A Panoptic Segmentation for Indoor Environments using MaskDINO: An Experiment on the Impact of Contrast
Robot perception involves recognizing the surrounding environment, particularly in indoor spaces like kitchens, classrooms, and dining areas. This recognition is crucial for tasks such as object identification. Objects in indoor environments can be categorized into "things," with fixed an...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Computer Vision Center Press
2025-01-01
|
| Series: | ELCVIA Electronic Letters on Computer Vision and Image Analysis |
| Subjects: | |
| Online Access: | https://elcvia.cvc.uab.cat/article/view/1861 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087998889459712 |
|---|---|
| author | Khalisha Putri Ika Candradewi - |
| author_facet | Khalisha Putri Ika Candradewi - |
| author_sort | Khalisha Putri |
| collection | DOAJ |
| description |
Robot perception involves recognizing the surrounding environment, particularly in indoor spaces like kitchens, classrooms, and dining areas. This recognition is crucial for tasks such as object identification. Objects in indoor environments can be categorized into "things," with fixed and countable shapes (e.g., tables, chairs), and "stuff," which lack a fixed shape and cannot be counted (e.g., sky, walls). Object detection and instance segmentation methods excel in identifying "things," with instance segmentation providing more detailed representations than object detection. However, semantic segmentation can identify both "things" and "stuff" but lacks segmentation at the object level. Panoptic segmentation, a fusion of both methods, offers comprehensive object and stuff identification and object-level segmentation. Considerations need to be made regarding the variabilities of room conditions in contrast to implementing panoptic segmentation indoors. High or low contrast in the room potentially reduces the clarity of the shape of an object, thus affecting the segmentation results of that object. We experimented with how contrast varieties impact the panoptic segmentation performance using the MaskDINO model, the first on the panoptic quality (PQ) leaderboard. We then improved the model generalization on the various contrasts by re-optimizing it using a contrast-augmented dataset.
|
| format | Article |
| id | doaj-art-6d16caa82bea4928aba0a4822035b6fa |
| institution | Kabale University |
| issn | 1577-5097 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Computer Vision Center Press |
| record_format | Article |
| series | ELCVIA Electronic Letters on Computer Vision and Image Analysis |
| spelling | doaj-art-6d16caa82bea4928aba0a4822035b6fa2025-02-06T02:27:14ZengComputer Vision Center PressELCVIA Electronic Letters on Computer Vision and Image Analysis1577-50972025-01-0124110.5565/rev/elcvia.1861A Panoptic Segmentation for Indoor Environments using MaskDINO: An Experiment on the Impact of ContrastKhalisha PutriIka Candradewi -0Universitas Gadjah Mada Robot perception involves recognizing the surrounding environment, particularly in indoor spaces like kitchens, classrooms, and dining areas. This recognition is crucial for tasks such as object identification. Objects in indoor environments can be categorized into "things," with fixed and countable shapes (e.g., tables, chairs), and "stuff," which lack a fixed shape and cannot be counted (e.g., sky, walls). Object detection and instance segmentation methods excel in identifying "things," with instance segmentation providing more detailed representations than object detection. However, semantic segmentation can identify both "things" and "stuff" but lacks segmentation at the object level. Panoptic segmentation, a fusion of both methods, offers comprehensive object and stuff identification and object-level segmentation. Considerations need to be made regarding the variabilities of room conditions in contrast to implementing panoptic segmentation indoors. High or low contrast in the room potentially reduces the clarity of the shape of an object, thus affecting the segmentation results of that object. We experimented with how contrast varieties impact the panoptic segmentation performance using the MaskDINO model, the first on the panoptic quality (PQ) leaderboard. We then improved the model generalization on the various contrasts by re-optimizing it using a contrast-augmented dataset. https://elcvia.cvc.uab.cat/article/view/1861MaskDINOIndoor EnvironmentPanoptic Segmentation |
| spellingShingle | Khalisha Putri Ika Candradewi - A Panoptic Segmentation for Indoor Environments using MaskDINO: An Experiment on the Impact of Contrast ELCVIA Electronic Letters on Computer Vision and Image Analysis MaskDINO Indoor Environment Panoptic Segmentation |
| title | A Panoptic Segmentation for Indoor Environments using MaskDINO: An Experiment on the Impact of Contrast |
| title_full | A Panoptic Segmentation for Indoor Environments using MaskDINO: An Experiment on the Impact of Contrast |
| title_fullStr | A Panoptic Segmentation for Indoor Environments using MaskDINO: An Experiment on the Impact of Contrast |
| title_full_unstemmed | A Panoptic Segmentation for Indoor Environments using MaskDINO: An Experiment on the Impact of Contrast |
| title_short | A Panoptic Segmentation for Indoor Environments using MaskDINO: An Experiment on the Impact of Contrast |
| title_sort | panoptic segmentation for indoor environments using maskdino an experiment on the impact of contrast |
| topic | MaskDINO Indoor Environment Panoptic Segmentation |
| url | https://elcvia.cvc.uab.cat/article/view/1861 |
| work_keys_str_mv | AT khalishaputri apanopticsegmentationforindoorenvironmentsusingmaskdinoanexperimentontheimpactofcontrast AT ikacandradewi apanopticsegmentationforindoorenvironmentsusingmaskdinoanexperimentontheimpactofcontrast AT khalishaputri panopticsegmentationforindoorenvironmentsusingmaskdinoanexperimentontheimpactofcontrast AT ikacandradewi panopticsegmentationforindoorenvironmentsusingmaskdinoanexperimentontheimpactofcontrast |