Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images
The identification of human activities from videos is important for many applications. For such a task, three-dimensional (3D) depth images or image sequences (videos) can be used, which represent the positioning information of the objects in a 3D scene obtained from depth sensors. This paper presen...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/9/3531 |
| _version_ | 1797502818291023872 |
|---|---|
| author | Karolis Ryselis Tomas Blažauskas Robertas Damaševičius Rytis Maskeliūnas |
| author_facet | Karolis Ryselis Tomas Blažauskas Robertas Damaševičius Rytis Maskeliūnas |
| author_sort | Karolis Ryselis |
| collection | DOAJ |
| description | The identification of human activities from videos is important for many applications. For such a task, three-dimensional (3D) depth images or image sequences (videos) can be used, which represent the positioning information of the objects in a 3D scene obtained from depth sensors. This paper presents a framework to create foreground–background masks from depth images for human body segmentation. The framework can be used to speed up the manual depth image annotation process with no semantics known beforehand and can apply segmentation using a performant algorithm while the user only adjusts the parameters, or corrects the automatic segmentation results, or gives it hints by drawing a boundary of the desired object. The approach has been tested using two different datasets with a human in a real-world closed environment. The solution has provided promising results in terms of reducing the manual segmentation time from the perspective of the processing time as well as the human input time. |
| first_indexed | 2024-03-10T03:41:34Z |
| format | Article |
| id | doaj.art-f592979cf189438295c20a01ec314281 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:41:34Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f592979cf189438295c20a01ec3142812023-11-23T09:19:50ZengMDPI AGSensors1424-82202022-05-01229353110.3390/s22093531Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor ImagesKarolis Ryselis0Tomas Blažauskas1Robertas Damaševičius2Rytis Maskeliūnas3Faculty of Informatics, Kaunas University of Technology, 44249 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, 44249 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, 44249 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, 44249 Kaunas, LithuaniaThe identification of human activities from videos is important for many applications. For such a task, three-dimensional (3D) depth images or image sequences (videos) can be used, which represent the positioning information of the objects in a 3D scene obtained from depth sensors. This paper presents a framework to create foreground–background masks from depth images for human body segmentation. The framework can be used to speed up the manual depth image annotation process with no semantics known beforehand and can apply segmentation using a performant algorithm while the user only adjusts the parameters, or corrects the automatic segmentation results, or gives it hints by drawing a boundary of the desired object. The approach has been tested using two different datasets with a human in a real-world closed environment. The solution has provided promising results in terms of reducing the manual segmentation time from the perspective of the processing time as well as the human input time.https://www.mdpi.com/1424-8220/22/9/3531human body segmentationdepth imagesimage processingpoint cloud |
| spellingShingle | Karolis Ryselis Tomas Blažauskas Robertas Damaševičius Rytis Maskeliūnas Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images Sensors human body segmentation depth images image processing point cloud |
| title | Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images |
| title_full | Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images |
| title_fullStr | Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images |
| title_full_unstemmed | Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images |
| title_short | Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images |
| title_sort | computer aided depth video stream masking framework for human body segmentation in depth sensor images |
| topic | human body segmentation depth images image processing point cloud |
| url | https://www.mdpi.com/1424-8220/22/9/3531 |
| work_keys_str_mv | AT karolisryselis computeraideddepthvideostreammaskingframeworkforhumanbodysegmentationindepthsensorimages AT tomasblazauskas computeraideddepthvideostreammaskingframeworkforhumanbodysegmentationindepthsensorimages AT robertasdamasevicius computeraideddepthvideostreammaskingframeworkforhumanbodysegmentationindepthsensorimages AT rytismaskeliunas computeraideddepthvideostreammaskingframeworkforhumanbodysegmentationindepthsensorimages |