Approaches, Challenges, and Applications for Deep Visual Odometry: Toward Complicated and Emerging Areas

Wang, Ke; Ma, Sai; Chen, Junlan; Ren, Fan; Lǚ, Jianbo

doi:10.1109/tcds.2020.3038898

Cited by 76 publications

(42 citation statements)

References 118 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With recent advancements in the VO systems with loop-closure, the boundary between VO and Visual-SLAM (V-SLAM) has become blurred; nevertheless, VO systems devote more attention to ego-motion estimation than to map building [ 157 ]. There exist several review papers on the VO systems—[ 13 , 158 , 159 , 160 ] provided a comprehensive overview of VO and V-SLAM; the two-part survey [ 161 , 162 ] highlighted feature-based VO; while [ 163 , 164 , 165 , 166 ] conducted reviews of recent advancements in VO and V-SLAM using state-of-the-art data-driven methods. VO can be classified into geometry-based methods and learning-based methods; geometry-based methods can be further categorized into feature-based approaches, appearance-based approaches, and hybrid approaches.…”

Section: Sensors and Sensor-based Odometry Methodsmentioning

confidence: 99%

Sensors and Sensor Fusion Methodologies for Indoor Odometry: A Review

et al. 2022

View full text Add to dashboard Cite

Although Global Navigation Satellite Systems (GNSSs) generally provide adequate accuracy for outdoor localization, this is not the case for indoor environments, due to signal obstruction. Therefore, a self-contained localization scheme is beneficial under such circumstances. Modern sensors and algorithms endow moving robots with the capability to perceive their environment, and enable the deployment of novel localization schemes, such as odometry, or Simultaneous Localization and Mapping (SLAM). The former focuses on incremental localization, while the latter stores an interpretable map of the environment concurrently. In this context, this paper conducts a comprehensive review of sensor modalities, including Inertial Measurement Units (IMUs), Light Detection and Ranging (LiDAR), radio detection and ranging (radar), and cameras, as well as applications of polymers in these sensors, for indoor odometry. Furthermore, analysis and discussion of the algorithms and the fusion frameworks for pose estimation and odometry with these sensors are performed. Therefore, this paper straightens the pathway of indoor odometry from principle to application. Finally, some future prospects are discussed.

show abstract

Section: Sensors and Sensor-based Odometry Methodsmentioning

confidence: 99%

Sensors and Sensor Fusion Methodologies for Indoor Odometry: A Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Traditional inter-frame estimation methods adopt feature-based methods or direct methods to identify camera pose through multi-view geometry [152]. Features-based methods need complex feature extraction and matching.…”

Section: Cnn With Vslammentioning

confidence: 99%

An Overview on Visual SLAM: From Tradition to Semantic

et al. 2022

View full text Add to dashboard Cite

Visual SLAM (VSLAM) has been developing rapidly due to its advantages of low-cost sensors, the easy fusion of other sensors, and richer environmental information. Traditional visionbased SLAM research has made many achievements, but it may fail to achieve wished results in challenging environments. Deep learning has promoted the development of computer vision, and the combination of deep learning and SLAM has attracted more and more attention. Semantic information, as high-level environmental information, can enable robots to better understand the surrounding environment. This paper introduces the development of VSLAM technology from two aspects: traditional VSLAM and semantic VSLAM combined with deep learning. For traditional VSLAM, we summarize the advantages and disadvantages of indirect and direct methods in detail and give some classical VSLAM open-source algorithms. In addition, we focus on the development of semantic VSLAM based on deep learning. Starting with typical neural networks CNN and RNN, we summarize the improvement of neural networks for the VSLAM system in detail. Later, we focus on the help of target detection and semantic segmentation for VSLAM semantic information introduction. We believe that the development of the future intelligent era cannot be without the help of semantic technology. Introducing deep learning into the VSLAM system to provide semantic information can help robots better perceive the surrounding environment and provide people with higher-level help.

show abstract

“…More recently, deep learning based approaches have dominated computer vision [14]. Inspired by this, the field has adapted CNNs to extract and match feature points and to estimate VO [30]. DeTone et al [5] present a learningbased approach to detect interest point detectors and descriptors.…”

Section: Related Workmentioning

confidence: 99%

MDN-VO: Estimating Visual Odometry with Confidence

Kaygusuz,

Mendez,

Bowden

2021

Preprint

View full text Add to dashboard Cite

Visual Odometry (VO) is used in many applications including robotics and autonomous systems. However, traditional approaches based on feature matching are computationally expensive and do not directly address failure cases, instead relying on heuristic methods to detect failure. In this work, we propose a deep learning-based VO model to efficiently estimate 6-DoF poses, as well as a confidence model for these estimates. We utilise a CNN -RNN hybrid model to learn feature representations from image sequences. We then employ a Mixture Density Network (MDN) which estimates camera motion as a mixture of Gaussians, based on the extracted spatiotemporal representations.Our model uses pose labels as a source of supervision, but derives uncertainties in an unsupervised manner. We evaluate the proposed model on the KITTI and nuScenes datasets and report extensive quantitative and qualitative results to analyse the performance of both pose and uncertainty estimation. Our experiments show that the proposed model exceeds state-of-theart performance in addition to detecting failure cases using the predicted pose uncertainty.

show abstract

Approaches, Challenges, and Applications for Deep Visual Odometry: Toward Complicated and Emerging Areas

Cited by 76 publications

References 118 publications

Sensors and Sensor Fusion Methodologies for Indoor Odometry: A Review

Sensors and Sensor Fusion Methodologies for Indoor Odometry: A Review

An Overview on Visual SLAM: From Tradition to Semantic

MDN-VO: Estimating Visual Odometry with Confidence

Contact Info

Product

Resources

About