Daniel Groos
About
- Development of machine learning models for video-based motion capture and early prediction of cerebral palsy
- Interdisciplinary collaboration between NTNU (IKOM, INB and IDI), St. Olavs Hospital (Clinic of Clinical Services and Department of Neonatology) and Norwegian Open AI Lab
- Movement analysis in golf and baseball with Initial Force and kinematic analysis of elite ski jumpers in collaboration with Centre for Elite Sports Research and Olympiatoppen
- Inventor of deep learning methods for video-based motion capture and early detection of cerebral palsy
- Deep Learning
- Computer Vision
- Convolutional Neural Networks
- Graph Convolutional Networks
- Human Activity Recognition
- Human Pose Estimation
- Supervised Learning
- Transfer Learning
- Explainable Artificial Intelligence
- Doctoral degree in Medical Technology from NTNU (2018-2022)
- Master of Science in Computer Science from NTNU (2013-2018)
- Specialization in Artificial Intelligence
Publications
2022
-
Groos, Daniel;
Ihlen, Espen A. F.;
Adde, Lars;
Ramampiaro, Heri.
(2022)
Convolutional networks for video-based infant movement analysis. Towards objective prognosis of cerebral palsy from infant spontaneous movements.
Norges teknisk-naturvitenskapelige universitet
Norges teknisk-naturvitenskapelige universitet
Doctoral dissertation
-
Groos, Daniel;
Adde, Lars;
Støen, Ragnhild;
Ramampiaro, Heri;
Ihlen, Espen Alexander F..
(2022)
Towards human-level performance on automatic pose estimation of infant spontaneous movements.
Computerized Medical Imaging and Graphics
Academic article
-
Groos, Daniel;
Adde, Lars;
Aubert, Sindre Aarnes;
Boswell, Lynn;
Regnier, Raye-Ann De;
Fjørtoft, Toril Larsson.
(2022)
Development and Validation of a Deep Learning Method to Predict Cerebral Palsy from Spontaneous Movements in Infants at High Risk.
JAMA Network Open
Academic article
2021
-
Groos, Daniel;
Adde, Lars;
Støen, Ragnhild;
Ramampiaro, Heri;
Ihlen, Espen Alexander F..
(2021)
New automatic, efficient, and highly precise tracking of infant spontaneous movements.
Developmental Medicine & Child Neurology
Abstract
-
Groos, Daniel;
Adde, Lars;
Aubert, Sindre Aarnes;
Haukeland, Andreas;
Ramampiaro, Heri;
Støen, Ragnhild.
(2021)
Fully automated clinical movement analysis from videos using skeleton-based deep learning.
Gait & Posture
Abstract
-
Adde, Lars;
Brown, Annemette;
Broeck, Christine van den;
DeCoen, Kris;
Eriksen, Beate Horsberg;
Fjørtoft, Toril Larsson.
(2021)
In-Motion-App for remote General Movement Assessment: a multi-site observational study.
BMJ Open
Academic article
-
Elfmark, Ola;
Ettema, Gertjan;
Groos, Daniel;
Ihlen, Espen Alexander F.;
Velta, Rune;
Haugen, Per.
(2021)
Performance analysis in ski jumping with a differential global navigation satellite system and video-based pose estimation.
Sensors
Academic article
2020
-
Groos, Daniel;
Adde, Lars;
Ihlen, Espen Alexander F..
(2020)
Approaching human precision on automatic markerless tracking of human movements.
Gait & Posture
Abstract
-
Groos, Daniel;
Ramampiaro, Heri;
Ihlen, Espen Alexander F..
(2020)
EfficientPose: Scalable single-person pose estimation.
Applied Intelligence - The International Journal of Research on Intelligent Systems for Real Life Complex Problems
Academic article
2019
-
Groos, Daniel;
Aurlien, Kristian;
Ramampiaro, Heri;
Ihlen, Espen Alexander F.;
deRegnier, RA;
Peyton, Colleen.
(2019)
Deep Learning‐based infant motion tracking facilitating early detection of cerebral palsy.
Developmental Medicine & Child Neurology
Abstract
2018
-
Groos, Daniel;
Aurlien, Kristian.
(2018)
Infant body part tracking in videos using Deep Learning.
NTNU
NTNU
Masters thesis
Journal publications
-
Groos, Daniel;
Adde, Lars;
Støen, Ragnhild;
Ramampiaro, Heri;
Ihlen, Espen Alexander F..
(2022)
Towards human-level performance on automatic pose estimation of infant spontaneous movements.
Computerized Medical Imaging and Graphics
Academic article
-
Groos, Daniel;
Adde, Lars;
Aubert, Sindre Aarnes;
Boswell, Lynn;
Regnier, Raye-Ann De;
Fjørtoft, Toril Larsson.
(2022)
Development and Validation of a Deep Learning Method to Predict Cerebral Palsy from Spontaneous Movements in Infants at High Risk.
JAMA Network Open
Academic article
-
Groos, Daniel;
Adde, Lars;
Støen, Ragnhild;
Ramampiaro, Heri;
Ihlen, Espen Alexander F..
(2021)
New automatic, efficient, and highly precise tracking of infant spontaneous movements.
Developmental Medicine & Child Neurology
Abstract
-
Groos, Daniel;
Adde, Lars;
Aubert, Sindre Aarnes;
Haukeland, Andreas;
Ramampiaro, Heri;
Støen, Ragnhild.
(2021)
Fully automated clinical movement analysis from videos using skeleton-based deep learning.
Gait & Posture
Abstract
-
Adde, Lars;
Brown, Annemette;
Broeck, Christine van den;
DeCoen, Kris;
Eriksen, Beate Horsberg;
Fjørtoft, Toril Larsson.
(2021)
In-Motion-App for remote General Movement Assessment: a multi-site observational study.
BMJ Open
Academic article
-
Elfmark, Ola;
Ettema, Gertjan;
Groos, Daniel;
Ihlen, Espen Alexander F.;
Velta, Rune;
Haugen, Per.
(2021)
Performance analysis in ski jumping with a differential global navigation satellite system and video-based pose estimation.
Sensors
Academic article
-
Groos, Daniel;
Adde, Lars;
Ihlen, Espen Alexander F..
(2020)
Approaching human precision on automatic markerless tracking of human movements.
Gait & Posture
Abstract
-
Groos, Daniel;
Ramampiaro, Heri;
Ihlen, Espen Alexander F..
(2020)
EfficientPose: Scalable single-person pose estimation.
Applied Intelligence - The International Journal of Research on Intelligent Systems for Real Life Complex Problems
Academic article
-
Groos, Daniel;
Aurlien, Kristian;
Ramampiaro, Heri;
Ihlen, Espen Alexander F.;
deRegnier, RA;
Peyton, Colleen.
(2019)
Deep Learning‐based infant motion tracking facilitating early detection of cerebral palsy.
Developmental Medicine & Child Neurology
Abstract
Report
-
Groos, Daniel;
Ihlen, Espen A. F.;
Adde, Lars;
Ramampiaro, Heri.
(2022)
Convolutional networks for video-based infant movement analysis. Towards objective prognosis of cerebral palsy from infant spontaneous movements.
Norges teknisk-naturvitenskapelige universitet
Norges teknisk-naturvitenskapelige universitet
Doctoral dissertation
-
Groos, Daniel;
Aurlien, Kristian.
(2018)
Infant body part tracking in videos using Deep Learning.
NTNU
NTNU
Masters thesis
Outreach
2021
-
Academic lectureGroos, Daniel; Adde, Lars; Støen, Ragnhild; Ramampiaro, Heri; Ihlen, Espen Alexander F.. (2021) New automatic, efficient, and highly precise tracking of infant spontaneous movements. European Academy of Childhood Disability 2021 , Virtual 2021-05-20 - 2021-06-10
-
Academic lectureGroos, Daniel; Adde, Lars; Aubert, Sindre Aarnes; Haukeland, Andreas; Ramampiaro, Heri; Støen, Ragnhild. (2021) Fully automated clinical movement analysis from videos using skeleton-based deep learning. ESMAC 2021 2021-10-14 - 2021-10-15
2020
-
Academic lectureGroos, Daniel; Adde, Lars; Ihlen, Espen Alexander F.. (2020) Approaching human precision on automatic markerless tracking of human movements. Virtual ESMAC 2020 2020-09-17 -
2019
-
PosterGroos, Daniel; Aurlien, Kristian; Ramampiaro, Heri; Ihlen, Espen Alexander F.; deRegnier, RA; Peyton, Colleen. (2019) Deep Learning-based infant motion tracking facilitating early detection of cerebral palsy. European Academy of Childhood Disability 2019 , Paris 2019-05-23 - 2019-05-25