Robust visual SLAM across seasons

Naseer, Tayyab; Ruhnke, Michael; Stachniss, Cyrill; Spinello, Luciano; Burgard, Wolfram

doi:10.1109/iros.2015.7353721

Cited by 75 publications

(37 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their application in localization methods remains an open challenge but a direct use would be to remove moving, or temporally static, obstacles that can disturb the proper behavior of a SLAM algorithm. More generally, CNNs could change how place recognition is performed by using feature maps coming from these networks as in [142]. The impact and the use of CNNs for localization in autonomous driving will surely evolve in the coming years.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving

Bresson

Alsayed

et al. 2017

IEEE Trans. Intell. Veh.

673

366

View full text Add to dashboard Cite

Abstract-In this article, we propose a survey of the Simultaneous Localization And Mapping field when considering the recent evolution of autonomous driving. The growing interest regarding self-driving cars has given new directions to localization and mapping techniques. In this survey, we give an overview of the different branches of SLAM before going into the details of specific trends that are of interest when considered with autonomous applications in mind. We first present the limits of classical approaches for autonomous driving and discuss the criteria that are essential for this kind of application. We then review the methods where the identified challenges are tackled. We mostly focus on approaches building and reusing long-term maps in various conditions (weather, season, etc.). We also go through the emerging domain of multi-vehicle SLAM and its link with self-driving cars. We survey the different paradigms of that field (centralized and distributed) and the existing solutions. Finally, we conclude by giving an overview of the various largescale experiments that have been carried out until now and discuss the remaining challenges and future orientations.

show abstract

Section: Discussionmentioning

confidence: 99%

“…It requires a few seconds to process each image. An evolution of this method has been presented in [142]. The authors replaced the HOG features used to represent images with a global image feature map from a Deep Convolutional Neural Networks.…”

Section: A Relocalization and Loop Closurementioning

confidence: 99%

Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving

Bresson

Alsayed

et al. 2017

IEEE Trans. Intell. Veh.

673

366

View full text Add to dashboard Cite

show abstract

“…Originally invented for computer version, CNN models have subsequently been shown to be effective for many different problems including, Simultaneous Localization and Mapping(SLAM) [8], Decision Making [9] and Automatic Driving [10].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

A Convolutional Neural Networks Approach to Devise Controller

Liu

Dong

2017

MATEC Web Conf.

View full text Add to dashboard Cite

Abstract. PID controller is widely used in many fields. The input sequence and output sequence of a wellparameterized PID controller are transformed into a matrix presented in images in this paper, and a EveryTimestep data augmentation algorithm is operated.This paper propose a image to image Convolutional Neural Networks(CNN) structure to learn the PID controller, which incorporates the successful methods in computer vision and deep learning to control field. The simulation is performed using Matlab/Simulink and Keras [1]. The simulation demonstrates that the CNN controller is capable in performance.

show abstract

“…The SeqSLAM approach [26] utilized the sum of absolute differences between contrast low-resolution images as global features to perform sequence-based place recognition. Deep features based on convolutional neural networks (CNNs) were adopted to match image sequences [31]. Global features can encode whole image information and no dictionary-based quantization is required, which showed promising performance for long-term place recognition [2,26,27,30,33].…”

Section: A Visual Features For Scene Representationmentioning

confidence: 99%

“…The current implementation was programmed using a mixture of unoptimized Matlab and C++ on a Linux laptop with an i7 3.0 GHz GPU, 16G memory and 2G GPU. Similar to other state-of-the-art methods [31,39], the implementation in this current stage is not able to perform large-scale longterm loop closure detection in real time. A key limiting factor is that the runtime is proportional to the number of previously visited places.…”

Section: A Experiments Setupmentioning

confidence: 99%

Robust Multimodal Sequence-Based Loop Closure Detection via Structured Sparsity

Zhang¹,

Han²,

Wang³

Robotics: Science and Systems XII

View full text Add to dashboard Cite

Abstract-Loop closure detection is an essential component for simultaneously localization and mapping in a variety of robotics applications. One of the most challenging problems is to perform long-term place recognition with strong perceptual aliasing and appearance variations due to changes of illumination, vegetation, weather, etc. To address this challenge, we propose a novel Robust Multimodal Sequence-based (ROMS) method for long-term loop closure detection, by formulating image sequence matching as an optimization problem regularized by structured sparsity-inducing norms. Our method is able to model the sparsity nature of place recognition, i.e., the current location should match only a small subset of previously visited places, as well as to model underlying structures of image sequences and incorporate multiple feature modalities to construct a discriminative scene representation. In addition, a new optimization algorithm is developed to efficiently solve the formulated problem, which has a theoretical guarantee to converge to the global optimal solution. To evaluate the ROMS algorithm, extensive experiments are performed using large-scale benchmark datasets, including St Lucia, CMU-VL, and Nordland datasets. Experimental results have validated that our algorithm outperforms previous loop closure detection methods, and obtains the state-of-the-art performance on long-term place recognition.

show abstract

Robust visual SLAM across seasons

Cited by 75 publications

References 20 publications

Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving

Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving

A Convolutional Neural Networks Approach to Devise Controller

Robust Multimodal Sequence-Based Loop Closure Detection via Structured Sparsity

Contact Info

Product

Resources

About