We present a novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research. In total, we recorded 6 hours of traffic scenarios at 10-100 Hz using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras, a Velodyne 3D laser scanner and a high-precision GPS/IMU inertial navigation system. The scenarios are diverse, capturing real-world traffic situations, and range from freeways over rural areas to inner-city scenes with many static and dynamic objects. Our data is calibrated, synchronized and timestamped, and we provide the rectified and raw image sequences. Our dataset also contains object labels in the form of 3D tracklets, and we provide online benchmarks for stereo, optical flow, object detection and other tasks. This paper describes our recording platform, the data format and the utilities that we provide.

/pdf/vision-meets-robotics-the-kitti-dataset-2h3kd0lpgn.pdf

Vision meets robotics: The KITTI dataset

Simultaneous Localization and Mapping (SLAM)consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications, and witnessing a steady transition of this technology to industry. We survey the current state of SLAM. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors' take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?

/pdf/past-present-and-future-of-simultaneous-localization-and-dhljw0akg5.pdf

Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age

Visual place recognition is a challenging problem due to the vast range of ways in which the appearance of real-world places can vary. In recent years, improvements in visual sensing capabilities, an ever-increasing focus on long-term mobile robot autonomy, and the ability to draw on state-of-the-art research in other disciplines—particularly recognition in computer vision and animal navigation in neuroscience—have all contributed to significant advances in visual place recognition systems. This paper presents a survey of the visual place recognition research landscape. We start by introducing the concepts behind place recognition—the role of place recognition in the animal kingdom, how a “place” is defined in a robotics context, and the major components of a place recognition system. Long-term robot operations have revealed that changing appearance can be a significant factor in visual place recognition failure; therefore, we discuss how place recognition solutions can implicitly or explicitly account for appearance change within the environment. Finally, we close with a discussion on the future of visual place recognition, in particular with respect to the rapid advances being made in the related fields of deep learning, semantic scene understanding, and video description.

/pdf/visual-place-recognition-a-survey-d2xtkdlp55.pdf

Visual Place Recognition: A Survey

Depth estimation and semantic segmentation are two fundamental problems in image understanding. While the two tasks are strongly correlated and mutually beneficial, they are usually solved separately or sequentially. Motivated by the complementary properties of the two tasks, we propose a unified framework for joint depth and semantic prediction. Given an image, we first use a trained Convolutional Neural Network (CNN) to jointly predict a global layout composed of pixel-wise depth values and semantic labels. By allowing for interactions between the depth and semantic information, the joint network provides more accurate depth prediction than a state-of-the-art CNN trained solely for depth prediction [6]. To further obtain fine-level details, the image is decomposed into local segments for region-level depth and semantic prediction under the guidance of global layout. Utilizing the pixel-wise global prediction and region-wise local prediction, we formulate the inference problem in a two-layer Hierarchical Conditional Random Field (HCRF) to produce the final depth and semantic map. As demonstrated in the experiments, our approach effectively leverages the advantages of both tasks and provides the state-of-the-art results.

/pdf/towards-unified-depth-and-semantic-prediction-from-a-single-1bbyix9kyu.pdf

Towards unified depth and semantic prediction from a single image

In this paper, we present a novel probabilistic generative model for multi-object traffic scene understanding from movable platforms which reasons jointly about the 3D scene layout as well as the location and orientation of objects in the scene. In particular, the scene topology, geometry, and traffic activities are inferred from short video sequences. Inspired by the impressive driving capabilities of humans, our model does not rely on GPS, lidar, or map knowledge. Instead, it takes advantage of a diverse set of visual cues in the form of vehicle tracklets, vanishing points, semantic scene labels, scene flow, and occupancy grids. For each of these cues, we propose likelihood functions that are integrated into a probabilistic generative model. We learn all model parameters from training data using contrastive divergence. Experiments conducted on videos of 113 representative intersections show that our approach successfully infers the correct layout in a variety of very challenging scenarios. To evaluate the importance of each feature cue, experiments using different feature combinations are conducted. Furthermore, we show how by employing context derived from the proposed method we are able to improve over the state-of-the-art in terms of object detection and object orientation estimation in challenging and cluttered urban environments.

/pdf/3d-traffic-scene-understanding-from-movable-platforms-4ao3ufxzw6.pdf

3D Traffic Scene Understanding From Movable Platforms

This paper presents a nonparametric approach to semantic parsing using small patches and simple gradient, color and location features. We learn the relevance of individual feature channels at test time using a locally adaptive distance metric. To further improve the accuracy of the nonparametric approach, we examine the importance of the retrieval set used to compute the nearest neighbours using a novel semantic descriptor to retrieve better candidates. The approach is validated by experiments on several datasets used for semantic parsing demonstrating the superiority of the method compared to the state of art approaches.

/pdf/nonparametric-scene-parsing-with-adaptive-feature-relevance-8upeuecqqd.pdf

Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context

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.

/pdf/localization-in-urban-environments-using-a-panoramic-gist-1k2jpwhlch.pdf

Localization in Urban Environments Using a Panoramic Gist Descriptor

We present an approach for detecting loop clo- sures in a large sequence of omni-directional images of urban environments. In particular we investigate the efficacy of global gist descriptors computed for 360 o cylindrical panoramas and compare it with the baseline vocabulary tree approach. In the context of loop closure detection, we describe a novel matching strategy for panoramic views, exploiting the fact that the vehicle travels in urban environments where heading of the vehicle at previously visited locations and loop closure points are related by multiple of 90 o degrees. The performance of the presented approach is promising despite the simplicity of the descriptor. I. INTRODUCTION The problem of generating metric and/or topological maps from streams of visual data has became in recent years a very active area of research. This increased interest has been to a large extent facilitated by improvements in large scale wide- baseline matching techniques and advances in localization by means place recognition. The problem of localization by means of place recognition, for purely appearance based strategies is typically formulated as an image based retrieval task. Namely given a database of views from certain geo- graphical area, and set of new query views the goal was to determine the closest view from the reference database. The problem of loop closure detection we investigate here is different in its nature in that it explicitly takes into account temporal ordering constraints among the views as opposed to considering the database as unorganized collection of views. The loop closure problem requires determining for two images whether they have been taken from the same place. In principle the problem of loop closure detection can be tackled using the same strategies as those used in location recognition. Namely given n views of the video sequences, loops are hypothesized by comparing all views to all other views. The efficiency and scalability of the existing strategies depends on chosen image representation and the selected similarity measure. In this paper we investigate the suitability of the global gist descriptor as image representation and pro- posed a novel image panorama similarity measure between two views, which exploits the Manhattan world assumption stating that the vehicle heading at previously visited locations and current views are related by multiple of 90 o degrees. We will demonstrate that despite the simplicity and compactness of the global gist descriptor, its discriminability is quite high partly due to 360 o field of view.

/pdf/visual-loop-closing-using-gist-descriptors-in-manhattan-274g5fnoxa.pdf

Visual Loop Closing using Gist Descriptors in Manhattan World

Unsupervised object-centric learning aims to represent the modular, compositional, and causal structure of a scene as a set of object representations and thereby promises to resolve many critical limitations of traditional single-vector representations such as poor systematic generalization. Although there have been many remarkable advances in recent years, one of the most critical problems in this direction has been that previous methods work only with simple and synthetic scenes but not with complex and naturalistic images or videos. In this paper, we propose STEVE, an unsupervised model for object-centric learning in videos. Our proposed model makes a significant advancement by demonstrating its effectiveness on various complex and naturalistic videos unprecedented in this line of research. Interestingly, this is achieved by neither adding complexity to the model architecture nor introducing a new objective or weak supervision. Rather, it is achieved by a surprisingly simple architecture that uses a transformer-based image decoder conditioned on slots and the learning objective is simply to reconstruct the observation. Our experiment results on various complex and naturalistic videos show significant improvements compared to the previous state-of-the-art.

Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos

Methods for acquisition and maintenance of an environment model are central to a broad class of mobility and navigation problems. Towards this end, various metric, topological or hybrid models have been proposed. Due to recent advances in sensing and recognition, acquisition of semantic models of the environments have gained increased interest in the community. In this work, we will demonstrate a capability of using weak semantic models of the environment to induce different topological models, capturing the spatial semantics of the environment at different levels. In the first stage of the model acquisition, we propose to compute semantic layout of the street scenes imagery by recognizing and segmenting buildings, roads, sky, cars and trees. Given such semantic layout, we propose an informative feature characterizing the layout and train a classifier to recognize street intersections in challenging urban inner city scenes. We also show how the evidence of different semantic concepts can induce useful topological representation of the environment, which can aid navigation and localization tasks. To demonstrate the approach, we carry out experiments on a challenging dataset of omnidirectional inner city street views and report the performance of both semantic segmentation and intersection classification.

/pdf/acquiring-semantics-induced-topology-in-urban-environments-2udx4nz65y.pdf

Gautam Singh

Papers

Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context

Localization in Urban Environments Using a Panoramic Gist Descriptor

Visual Loop Closing using Gist Descriptors in Manhattan World

Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos

Acquiring semantics induced topology in urban environments