He, Z;
He, H;
(2018)
Unsupervised Multi-Object Detection for Video Surveillance Using Memory-Based Recurrent Attention Networks.
Symmetry
, 10
(9)
, Article 375. 10.3390/sym10090375.
Preview |
Text
symmetry-10-00375.pdf - Published Version Download (4MB) | Preview |
Abstract
Nowadays, video surveillance has become ubiquitous with the quick development of artificial intelligence. Multi-object detection (MOD) is a key step in video surveillance and has been widely studied for a long time. The majority of existing MOD algorithms follow the “divide and conquer” pipeline and utilize popular machine learning techniques to optimize algorithm parameters. However, this pipeline is usually suboptimal since it decomposes the MOD task into several sub-tasks and does not optimize them jointly. In addition, the frequently used supervised learning methods rely on the labeled data which are scarce and expensive to obtain. Thus, we propose an end-to-end Unsupervised Multi-Object Detection framework for video surveillance, where a neural model learns to detect objects from each video frame by minimizing the image reconstruction error. Moreover, we propose a Memory-Based Recurrent Attention Network to ease detection and training. The proposed model was evaluated on both synthetic and real datasets, exhibiting its potential.
| Type: | Article |
|---|---|
| Title: | Unsupervised Multi-Object Detection for Video Surveillance Using Memory-Based Recurrent Attention Networks |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.3390/sym10090375 |
| Publisher version: | https://doi.org/10.3390/sym10090375 |
| Language: | English |
| Additional information: | This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ |
| Keywords: | Science & Technology, Multidisciplinary Sciences, Science & Technology - Other Topics, object detection, unsupervised learning, recurrent network, memory, attention, video surveillance, RECOGNITION |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10063696 |
Archive Staff Only
 |
View Item |
