https://scholars.lib.ntu.edu.tw/handle/123456789/581451
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Chou Y.-S | en_US |
dc.contributor.author | Wang C.-Y | en_US |
dc.contributor.author | SHOU-DE LIN | en_US |
dc.contributor.author | Liao H.-Y.M. | en_US |
dc.creator | Chou Y.-S;Wang C.-Y;Lin S.-D;Liao H.-Y.M. | - |
dc.date.accessioned | 2021-09-02T00:08:53Z | - |
dc.date.available | 2021-09-02T00:08:53Z | - |
dc.date.issued | 2020 | - |
dc.identifier.issn | 15224880 | - |
dc.identifier.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85098669794&doi=10.1109%2fICIP40778.2020.9190802&partnerID=40&md5=43eb83516d7b49991e7ba9687b2a9f47 | - |
dc.identifier.uri | https://scholars.lib.ntu.edu.tw/handle/123456789/581451 | - |
dc.description.abstract | In recent years, deep learning has made dramatic advances in computer vision field, especially in improving the performance of object detection as well as instance semantic segmentation. Still, multi-object tracking (MOT) remains a very challenging issue. Even in state-of-the-art deep learning-based object detectors, a preferred paradigm for MOT: tracking-by-detection, can only slightly improve the tracking performance. Pixel-level information is considered more precise and useful for tracking performance improvement than using conventional information, such as foreground or background content in a bounding box. However, the performance of current state-of-the-art models for automatically annotating pixel-level information is still far from the expectation of human beings. Therefore, we shall explore how multi-object tracking and segmentation (MOTS) is affected when the information obtained after applying instance semantic segmentation is incomplete. We propose a mask-guided two-streamed augmentation learning (MGTSAL) algorithm, which can be applied to TrackR-CNN to alleviate significant drop of MOTS performance when encountering incompletely segmented information. We evaluate the proposed approach on MOTS KITTI dataset, and our approach outperforms the baseline model TrackR-CNN in all our experimental settings. The promising experimental results and ablation study validate the effectiveness of the proposed approach. ? 2020 IEEE. | - |
dc.relation.ispartof | Proceedings - International Conference on Image Processing, ICIP | - |
dc.subject | Deep learning; Image segmentation; Object detection; Object recognition; Pixels; Semantics; Baseline models; Bounding box; Multi-object tracking; Object detectors; Semantic segmentation; State of the art; Tracking by detections; Tracking performance; Object tracking | - |
dc.title | How Incompletely Segmented Information Affects Multi-Object Tracking and Segmentation (MOTS) | en_US |
dc.type | conference paper | en |
dc.identifier.doi | 10.1109/ICIP40778.2020.9190802 | - |
dc.identifier.scopus | 2-s2.0-85098669794 | - |
dc.relation.pages | 2086-2090 | - |
dc.relation.journalvolume | 2020-October | - |
item.cerifentitytype | Publications | - |
item.fulltext | no fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_5794 | - |
item.openairetype | conference paper | - |
item.grantfulltext | none | - |
crisitem.author.dept | Networking and Multimedia | - |
crisitem.author.dept | Computer Science and Information Engineering | - |
crisitem.author.dept | FinTech Center | - |
crisitem.author.dept | Center for Artificial Intelligence and Advanced Robotics | - |
crisitem.author.orcid | 0000-0001-9970-1250 | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | Others: University-Level Research Centers | - |
crisitem.author.parentorg | Others: University-Level Research Centers | - |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。