Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios
Head pose assessment can reveal important clinical information on human motor control. Quantitative assessment have the potential to objectively evaluate head pose and movements’ specifics, in order to monitor the progression of a disease or the effectiveness of a treatment. Optoelectronic camera-ba...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/18/6850 |
| _version_ | 1797482592676610048 |
|---|---|
| author | Yassine Hammadi François Grondin François Ferland Karina Lebel |
| author_facet | Yassine Hammadi François Grondin François Ferland Karina Lebel |
| author_sort | Yassine Hammadi |
| collection | DOAJ |
| description | Head pose assessment can reveal important clinical information on human motor control. Quantitative assessment have the potential to objectively evaluate head pose and movements’ specifics, in order to monitor the progression of a disease or the effectiveness of a treatment. Optoelectronic camera-based motion-capture systems, recognized as a gold standard in clinical biomechanics, have been proposed for head pose estimation. However, these systems require markers to be positioned on the person’s face which is impractical for everyday clinical practice. Furthermore, the limited access to this type of equipment and the emerging trend to assess mobility in natural environments support the development of algorithms capable of estimating head orientation using off-the-shelf sensors, such as RGB cameras. Although artificial vision is a popular field of research, limited validation of human pose estimation based on image recognition suitable for clinical applications has been performed. This paper first provides a brief review of available head pose estimation algorithms in the literature. Current state-of-the-art head pose algorithms designed to capture the facial geometry from videos, OpenFace 2.0, MediaPipe and 3DDFA_V2, are then further evaluated and compared. Accuracy is assessed by comparing both approaches to a baseline, measured with an optoelectronic camera-based motion-capture system. Results reveal a mean error lower or equal to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5</mn><mo>.</mo><msup><mn>6</mn><mo>∘</mo></msup></mrow></semantics></math></inline-formula> for 3DDFA_V2 depending on the plane of movement, while the mean error reaches <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>14</mn><mo>.</mo><msup><mn>1</mn><mo>∘</mo></msup></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>11</mn><mo>.</mo><msup><mn>0</mn><mo>∘</mo></msup></mrow></semantics></math></inline-formula> for OpenFace 2.0 and MediaPipe, respectively. This demonstrates the superiority of the 3DDFA_V2 algorithm in estimating head pose, in different directions of motion, and suggests that this algorithm can be used in clinical scenarios. |
| first_indexed | 2024-03-09T22:34:36Z |
| format | Article |
| id | doaj.art-34aec2225d0f4a23844cdb6d02769b95 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T22:34:36Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-34aec2225d0f4a23844cdb6d02769b952023-11-23T18:50:19ZengMDPI AGSensors1424-82202022-09-012218685010.3390/s22186850Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical ScenariosYassine Hammadi0François Grondin1François Ferland2Karina Lebel3Department of Electrical and Computer Engineering, Faculty of Engineering, Université de Sherbrooke, Sherbrooke, QC J1H 5N4, CanadaDepartment of Electrical and Computer Engineering, Faculty of Engineering, Université de Sherbrooke, Sherbrooke, QC J1H 5N4, CanadaDepartment of Electrical and Computer Engineering, Faculty of Engineering, Université de Sherbrooke, Sherbrooke, QC J1H 5N4, CanadaDepartment of Electrical and Computer Engineering, Faculty of Engineering, Université de Sherbrooke, Sherbrooke, QC J1H 5N4, CanadaHead pose assessment can reveal important clinical information on human motor control. Quantitative assessment have the potential to objectively evaluate head pose and movements’ specifics, in order to monitor the progression of a disease or the effectiveness of a treatment. Optoelectronic camera-based motion-capture systems, recognized as a gold standard in clinical biomechanics, have been proposed for head pose estimation. However, these systems require markers to be positioned on the person’s face which is impractical for everyday clinical practice. Furthermore, the limited access to this type of equipment and the emerging trend to assess mobility in natural environments support the development of algorithms capable of estimating head orientation using off-the-shelf sensors, such as RGB cameras. Although artificial vision is a popular field of research, limited validation of human pose estimation based on image recognition suitable for clinical applications has been performed. This paper first provides a brief review of available head pose estimation algorithms in the literature. Current state-of-the-art head pose algorithms designed to capture the facial geometry from videos, OpenFace 2.0, MediaPipe and 3DDFA_V2, are then further evaluated and compared. Accuracy is assessed by comparing both approaches to a baseline, measured with an optoelectronic camera-based motion-capture system. Results reveal a mean error lower or equal to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5</mn><mo>.</mo><msup><mn>6</mn><mo>∘</mo></msup></mrow></semantics></math></inline-formula> for 3DDFA_V2 depending on the plane of movement, while the mean error reaches <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>14</mn><mo>.</mo><msup><mn>1</mn><mo>∘</mo></msup></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>11</mn><mo>.</mo><msup><mn>0</mn><mo>∘</mo></msup></mrow></semantics></math></inline-formula> for OpenFace 2.0 and MediaPipe, respectively. This demonstrates the superiority of the 3DDFA_V2 algorithm in estimating head pose, in different directions of motion, and suggests that this algorithm can be used in clinical scenarios.https://www.mdpi.com/1424-8220/22/18/6850movement analysisface recognitionneural networksOpenFace 2.03DDFA_V2realsense |
| spellingShingle | Yassine Hammadi François Grondin François Ferland Karina Lebel Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios Sensors movement analysis face recognition neural networks OpenFace 2.0 3DDFA_V2 realsense |
| title | Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios |
| title_full | Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios |
| title_fullStr | Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios |
| title_full_unstemmed | Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios |
| title_short | Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios |
| title_sort | evaluation of various state of the art head pose estimation algorithms for clinical scenarios |
| topic | movement analysis face recognition neural networks OpenFace 2.0 3DDFA_V2 realsense |
| url | https://www.mdpi.com/1424-8220/22/18/6850 |
| work_keys_str_mv | AT yassinehammadi evaluationofvariousstateoftheartheadposeestimationalgorithmsforclinicalscenarios AT francoisgrondin evaluationofvariousstateoftheartheadposeestimationalgorithmsforclinicalscenarios AT francoisferland evaluationofvariousstateoftheartheadposeestimationalgorithmsforclinicalscenarios AT karinalebel evaluationofvariousstateoftheartheadposeestimationalgorithmsforclinicalscenarios |