Multi-Perspective Anomaly Detection

Jakob, Peter M.; Madan, Manav; Schmid-Schirling, Tobias; Valada, Abhinav

doi:10.3390/s21165311

Cited by 8 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors discarded the discriminator during testing [16] because it did not improve the anomaly score. There is a lack of work on anomaly detection using multiple views [17]. In [18], the author detects facial micro-expressions to detect anomalies in the dataset given in [19].…”

Section: Related Workmentioning

confidence: 99%

Anomaly detection using deep learning based model with feature attention

Nayak,

Chaudhari

2024

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">Anomaly detection is a difficult problem with numerous industrial applications, such as analyzing the quality of objects using images. Anomaly detection is the process of identifying outliers in a given dataset. Recently, machine learning approaches to computer vision problems have outperformed classical state-of-the-art approaches. Anomaly detection problems can be solved using supervised approaches. However, labelled datasets are hard to obtain. Thus, many researchers have taken an unsupervised approach to solving the problem of anomaly detection. In this study, we use an adversarial auto encoder model as a base model and create a custom model to detect anomalies in images and videos. The model was trained exclusively on normal data. The modified national institute of standards and technology database (MNIST) dataset achieved an area under curve (AUC) score of 0.872 for anomaly detection, while the University of California San Diego (UCSD) anomaly dataset (Video dataset) achieved an AUC score of 0.74 for Ped1 and 0.87 for Ped2. To calculate the anomaly score, the concept of attention weights is combined with the reconstruction loss, and the proposed method outperformed other similar methods designed for the same problem. However, the usefulness of the proposed model was demonstrated through the detection of anomalies, and the model is still being improved for use in real-world situations.</span>

show abstract

Section: Related Workmentioning

confidence: 99%

Anomaly detection using deep learning based model with feature attention

Nayak,

Chaudhari

2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Firstly, the optical flow frame is encoded to obtain the output z and the memory module is used to convert z into a query Z * . The query obtained from the memory network is shown in Formula (1).…”

Section: Video Optical Flow Reconstruction With Memory Mechanismmentioning

confidence: 99%

“…With the development of sensors, video surveillance and sensor networks are widely used in various fields, such as traffic monitoring, environmental monitoring, industrial control, etc. [ 1 , 2 , 3 ]. The goal of video surveillance and sensor networks is to achieve accurate monitoring and detection of anomalous targets.…”

Section: Introductionmentioning

confidence: 99%

A Novel Unsupervised Video Anomaly Detection Framework Based on Optical Flow Reconstruction and Erased Frame Prediction

Huang

Zhao

Gao

et al. 2023

Sensors

View full text Add to dashboard Cite

Reconstruction-based and prediction-based approaches are widely used for video anomaly detection (VAD) in smart city surveillance applications. However, neither of these approaches can effectively utilize the rich contextual information that exists in videos, which makes it difficult to accurately perceive anomalous activities. In this paper, we exploit the idea of a training model based on the “Cloze Test” strategy in natural language processing (NLP) and introduce a novel unsupervised learning framework to encode both motion and appearance information at an object level. Specifically, to store the normal modes of video activity reconstructions, we first design an optical stream memory network with skip connections. Secondly, we build a space–time cube (STC) for use as the basic processing unit of the model and erase a patch in the STC to form the frame to be reconstructed. This enables a so-called ”incomplete event (IE)” to be completed. On this basis, a conditional autoencoder is utilized to capture the high correspondence between optical flow and STC. The model predicts erased patches in IEs based on the context of the front and back frames. Finally, we employ a generating adversarial network (GAN)-based training method to improve the performance of VAD. By distinguishing the predicted erased optical flow and erased video frame, the anomaly detection results are shown to be more reliable with our proposed method which can help reconstruct the original video in IE. Comparative experiments conducted on the benchmark UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets demonstrate AUROC scores reaching 97.7%, 89.7%, and 75.8%, respectively.

show abstract

“…In complex environments, the considerable visual disparities between images from different perspectives render the fusion process difficult. In such contexts, the flexibility and powerful pattern recognition capabilities of deep learning become particularly crucial [7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Exploring the Application of Deep Learning in Multi-View Image Fusion in Complex Environments

Luo,

Shao

2023

View full text Add to dashboard Cite

The advancement of technology has unveiled the immense potential of deep learning across various domains, notably in multi-view image fusion within complex environments. Multiview image fusion aims to merge images from different perspectives to garner more comprehensive and detailed information. Despite this, challenges persist in such fusion under complex conditions, particularly when confronting significant variations in perspective and intricate lighting scenarios. Predominant deep learning approaches, reliant on extensive annotated data, grapple with high computational complexity when processing large-scale and high-dimensional image data, thus hindering real-time applicability. This exploration primarily focuses on two facets: multi-view image registration based on the moment of inertia axis method, and multi-view image fusion utilizing morphological decomposition and attention feature integration. The objective is to enhance the efficiency and effectiveness of multi-view image fusion in complex settings, propelling the practical advancement of deep learning technologies.

show abstract

Multi-Perspective Anomaly Detection

Cited by 8 publications

References 20 publications

Anomaly detection using deep learning based model with feature attention

Anomaly detection using deep learning based model with feature attention

A Novel Unsupervised Video Anomaly Detection Framework Based on Optical Flow Reconstruction and Erased Frame Prediction

Exploring the Application of Deep Learning in Multi-View Image Fusion in Complex Environments

Contact Info

Product

Resources

About