Real-time visual loop-closure detection (original) (raw)

Fast and incremental method for loop-closure detection using bags of visual words

… , IEEE Transactions on, 2008

In robotic applications of visual simultaneous localization and mapping techniques, loop-closure detection and global localization are two issues that require the capacity to recognize a previously visited place from current camera measurements. We present an online method that makes it possible to detect when an image comes from an already perceived scene using local shape and color information. Our approach extends the bag-of-words method used in image classification to incremental conditions and relies on Bayesian filtering to estimate loop-closure probability. We demonstrate the efficiency of our solution by real-time loop-closure detection under strong perceptual aliasing conditions in both indoor and outdoor image sequences taken with a handheld camera.

Tree of Words for Visual Loop Closure Detection in Urban SLAM

2008

This paper introduces vision based loop closure detection in Simultaneous Localisation And Mapping (SLAM) using Tree of Words. The loop closure performance in a complex urban environment is examined and an additional feature is suggested for safer matching. A SLAM ground experiment in an urban area is performed using Tree of Words, a delayed state information filter and planar laser scans for relative pose estimation. Results show that a good map estimation using our vision based loop closure detection can be obtained in near real, yet constant, time. It is shown that an odometry supported recall rate of almost 70% can be obtained with a false detection rate of about 0.01%.

Combining odometry and visual loop-closure detection for consistent topo-metrical mapping

2010

We address the problem of simultaneous localization and mapping (SLAM) by combining visual loop-closure detection with metrical information given by a robot odometry. The proposed algorithm extends a purely appearance-based loopclosure detection method based on bags of visual words [1] which is able to detect when the robot has returned back to a previously visited place. An efficient optimization algorithm is used to integrate odometry information in this method to generate a consistent topo-metrical map. The resulting algorithm which only requires a monocular camera and odometry data and is simple, and robust without requiring any a priori information on the environment.

A spherical representation for efficient visual loop closing

2011

Mapping. Our solution relies on an ego-centred spherical representation of the environment and the exploitation of two kinds of information: local appearance and global feature density. Local appearance is provided by local features extracted from the spherical representation and processed using the bag of visual words approach. Global density information is computed from the distribution over the sphere of these features thus characterizing the environment structure. The approach is purely appearance-based and does not involve any geometric information such as epipolar constraints. An experiment on an 1.5kms trajectory in an environment containing buildings and vegetation validates our algorithm and shows a reduction of the false alarm rate by about 50% for the same probability of detection compared to the standard bag of visual words approach.

Fast loop-closure detection using visual-word-vectors from image sequences

The International Journal of Robotics Research

In this paper, a novel pipeline for loop-closure detection is proposed. We base our work on a bag of binary feature words and we produce a description vector capable of characterizing a physical scene as a whole. Instead of relying on single camera measurements, the robot’s trajectory is dynamically segmented into image sequences according to its content. The visual word occurrences from each sequence are then combined to create sequence-visual-word-vectors and provide additional information to the matching functionality. In this way, scenes with considerable visual differences are firstly discarded, while the respective image-to-image associations are provided subsequently. With the purpose of further enhancing the system’s performance, a novel temporal consistency filter (trained offline) is also introduced to advance matches that persist over time. Evaluation results prove that the presented method compares favorably with other state-of-the-art techniques, while our algorithm is ...

A discriminative approach for appearance based loop closing

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012

The place recognition module is a fundamental component in SLAM systems, as incorrect loop closures may result in severe errors in trajectory estimation. In the case of appearance-based methods the bag-of-words approach is typically employed for recognizing locations. This paper introduces a novel algorithm for improving loop closures detection performance by adopting a set of visual words weights, learned offline accordingly to a discriminative criterion. The proposed weights learning approach, based on the large margin paradigm, can be used for generic similarity functions and relies on an efficient online leaning algorithm in the training phase. As the computed weights are usually very sparse, a gain in terms of computational cost at recognition time is also obtained. Our experiments, conducted on publicly available datasets, demonstrate that the discriminative weights lead to loop closures detection results that are more accurate than the traditional bag-of-words method and that our place recognition approach is competitive with state-of-the-art methods.

Incremental vision-based topological SLAM

Intelligent Robots and …, 2008

In robotics, appearance-based topological map building consists in infering the topology of the environment explored by a robot from its sensor measurements. In this paper, we propose a vision-based framework that considers this data association problem from a loop-closure detection perspective in order to correctly assign each measurement to its location. Our approach relies on the visual bag of words paradigm to represent the images and on a discrete Bayes filter to compute the probability of loop-closure. We demonstrate the efficiency of our solution by incremental and real-time consistent map building in an indoor environment and under strong perceptual aliasing conditions using a single monocular wide-angle camera.

Light-weight place recognition and loop detection using road markings

ArXiv, 2017

In this paper, we propose an efficient algorithm for robust place recognition and loop detection using camera information only. Our pipeline purely relies on spatial localization and semantic information of road markings. The creation of the database of road markings sequences is performed online, which makes the method applicable for real-time loop closure for visual SLAM techniques. Furthermore, our algorithm is robust to various weather conditions, occlusions from vehicles, and shadows. We have performed an extensive number of experiments which highlight the effectiveness and scalability of the proposed method.

The Revisiting Problem in Simultaneous Localization and Mapping

Springer eBooks, 2022

Where am I? This is one of the most critical questions that any intelligent system should answer to decide whether it navigates to a previously visited area. This problem has long been acknowledged for its challenging nature in simultaneous localization and mapping (SLAM), wherein the robot needs to correctly associate the incoming sensory data to the database allowing consistent map generation. The significant advances in computer vision achieved over the last 20 years, the increased computational power, and the growing demand for long-term exploration contributed to efficiently performing such a complex task with inexpensive perception sensors. In this article, visual loop closure detection, which formulates a solution based solely on appearance input data, is surveyed. We start by briefly introducing place recognition and SLAM concepts in robotics. Then, we describe a loop closure detection system's structure, covering an extensive collection of topics, including the feature extraction, the environment representation, the decision-making step, and the evaluation process. We conclude by discussing open and new research challenges, particularly concerning the robustness in dynamic environments, the computational complexity, and scalability in long-term operations. The article aims to serve as a tutorial and a position paper for newcomers to visual loop closure detection.

An incremental loop closure detection method based on depth information for indoor dynamic scenes

Proceedings of the 2018 3rd Joint International Information Technology，Mechanical and Electronic Engineering Conference (JIMEC 2018), 2018

We present a RGB-D based place recognition algorithm methods for large-scale dynamic indoor environment. In contrast with other methods, our methods focus on the scene that dynamic objects are remarkable and avoid the unnecessary calculate expenses on the whole image sequences. In order to prohibit the influence of dynamic object, the depth information was applied to discriminate the image foreground information and filter it out. We conducted our methods on the public dataset and tested on the real environment. The results demonstrate that the proposed methods can effectively improve the loop-closure system in indoor dynamic environments.