Local Anomaly Detection in Videos using Object-Centric Adversarial Learning

11/13/2020
by   Pankaj Raj Roy, et al.
0

We propose a novel unsupervised approach based on a two-stage object-centric adversarial framework that only needs object regions for detecting frame-level local anomalies in videos. The first stage consists in learning the correspondence between the current appearance and past gradient images of objects in scenes deemed normal, allowing us to either generate the past gradient from current appearance or the reverse. The second stage extracts the partial reconstruction errors between real and generated images (appearance and past gradient) with normal object behaviour, and trains a discriminator in an adversarial fashion. In inference mode, we employ the trained image generators with the adversarially learned binary classifier for outputting region-level anomaly detection scores. We tested our method on four public benchmarks, UMN, UCSD, Avenue and ShanghaiTech and our proposed object-centric adversarial approach yields competitive or even superior results compared to state-of-the-art methods.

READ FULL TEXT

page 2

page 11

research
06/10/2021

Predicting Next Local Appearance for Video Anomaly Detection

We present a local anomaly detection method in videos. As opposed to mos...
research
05/03/2022

Object Class Aware Video Anomaly Detection through Image Translation

Semi-supervised video anomaly detection (VAD) methods formulate the task...
research
03/09/2023

Multi-level Memory-augmented Appearance-Motion Correspondence Framework for Video Anomaly Detection

Frame prediction based on AutoEncoder plays a significant role in unsupe...
research
08/17/2019

Anomaly Detection in Video Sequence with Appearance-Motion Correspondence

Anomaly detection in surveillance videos is currently a challenge becaus...
research
03/07/2022

Object-centric and memory-guided normality reconstruction for video anomaly detection

This paper addresses video anomaly detection problem for videosurveillan...
research
11/28/2022

Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation

We propose a very fast frame-level model for anomaly detection in video,...
research
05/27/2022

Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos

Unsupervised object-centric learning aims to represent the modular, comp...

Please sign up or login with your details

Forgot password? Click here to reset