Deep learning and handcrafted features for one-class anomaly detection in UAV video
- PDF / 1,647,927 Bytes
- 22 Pages / 439.642 x 666.49 pts Page_size
- 85 Downloads / 210 Views
Deep learning and handcrafted features for one-class anomaly detection in UAV video Amira Chriki1,2
· Haifa Touati1 · Hichem Snoussi3 · Farouk Kamoun2,4
Received: 18 March 2020 / Revised: 10 July 2020 / Accepted: 28 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Visual surveillance systems have recently captured the attention of the research community. Most of the proposed surveillance systems deal with stationary cameras. Nevertheless, these systems may reflect minor applicability in anomaly detection when multiple cameras are required. Lately, under technological progress in electronic and avionics systems, Unmanned Aerial Vehicles (UAVs) are increasingly used in a wide variety of urban missions. Especially, in the surveillance context, UAVs can be used as mobile cameras to overcome weaknesses of stationary cameras. One of the principal advantages that makes UAVs attractive is their ability to provide a new aerial perspective. Despite their numerous advantages, there are many difficulties associated with automatic anomalies detection by an UAV, as there is a lack in the proposed contributions describing anomaly detection in videos recorded by a drone. In this paper, we propose new anomaly detection techniques for assisting UAV based surveillance mission where videos are acquired by a mobile camera. To extract robust features from UAV videos, three different features extraction methods were used, namely a pretrained Convolutional Neural Network (CNN) and two popular handcrafted methods (Histogram of Oriented Gradient (HOG) and HOG3D). One Class Support Vector Machine (OCSVM) has been then applied for the unsupervised classification. Extensive experiments carried on a dataset containing videos taken by an UAV monitoring a car parking, prove the efficiency of the proposed techniques. Specifically, the quantitative results obtained using the challenging Area Under Curve (AUC) evaluation metric show that, despite the variation among them, the proposed methods achieve good results in comparison to the existing technique with an AUC = 0.78 at worst and an AUC = 0.93 at best. Keywords UAVs · Anomaly detection · Convolutional neural network · Handcrafted features · Unsupervised learning · One class classification
Amira Chriki
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
1 Introduction Lately, with the widespread use of surveillance cameras in public areas, visual surveillance systems have attracted increasing interest from the research community of military and urban security systems. Their effectiveness was proved in various fields, such as traffic monitoring, malicious and intrusion detection. Such systems aim to detect automatically potential suspicious items or signs of intrusion, and consequently generate a warning to a human operator. Without being context specific, this detection mainly consists of identifying changes between frames of the same scene but separated in time. These
Data Loading...
