We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

This paper presents ORB-SLAM, a feature-based monocular simultaneous localization and mapping (SLAM) system that operates in real time, in small and large indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.

/pdf/orb-slam-a-versatile-and-accurate-monocular-slam-system-t5f1c0a74e.pdf

ORB-SLAM: A Versatile and Accurate Monocular SLAM System

This paper presents ORB-SLAM, a feature-based monocular SLAM system that operates in real time, in small and large, indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.

/pdf/orb-slam-a-versatile-and-accurate-monocular-slam-system-rnvdngj54a.pdf

ORB-SLAM: a Versatile and Accurate Monocular SLAM System

We present ORB-SLAM2, a complete simultaneous localization and mapping (SLAM) system for monocular, stereo and RGB-D cameras, including map reuse, loop closing, and relocalization capabilities. The system works in real time on standard central processing units in a wide variety of environments from small hand-held indoors sequences, to drones flying in industrial environments and cars driving around a city. Our back-end, based on bundle adjustment with monocular and stereo observations, allows for accurate trajectory estimation with metric scale. Our system includes a lightweight localization mode that leverages visual odometry tracks for unmapped regions and matches with map points that allow for zero-drift localization. The evaluation on 29 popular public sequences shows that our method achieves state-of-the-art accuracy, being in most cases the most accurate SLAM solution. We publish the source code, not only for the benefit of the SLAM community, but with the aim of being an out-of-the-box SLAM solution for researchers in other fields.

ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras

We propose a direct (feature-less) monocular SLAM algorithm which, in contrast to current state-of-the-art regarding direct methods, allows to build large-scale, consistent maps of the environment Along with highly accurate pose estimation based on direct image alignment, the 3D environment is reconstructed in real-time as pose-graph of keyframes with associated semi-dense depth maps These are obtained by filtering over a large number of pixelwise small-baseline stereo comparisons The explicitly scale-drift aware formulation allows the approach to operate on challenging sequences including large variations in scene scale Major enablers are two key novelties: (1) a novel direct tracking method which operates on \(\mathfrak{sim}(3)\), thereby explicitly detecting scale-drift, and (2) an elegant probabilistic solution to include the effect of noisy depth values into tracking The resulting direct monocular SLAM system runs in real-time on a CPU

/pdf/lsd-slam-large-scale-direct-monocular-slam-4eqdolimo8.pdf

LSD-SLAM: Large-Scale Direct Monocular SLAM

In this paper, we present a novel benchmark for the evaluation of RGB-D SLAM systems. We recorded a large set of image sequences from a Microsoft Kinect with highly accurate and time-synchronized ground truth camera poses from a motion capture system. The sequences contain both the color and depth images in full sensor resolution (640 × 480) at video frame rate (30 Hz). The ground-truth trajectory was obtained from a motion-capture system with eight high-speed tracking cameras (100 Hz). The dataset consists of 39 sequences that were recorded in an office environment and an industrial hall. The dataset covers a large variety of scenes and camera motions. We provide sequences for debugging with slow motions as well as longer trajectories with and without loop closures. Most sequences were recorded from a handheld Kinect with unconstrained 6-DOF motions but we also provide sequences from a Kinect mounted on a Pioneer 3 robot that was manually navigated through a cluttered indoor environment. To stimulate the comparison of different approaches, we provide automatic evaluation tools both for the evaluation of drift of visual odometry systems and the global pose error of SLAM systems. The benchmark website [1] contains all data, detailed descriptions of the scenes, specifications of the data formats, sample code, and evaluation tools.

/pdf/a-benchmark-for-the-evaluation-of-rgb-d-slam-systems-4sau0k4128.pdf

A benchmark for the evaluation of RGB-D SLAM systems

In this paper, we present a novel mapping system that robustly generates highly accurate 3-D maps using an RGB-D camera. Our approach requires no further sensors or odometry. With the availability of low-cost and light-weight RGB-D sensors such as the Microsoft Kinect, our approach applies to small domestic robots such as vacuum cleaners, as well as flying robots such as quadrocopters. Furthermore, our system can also be used for free-hand reconstruction of detailed 3-D models. In addition to the system itself, we present a thorough experimental evaluation on a publicly available benchmark dataset. We analyze and discuss the influence of several parameters such as the choice of the feature descriptor, the number of visual features, and validation methods. The results of the experiments demonstrate that our system can robustly deal with challenging scenarios such as fast camera motions and feature-poor environments while being fast enough for online operation. Our system is fully available as open source and has already been widely adopted by the robotics community.

3-D Mapping With an RGB-D Camera

We present an approach to simultaneous localization and mapping (SLAM) for RGB-D cameras like the Microsoft Kinect. Our system concurrently estimates the trajectory of a hand-held Kinect and generates a dense 3D model of the environment. We present the key features of our approach and evaluate its performance thoroughly on a recently published dataset, including a large set of sequences of different scenes with varying camera speeds and illumination conditions. In particular, we evaluate the accuracy, robustness, and processing time for three different feature descriptors (SIFT, SURF, and ORB). The experiments demonstrate that our system can robustly deal with difficult data in common indoor scenarios while being fast enough for online operation. Our system is fully available as open-source.

/pdf/an-evaluation-of-the-rgb-d-slam-system-4i5jftdzbs.pdf

An evaluation of the RGB-D SLAM system

Real-time 3D visual SLAM with a hand-held camera

Truly versatile robots operating in the real world have to be able to learn about objects and their properties autonomously, that is, without being provided with carefully engineered training data. This paper presents an approach that allows a robot to discover object classes in three-dimensional range data in an unsupervised fashion and without a-priori knowledge about the observed objects. Our approach builds on Latent Dirichlet Allocation (LDA), a recently proposed probabilistic method for discovering topics in text documents. We discuss feature extraction, hypothesis generation, and statistical modeling of objects in 3D range data as well as the novel application of LDA to this domain. Our approach has been implemented and evaluated on real data of complex objects. Practical experiments demonstrate, that our approach is able to learn object class models autonomously that are consistent with the true classifications provided by a human. It furthermore outperforms unsupervised method such as hierarchical clustering that operate on a distance metric.

/pdf/unsupervised-discovery-of-object-classes-from-range-data-4uyeg17bz1.pdf

Felix Endres

Papers

A benchmark for the evaluation of RGB-D SLAM systems

3-D Mapping With an RGB-D Camera

An evaluation of the RGB-D SLAM system

Real-time 3D visual SLAM with a hand-held camera

Unsupervised discovery of object classes from range data using latent Dirichlet allocation