Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914245892898816 |
|---|---|
| author | Maag, Kira Chan, Robin Uhlemeyer, Svenja Kowol, Kamil Gottschalk, Hanno |
| author_facet | Maag, Kira Chan, Robin Uhlemeyer, Svenja Kowol, Kamil Gottschalk, Hanno |
| contents | In this work we present two video test data sets for the novel computer vision (CV) task of out of distribution tracking (OOD tracking). Here, OOD objects are understood as objects with a semantic class outside the semantic space of an underlying image segmentation algorithm, or an instance within the semantic space which however looks decisively different from the instances contained in the training data. OOD objects occurring on video sequences should be detected on single frames as early as possible and tracked over their time of appearance as long as possible. During the time of appearance, they should be segmented as precisely as possible. We present the SOS data set containing 20 video sequences of street scenes and more than 1000 labeled frames with up to two OOD objects. We furthermore publish the synthetic CARLA-WildLife data set that consists of 26 video sequences containing up to four OOD objects on a single frame. We propose metrics to measure the success of OOD tracking and develop a baseline algorithm that efficiently tracks the OOD objects. As an application that benefits from OOD tracking, we retrieve OOD sequences from unlabeled videos of street scenes containing OOD objects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_02074 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects Maag, Kira Chan, Robin Uhlemeyer, Svenja Kowol, Kamil Gottschalk, Hanno Computer Vision and Pattern Recognition In this work we present two video test data sets for the novel computer vision (CV) task of out of distribution tracking (OOD tracking). Here, OOD objects are understood as objects with a semantic class outside the semantic space of an underlying image segmentation algorithm, or an instance within the semantic space which however looks decisively different from the instances contained in the training data. OOD objects occurring on video sequences should be detected on single frames as early as possible and tracked over their time of appearance as long as possible. During the time of appearance, they should be segmented as precisely as possible. We present the SOS data set containing 20 video sequences of street scenes and more than 1000 labeled frames with up to two OOD objects. We furthermore publish the synthetic CARLA-WildLife data set that consists of 26 video sequences containing up to four OOD objects on a single frame. We propose metrics to measure the success of OOD tracking and develop a baseline algorithm that efficiently tracks the OOD objects. As an application that benefits from OOD tracking, we retrieve OOD sequences from unlabeled videos of street scenes containing OOD objects. |
| title | Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2210.02074 |