Single-Frame-Based Deep View Synchronization for Unsynchronized Multicamera Surveillance
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 10653-10667 |
Number of pages | 15 |
Journal / Publication | IEEE Transactions on Neural Networks and Learning Systems |
Volume | 34 |
Issue number | 12 |
Online published | 16 May 2022 |
Publication status | Published - Dec 2023 |
Link(s)
DOI | DOI |
---|---|
Attachment(s) | Documents
Publisher's Copyright Statement
|
Link to Scopus | https://www.scopus.com/record/display.uri?eid=2-s2.0-85130483656&origin=recordpage |
Permanent Link | https://scholars.cityu.edu.hk/en/publications/publication(aa2aedf8-43a6-4a0d-b7f1-41a655b2e593).html |
Abstract
Multicamera surveillance has been an active research topic for understanding and modeling scenes. Compared to a single camera, multicameras provide larger field-of-view and more object cues, and the related applications are multiview counting, multiview tracking, 3-D pose estimation or 3-D reconstruction, and so on. It is usually assumed that the cameras are all temporally synchronized when designing models for these multicamera-based tasks. However, this assumption is not always valid, especially for multicamera systems with network transmission delay and low frame rates due to limited network bandwidth, resulting in desynchronization of the captured frames across cameras. To handle the issue of unsynchronized multicameras, in this article, we propose a synchronization model that works in conjunction with existing deep neural network (DNN)-based multiview models, thus avoiding the redesign of the whole model. We consider two variants of the model, based on where in the pipeline the synchronization occurs, scene-level synchronization and camera-level synchronization. The view synchronization step and the task-specific view fusion and prediction step are unified in the same framework and trained in an end-to-end fashion. Our view synchronization models are applied to different DNNs-based multicamera vision tasks under the unsynchronized setting, including multiview counting and 3-D pose estimation, and achieve good performance compared to baselines.
Research Area(s)
- Synchronization, Cameras, Task analysis, Pose estimation, Computational modeling, Geometry, Crowd counting, deep learning, image matching, pose estimation, surveillance, VIDEO SYNCHRONIZATION
Bibliographic Note
Research Unit(s) information for this publication is provided by the author(s) concerned.
Citation Format(s)
Single-Frame-Based Deep View Synchronization for Unsynchronized Multicamera Surveillance. / Zhang, Qi; Chan, Antoni B.
In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 34, No. 12, 12.2023, p. 10653-10667.
In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 34, No. 12, 12.2023, p. 10653-10667.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Download Statistics
No data available