From IR Images to Point Clouds to Pose : Point Cloud-Based AR Glasses Pose Estimation
In this paper, we propose two novel AR glasses pose estimation algorithms from single infrared images by using 3D point clouds as an intermediate representation. Our first approach "PointsToRotation" is based on a Deep Neural Network alone, whereas our second approach "PointsToPose" is a hybrid model combining Deep Learning and a voting-based mechanism. Our methods utilize a point cloud estimator, which we trained on multi-view infrared images in a semi-supervised manner, generating point clouds based on one image only. We generate a point cloud dataset with our point cloud estimator using the HMDPose dataset, consisting of multi-view infrared images of various AR glasses with the corresponding 6-DoF poses. In comparison to another point cloud-based 6-DoF pose estimation named CloudPose, we achieve an error reduction of around 50%. Compared to a state-of-the-art image-based method, we reduce the pose estimation error by around 96%.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:7 |
---|---|
Enthalten in: |
Journal of imaging - 7(2021), 5 vom: 27. Apr. |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Firintepe, Ahmet [VerfasserIn] |
---|
Links: |
---|
Themen: |
Augmented reality |
---|
Anmerkungen: |
Date Revised 03.09.2021 published: Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.3390/jimaging7050080 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM330034405 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM330034405 | ||
003 | DE-627 | ||
005 | 20231225210425.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3390/jimaging7050080 |2 doi | |
028 | 5 | 2 | |a pubmed24n1100.xml |
035 | |a (DE-627)NLM330034405 | ||
035 | |a (NLM)34460676 | ||
035 | |a (PII)80 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Firintepe, Ahmet |e verfasserin |4 aut | |
245 | 1 | 0 | |a From IR Images to Point Clouds to Pose |b Point Cloud-Based AR Glasses Pose Estimation |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 03.09.2021 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a In this paper, we propose two novel AR glasses pose estimation algorithms from single infrared images by using 3D point clouds as an intermediate representation. Our first approach "PointsToRotation" is based on a Deep Neural Network alone, whereas our second approach "PointsToPose" is a hybrid model combining Deep Learning and a voting-based mechanism. Our methods utilize a point cloud estimator, which we trained on multi-view infrared images in a semi-supervised manner, generating point clouds based on one image only. We generate a point cloud dataset with our point cloud estimator using the HMDPose dataset, consisting of multi-view infrared images of various AR glasses with the corresponding 6-DoF poses. In comparison to another point cloud-based 6-DoF pose estimation named CloudPose, we achieve an error reduction of around 50%. Compared to a state-of-the-art image-based method, we reduce the pose estimation error by around 96% | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a augmented reality | |
650 | 4 | |a computer vision | |
650 | 4 | |a deep learning | |
650 | 4 | |a object pose estimation | |
650 | 4 | |a point clouds | |
700 | 1 | |a Vey, Carolin |e verfasserin |4 aut | |
700 | 1 | |a Asteriadis, Stylianos |e verfasserin |4 aut | |
700 | 1 | |a Pagani, Alain |e verfasserin |4 aut | |
700 | 1 | |a Stricker, Didier |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of imaging |d 2016 |g 7(2021), 5 vom: 27. Apr. |w (DE-627)NLM26971538X |x 2313-433X |7 nnns |
773 | 1 | 8 | |g volume:7 |g year:2021 |g number:5 |g day:27 |g month:04 |
856 | 4 | 0 | |u http://dx.doi.org/10.3390/jimaging7050080 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 7 |j 2021 |e 5 |b 27 |c 04 |