End-to-End Deep One-Class Learning for Anomaly Detection in UAV Video Stream

Abstract

In recent years, the use of drones for surveillance tasks has been on the rise worldwide. However, in the context of anomaly detection, only normal events are available for the learning process. Therefore, the implementation of a generative learning method in an unsupervised mode to solve this problem becomes fundamental. In this context, we propose a new end-to-end architecture capable of generating optical flow images from original UAV images and extracting compact spatio-temporal characteristics for anomaly detection purposes. It is designed with a custom loss function as a sum of three terms, the reconstruction loss (Rl), the generation loss (Gl) and the compactness loss (Cl) to ensure an efficient classification of the “deep-one” class. In addition, we propose to minimize the effect of UAV motion in video processing by applying background subtraction on optical flow images. We tested our method on very complex datasets called the mini-drone video dataset, and obtained results surpassing existing techniques’ performances with an AUC of 85.3.

Anomaly detection using edge computing in video surveillance system: review

“…One-class classifiers [ 18 , 19 ] have evolved as state of the art for anomaly detection in the research community in recent years. One-class classification (OCC) is a technique where the model is trained using only one class that is positive class [ 37 , 148 ]. [ 90 ] proposes a feature extractor network and a CNN-based OCC to detect anomalies using binary cross-entropy as the loss function.…”

“…To extract more features and increase the accuracy of prediction, Deep CNN networks are employed which have multiple hidden layers [ 37 ]. The deep learning approaches typically fall within a family of encoder–decoder models: an encoder that learns to generate an internal representation of the input data, and a decoder that attempts to reconstruct the original input based on this internal representation.…”

“…As the information regarding negative class is unavailable, OCC focuses on maximizing the boundary with respect to the origin [ 148 ]. Predominantly used for outlier detection, anomaly detection, and novelty detection, OCC can be further categorized as: boundary methods [ 18 , 19 ] which define a specific margin, generative approaches [ 37 ] which mainly use generative adversarial networks, and Discriminative approaches [ 90 ] which depend on the loss function.…”

Low-Altitude Aerial Video Surveillance via One-Class SVM Anomaly Detection from Textural Features in UAV Images

“…With the widespread use of drones (generally of the UAV family), especially in the last years, surveillance with UAVs is increasing in its popularity, and it is becoming a hot research field. The proposal in [102] presents a novel end-to-end strategy based on unsupervised generative learning applied on deep one-class classification. The system has two main goals.…”

Image and Video Forensics

“…Other contributions to this special session have addressed the problem of anomaly detection in unmanned aerial vehicle (UAV) video streams. Hamdi et al [15] proposed an end-to-end architecture capable of generating optical flow images from original UAV images and extracting compact spatio-temporal characteristics for anomaly detection purposes. Karantaidis et al [16] investigated the challenging problem of electric network frequency (ENF) estimation in static and non-static digital video recordings, designing an automated approach based on simple linear iterative clustering via the exploitation of areas with similar characteristics.…”