VSO: Visual Semantic Odometry

Lianos, Konstantinos-Nektarios; Schönberger, Johannes L.; Pollefeys, Marc; Sattler, Torsten

doi:10.1007/978-3-030-01225-0_15

Cited by 124 publications

(68 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic segmentation is the task of assigning a class label to each pixel in an image and is one of the fundamental problems in computer vision. Semantic segmentation has also been used to integrate higher-level scene understanding into other computer vision problems, e.g., dense 3D reconstruction [6,13,14,23,28,31,55,56,61], SLAM [7,35] and Structure-from-Motion [3], 3D model alignment [15,16,73], and location recognition [1,42,60].…”

Section: Introductionmentioning

confidence: 99%

A Cross-Season Correspondence Dataset for Robust Semantic Segmentation

Larsson

Stenborg

Hammarstrand

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

View full text Add to dashboard Cite

In this paper, we present a method to utilize 2D-2D point matches between images taken during different image conditions to train a convolutional neural network for semantic segmentation. Enforcing label consistency across the matches makes the final segmentation algorithm robust to seasonal changes. We describe how these 2D-2D matches can be generated with little human interaction by geometrically matching points from 3D models built from images. Two cross-season correspondence datasets are created providing 2D-2D matches across seasonal changes as well as from day to night. The datasets are made publicly available to facilitate further research. We show that adding the correspondences as extra supervision during training improves the segmentation performance of the convolutional neural network, making it more robust to seasonal changes and weather conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

A Cross-Season Correspondence Dataset for Robust Semantic Segmentation

Larsson

Stenborg

Hammarstrand

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sequence Method 03 04 05 06 07 10 Avg t rel r rel t rel r rel t rel r rel t rel r rel t rel r rel t rel r rel t rel r rel UnDeepVO [16] 5.00 6. 17 Comparison with learning-based methods As shown in Table 1, our method outperforms DeepVO [31], ESP-VO [32] and GFS-VO-RNN [33] (without motion decoupling) on all of the test sequences by a large margin. Since DeepVO, ESP-VO and GFS-VO only consider historical knowledge stored in a single hidden state, error accumulates severely.…”

Section: Results On the Kitti Datasetmentioning

confidence: 94%

Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

Xue

Wang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

105

View full text Add to dashboard Cite

Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components called Memory and Refining. The Memory component preserves global information by employing an adaptive and efficient selection strategy. The Refining component ameliorates previous results with the contexts stored in the Memory by adopting a spatial-temporal attention mechanism for feature distilling. Experiments on the KITTI and TUM-RGBD benchmark datasets demonstrate that our method outperforms state-of-the-art learning-based methods by a large margin and produces competitive results against classic monocular VO approaches. Especially, our model achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic VO algorithms tend to fail.

show abstract

“…• Semantic localization and mapping: Although geometric features such as points, lines and planes [151,165] are primarily used in current VINS for localization, these handcrafted features may not be work best for navigation, and it is of importance to be able to learn best features for VINS by leveraging recent advances of deep learning [166]. Moreover, a few recent research efforts have attempted to endow VINS with semantic understanding of environments [167,168,169,170], which is only sparsely explored but holds great potentials.…”

Section: Discussionmentioning

confidence: 99%

Visual-Inertial Navigation: A Concise Review

Huang

2019

2019 International Conference on Robotics and Automation (ICRA)

281

119

View full text Add to dashboard Cite

As inertial and visual sensors are becoming ubiquitous, visual-inertial navigation systems (VINS) have prevailed in a wide range of applications from mobile augmented reality to aerial navigation to autonomous driving, in part because of the complementary sensing capabilities and the decreasing costs and size of the sensors. In this paper, we survey thoroughly the research efforts taken in this field and strive to provide a concise but complete review of the related work -which is unfortunately missing in the literature while being greatly demanded by researchers and engineers -in the hope to accelerate the VINS research and beyond in our society as a whole.where δq describes the small rotation that causes the true and estimated attitude to coincide. The advantage of this parametrization permits a minimal representation, 3 × 3 covariance matrix E I θ I θ T , for the attitude uncertainty.

show abstract

VSO: Visual Semantic Odometry

Cited by 124 publications

References 53 publications

A Cross-Season Correspondence Dataset for Robust Semantic Segmentation

A Cross-Season Correspondence Dataset for Robust Semantic Segmentation

Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

Visual-Inertial Navigation: A Concise Review

Contact Info

Product

Resources

About