Projects per year
Abstract
Detecting anomalies in surveillance videos has long been an important but unsolved problem. In particular, many existing solutions are overly sensitive to (often ephemeral) visual artifacts in the raw video data, resulting in false positives and fragmented detection regions. To overcome such sensitivity and to capture true anomalies with semantic significance, one natural idea is to seek validation from abstract representations of the videos. This paper introduces a framework of robust anomaly detection using multilevel representations of both intensity and motion data. The framework consists of three main components: 1) representation learning using Denoising Autoencoders, 2) level-wise representation generation using Conditional Generative Adversarial Networks, and 3) consolidating anomalous regions detected at each representation level. Our proposed multilevel detector shows a significant improvement in pixel-level Equal Error Rate, namely 11.35%, 12.32% and 4.31% improvement in UCSD Ped 1, UCSD Ped 2 and Avenue datasets respectively. In addition, the model allowed us to detect mislabeled anomalies in the UCDS Ped 1.
Original language | English |
---|---|
Title of host publication | Proceedings of AAAI19-Thirty-Third AAAI conference on Artificial Intelligence |
Editors | Pascal Van Hentenryck, Zhi-Hua Zhou |
Place of Publication | Palo Alto CA USA |
Publisher | Association for the Advancement of Artificial Intelligence (AAAI) |
Pages | 5216-5223 |
Number of pages | 8 |
ISBN (Electronic) | 9781577358091 |
DOIs | |
Publication status | Published - 2019 |
Event | AAAI Conference on Artificial Intelligence 2019 - Honolulu, United States of America Duration: 27 Jan 2019 → 1 Feb 2019 Conference number: 33rd https://aaai.org/Conferences/AAAI-19/ |
Publication series
Name | Proceedings of the AAAI Conference on Artificial Intelligence |
---|---|
Publisher | AAAI Press |
Number | 1 |
Volume | 33 |
ISSN (Print) | 2159-5399 |
ISSN (Electronic) | 2374-3468 |
Conference
Conference | AAAI Conference on Artificial Intelligence 2019 |
---|---|
Abbreviated title | AAAI 2019 |
Country/Territory | United States of America |
City | Honolulu |
Period | 27/01/19 → 1/02/19 |
Internet address |
Projects
- 1 Finished
-
Stay Well: Analysing Lifestyle Data from Smart Monitoring Devices (ARC DP)
Phung, D., Venkatesh, S. & Kumar, M.
7/06/18 → 31/07/19
Project: Research