2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) 2019
DOI: 10.1109/iccvw.2019.00468
|View full text |Cite
|
Sign up to set email alerts
|

SLAMANTIC - Leveraging Semantics to Improve VSLAM in Dynamic Environments

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
24
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 27 publications
(26 citation statements)
references
References 30 publications
0
24
0
Order By: Relevance
“…The semantic segmentation network can be implemented inside a SLAM framework by various approaches, as in other methods like [36] and [16]. The output of this network, as stated before, is used for filtering out the undesired (dynamic) keypoints.…”
Section: A Preprocessingmentioning
confidence: 99%
“…The semantic segmentation network can be implemented inside a SLAM framework by various approaches, as in other methods like [36] and [16]. The output of this network, as stated before, is used for filtering out the undesired (dynamic) keypoints.…”
Section: A Preprocessingmentioning
confidence: 99%
“…We donate δ as the threshold to determine whether the feature points are dynamic or not, and the way to judge it is to calculate the distance k i of each feature point by using formula (8). If k i > δ, the feature point will be labeled as dynamic Otherwise, it will be labeled as static.…”
Section: ) Dynamic Features Detectionmentioning
confidence: 99%
“…Identifying and excluding feature points on dynamic objects is an effective way to eliminates the impact of dynamic environments on the system [7]. Recent studies [8], [9] have shown that feature points can be effectively classified based on the results of semantic segmentation. And then, only feature points located on static objects are allowed to participate in subsequent calculations.…”
Section: Introductionmentioning
confidence: 99%
“…(Wang et al, 2019) simultaneously improved SLAM and semantic segmentation by distinguishing between features on moving, potentially moving and on the static background for SLAM and using the 3D pose information to refine the segmentation. (Schorghuber et al, 2019) distinguished between similar object states in a dynamic fashion, using a continuously updated confidence factor. In contrast, we decided to use the basic masking approach, since many slowly moving objects are only observed for a short time in our handheld datasets.…”
Section: Related Workmentioning
confidence: 99%