Gaussian Process for Activity Modeling and Anomaly Detection

Liao, Wuping; Rosenhahn, Bodo; Yang, Michael Ying

doi:10.5194/isprsannals-ii-3-w5-467-2015

Cited by 9 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This addresses weaknesses of previous methods that struggle either due to restrictions of overly simplified data representations or limited distribution models and enables our method to set state-of-the-art performance on MVTec AD and MTD. In the future, the concept could be refined for video anomaly detection [40,25].…”

Section: Discussionmentioning

confidence: 99%

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

Rudolph¹,

Wehrbein²,

Rosenhahn³

et al. 2021

Preprint

View full text Add to dashboard Cite

In industrial manufacturing processes, errors frequently occur at unpredictable times and in unknown manifestations. We tackle the problem of automatic defect detection without requiring any image samples of defective parts. Recent works model the distribution of defect-free image data, using either strong statistical priors or overly simplified data representations. In contrast, our approach handles fine-grained representations incorporating the global and local image context while flexibly estimating the density. To this end, we propose a novel fully convolutional cross-scale normalizing flow (CS-Flow) that jointly processes multiple feature maps of different scales. Using normalizing flows to assign meaningful likelihoods to input samples allows for efficient defect detection on image-level. Moreover, due to the preserved spatial arrangement the latent space of the normalizing flow is interpretable which enables to localize defective regions in the image. Our work sets a new stateof-the-art in image-level defect detection on the benchmark datasets Magnetic Tile Defects and MVTec AD showing a 100% AUROC on 4 out of 15 classes.

show abstract

Section: Discussionmentioning

confidence: 99%

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

Rudolph¹,

Wehrbein²,

Rosenhahn³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the future we plan to refine the concept in order to find anomalies in video data comparable to [29,20].…”

Section: Discussionmentioning

confidence: 99%

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

Rudolph¹,

Wandt²,

Rosenhahn³

2020

Preprint

View full text Add to dashboard Cite

The detection of manufacturing errors is crucial in fabrication processes to ensure product quality and safety standards. Since many defects occur very rarely and their characteristics are mostly unknown a priori, their detection is still an open research question. To this end, we propose Dif-ferNet: It leverages the descriptiveness of features extracted by convolutional neural networks to estimate their density using normalizing flows. Normalizing flows are well-suited to deal with low dimensional data distributions. However, they struggle with the high dimensionality of images. Therefore, we employ a multi-scale feature extractor which enables the normalizing flow to assign meaningful likelihoods to the images. Based on these likelihoods we develop a scoring function that indicates defects. Moreover, propagating the score back to the image enables pixel-wise localization. To achieve a high robustness and performance we exploit multiple transformations in training and evaluation. In contrast to most other methods, ours does not require a large number of training samples and performs well with as low as 16 images. We demonstrate the superior performance over existing approaches on the challenging and newly proposed MVTec AD [4] and Magnetic Tile Defects [14] datasets.

show abstract

“…It's also recommended to multiply the arbitrary values by small scalar similar as to make the activation units active and be on the regions where activation functions ' derivations aren't close to zero. After forward propagation, the cost function( L) is calculated which is the Mean Square Error( MSE) between the vaticination Y ' and the ground verity markers Y ( 19). 𝐿 = 1 𝑛 Σ( 𝑌− 𝑌 ′) 2 2) The thing of the neural network is to make L close to zero, hence making Y and Y ' nearly the same, which mean making the network classify the input cases rightly.…”

Section: Neural Networkmentioning

confidence: 99%

Detection of Anomalous Behaviour in an Examination Hall Towards Automated Proctoring

2023

IRJMETS

View full text Add to dashboard Cite

The anomalous behaviour is hard to be detected simultaneously in a complex scene such as detecting abnormal movements of examinees in examination rooms. Modelling activities of moving objects and classifying them as normal or anomalous is a major research problem in video analysis. In this paper, we make use of the of neural networks and Gaussian distribution to help solve this problem by building a prototype of a monitoring system that consists of three stages; face detection using haar cascade detector, suspicious state detection using a neural network and lastly anomaly detection based on the Gaussian distribution. The main idea is to decide on whether the student is in a suspicious state or not using a trained neural network and then decide that a student performs an anomalous behaviour based on how many times he was found in a suspicious state in a defined time duration. The complete system has been tested on a proprietary data set achieving 97% accuracy with 3% false negative rate.

show abstract

Gaussian Process for Activity Modeling and Anomaly Detection

Cited by 9 publications

References 22 publications

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

Detection of Anomalous Behaviour in an Examination Hall Towards Automated Proctoring

Contact Info

Product

Resources

About