requires models at different levels of abstraction and additional abilities to deal with large amounts of data efficiently. Most successful approaches for appearance-based localization and mapping with large datasets typically represent locations using local image features. We study the feasibility of performing these tasks in urban environments using global descriptors instead and taking advantage of the increasingly common panoramic datasets. This paper describes how to represent a panorama using the global gist descriptor, while maintaining desirable invariance properties for location recognition and loop detection. We propose different gist similarity measures and algorithms for appearance-based localization and an online loop-closure detection method, where the probability of loop closure is determined in a Bayesian filtering framework using the proposed image representation. The extensive experimental validation in this paper shows that their performance in urban environments is comparable with local-feature-based approaches when using wide field-of-view images.

Efficient models for semantic segmentation, in terms of memory, speed, and computation, could boost many robotic applications with strong computational and temporal restrictions. This article presents a detailed analysis of different techniques for efficient semantic segmentation. Following this analysis, we have developed a novel architecture, MiniNet-v2, an enhanced version of MiniNet. MiniNet-v2 is built considering the best option depending on CPU or GPU availability. It reaches comparable accuracy to the state-of-the-art models but uses less memory and computational resources. We validate and analyze the details of our architecture through a comprehensive set of experiments on public benchmarks (Cityscapes, Camvid, and COCO-Text datasets), showing its benefits over relevant prior work. Our experiments include a sample application where these models can boost existing robotic applications.