Projects per year
Abstract
This paper sets out to investigate if semantic segmentation
can be used to achieve anonymity in video surveillance while maintaining
the ability to perform anomaly detection. The paper is centered around
finding the best model for segmenting the anomaly detection dataset
UCHK Avenue without semantic ground truth available. To do this, a
series of segmentation models pre-trained on ADE20K and Cityscapes
are evaluated against a custom semantic annotation of selected frames
from Avenue and the segmentation results are compared both quantitatively and qualitatively. The segmented dataset is then tested on a series
of different anomaly detection baselines and the results are compared
both in terms of global and anomaly specific accuracy. When comparing the anomaly detection accuracy for RGB and segmented data it
was found that anonymity in anomaly detection can be achieved at a
small cost in global accuracy but with better accuracy for some specific
anomalies.
can be used to achieve anonymity in video surveillance while maintaining
the ability to perform anomaly detection. The paper is centered around
finding the best model for segmenting the anomaly detection dataset
UCHK Avenue without semantic ground truth available. To do this, a
series of segmentation models pre-trained on ADE20K and Cityscapes
are evaluated against a custom semantic annotation of selected frames
from Avenue and the segmentation results are compared both quantitatively and qualitatively. The segmented dataset is then tested on a series
of different anomaly detection baselines and the results are compared
both in terms of global and anomaly specific accuracy. When comparing the anomaly detection accuracy for RGB and segmented data it
was found that anonymity in anomaly detection can be achieved at a
small cost in global accuracy but with better accuracy for some specific
anomalies.
Original language | English |
---|---|
Title of host publication | Advances in Visual Computing : 16th International Symposium, ISVC 2021, Virtual Event, October 4-6, 2021, Proceedings, Part II |
Editors | George Bebis, Vassilis Athitsos, Tong Yan, Manfred Lau, Frederick Li |
Number of pages | 123 |
Volume | 13018 |
Publisher | Springer |
Publication date | 2021 |
Pages | 110 |
ISBN (Print) | 978-3-030-90435-7 |
ISBN (Electronic) | 978-3-030-90436-4 |
DOIs | |
Publication status | Published - 2021 |
Event | 16th International Symposium on Visual Computing, ISVC 2021 - Virtual Online Duration: 4 Oct 2021 → 6 Oct 2021 |
Conference
Conference | 16th International Symposium on Visual Computing, ISVC 2021 |
---|---|
City | Virtual Online |
Period | 04/10/2021 → 06/10/2021 |
Series | Lecture Notes in Computer Science |
---|---|
ISSN | 0302-9743 |
Fingerprint
Dive into the research topics of 'Privacy-aware Anomaly Detection using Semantic Segmentation'. Together they form a unique fingerprint.Projects
- 1 Finished