R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild
<p dir="ltr">Semantic understanding of roadways is a key enabling factor for safe autonomous driving. However, existing autonomous driving datasets provide well-structured urban roads while ignoring unstructured roadways containing distress, potholes, water puddles, and various kinds...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , |
| منشور في: |
2024
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1864513541061476352 |
|---|---|
| author | Muhammad Atif Butt (10849980) |
| author2 | Hassan Ali (3348749) Adnan Qayyum (16875936) Waqas Sultani (22052018) Ala Al-Fuqaha (4434340) Junaid Qadir (16494902) |
| author2_role | author author author author author |
| author_facet | Muhammad Atif Butt (10849980) Hassan Ali (3348749) Adnan Qayyum (16875936) Waqas Sultani (22052018) Ala Al-Fuqaha (4434340) Junaid Qadir (16494902) |
| author_role | author |
| dc.creator.none.fl_str_mv | Muhammad Atif Butt (10849980) Hassan Ali (3348749) Adnan Qayyum (16875936) Waqas Sultani (22052018) Ala Al-Fuqaha (4434340) Junaid Qadir (16494902) |
| dc.date.none.fl_str_mv | 2024-08-23T09:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1007/s11263-024-02207-3 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/R_sup_2_sup_S100K_Road-Region_Segmentation_Dataset_for_Semi-supervised_Autonomous_Driving_in_the_Wild/29907188 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Autonomous driving Semantic segmentation Semi-supervised learning |
| dc.title.none.fl_str_mv | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">Semantic understanding of roadways is a key enabling factor for safe autonomous driving. However, existing autonomous driving datasets provide well-structured urban roads while ignoring unstructured roadways containing distress, potholes, water puddles, and various kinds of road patches i.e., earthen, gravel etc. To this end, we introduce Road Region Segmentation dataset (R<sup>2</sup>S100K)—a large-scale dataset and benchmark for training and evaluation of road segmentation in aforementioned challenging unstructured roadways. R<sup>2</sup>S100K comprises 100K images extracted from a large and diverse set of video sequences covering more than 1000 km of roadways. Out of these 100K privacy respecting images, 14,000 images have fine pixel-labeling of road regions, with 86,000 unlabeled images that can be leveraged through semi-supervised learning methods. Alongside, we present an Efficient Data Sampling based self-training framework to improve learning by leveraging unlabeled data. Our experimental results demonstrate that the proposed method significantly improves learning methods in generalizability and reduces the labeling cost for semantic segmentation tasks. Our benchmark will be publicly available to facilitate future research at https://r2s100k.github.io/.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal of Computer Vision<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s11263-024-02207-3" target="_blank">https://dx.doi.org/10.1007/s11263-024-02207-3</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_674e8f2064d9c776e29ba2bd36cf7c2e |
| identifier_str_mv | 10.1007/s11263-024-02207-3 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/29907188 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the WildMuhammad Atif Butt (10849980)Hassan Ali (3348749)Adnan Qayyum (16875936)Waqas Sultani (22052018)Ala Al-Fuqaha (4434340)Junaid Qadir (16494902)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationMachine learningAutonomous drivingSemantic segmentationSemi-supervised learning<p dir="ltr">Semantic understanding of roadways is a key enabling factor for safe autonomous driving. However, existing autonomous driving datasets provide well-structured urban roads while ignoring unstructured roadways containing distress, potholes, water puddles, and various kinds of road patches i.e., earthen, gravel etc. To this end, we introduce Road Region Segmentation dataset (R<sup>2</sup>S100K)—a large-scale dataset and benchmark for training and evaluation of road segmentation in aforementioned challenging unstructured roadways. R<sup>2</sup>S100K comprises 100K images extracted from a large and diverse set of video sequences covering more than 1000 km of roadways. Out of these 100K privacy respecting images, 14,000 images have fine pixel-labeling of road regions, with 86,000 unlabeled images that can be leveraged through semi-supervised learning methods. Alongside, we present an Efficient Data Sampling based self-training framework to improve learning by leveraging unlabeled data. Our experimental results demonstrate that the proposed method significantly improves learning methods in generalizability and reduces the labeling cost for semantic segmentation tasks. Our benchmark will be publicly available to facilitate future research at https://r2s100k.github.io/.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal of Computer Vision<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s11263-024-02207-3" target="_blank">https://dx.doi.org/10.1007/s11263-024-02207-3</a></p>2024-08-23T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s11263-024-02207-3https://figshare.com/articles/journal_contribution/R_sup_2_sup_S100K_Road-Region_Segmentation_Dataset_for_Semi-supervised_Autonomous_Driving_in_the_Wild/29907188CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/299071882024-08-23T09:00:00Z |
| spellingShingle | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild Muhammad Atif Butt (10849980) Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Autonomous driving Semantic segmentation Semi-supervised learning |
| status_str | publishedVersion |
| title | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild |
| title_full | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild |
| title_fullStr | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild |
| title_full_unstemmed | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild |
| title_short | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild |
| title_sort | R<sup>2</sup>S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild |
| topic | Information and computing sciences Artificial intelligence Computer vision and multimedia computation Machine learning Autonomous driving Semantic segmentation Semi-supervised learning |