Camera Tampering Detection using Generative Reference Model and Deep Learned Features

Mantini, Pranav; Shah, Shishir K.

doi:10.5220/0007392100850095

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Augmenting real images and videos with synthetic elements, on the other hand, bridges the gap much better between real and generated data, as only certain elements of the images are synthesized. Especially for surveillance purposes, such augmentations have been shown to produce good results for pedestrian anomalies [21], falling in water detection [24], camera tampering [22], and subtle anomalies such as dropping objects and animals in the frame, as seen in the work that the current paper is an extension of [20].…”

Section: Synthetic Datasetsmentioning

confidence: 99%

“…This synthetic data can be generated through the use of ready-built game worlds such as GTA [17,18] or full-city simulations [19]. Otherwise, they can be created through the augmentation of already existing real-world images with synthetic elements [20][21][22]. While most synthetic data augmentation relies on time-consuming processes, with weeks being spent on frame rendering in some cases [21,23], others, such as the works on responsive anomaly generation [20] and fall synthesis [24], are using real-time rendering game engines to speed up and streamline the process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

User-Centered Pipeline for Synthetic Augmentation of Anomaly Detection Datasets

Rosbak-Mortensen,

Jansen,

Muhlig

et al. 2024

Computers

View full text Add to dashboard Cite

Automatic anomaly detection plays a critical role in surveillance systems but requires datasets comprising large amounts of annotated data to train and evaluate models. Gathering and annotating these data is a labor-intensive task that can become costly. A way to circumvent this is to use synthetic data to augment anomalies directly into existing datasets. This far more diverse scenario can be created and come directly with annotations. This however also poses new issues for the computer-vision engineer and researcher end users, who are not readily familiar with 3D modeling, game development, or computer graphics methodologies and must rely on external specialists to use or tweak such pipelines. In this paper, we extend our previous work of an application that synthesizes dataset variations using 3D models and augments anomalies on real backgrounds using the Unity Engine. We developed a high-usability user interface for our application through a series of RITE experiments and evaluated the final product with the help of deep-learning specialists who provided positive feedback regarding its usability, accessibility, and user experience. Finally, we tested if the proposed solution can be used in the context of traffic surveillance by augmenting the train data from the challenging Street Scene dataset. We found that by using our synthetic data, we could achieve higher detection accuracy. We also propose the next steps to expand the proposed solution for better usability and render accuracy through the use of segmentation pre-processing.

show abstract

Section: Synthetic Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

User-Centered Pipeline for Synthetic Augmentation of Anomaly Detection Datasets

Rosbak-Mortensen,

Jansen,

Muhlig

et al. 2024

Computers

View full text Add to dashboard Cite

show abstract

“…As described in Section 1, we would like to solve the problem of robust estimation of the background and the foreground content from the video frames as described above. This step is intended as a preprocessing step to aid the segmentation and classification tasks, where one may use simple thresholding algorithms (Phansalkar et al, 2011) for segmentation or classification algorithms mentioned in Mantini and Shah (2019b). For demonstration purposes, we shall consider 2 short clips from UHCTD dataset to implement the proposed rSVDdpd algorithm as well as the usual SVD algorithm.…”

Section: Video Surveillance Background Modellingmentioning

confidence: 99%

“…The goal associated with any video surveillance data in presence of camera tampering is primarily to detect the presence of such tampering using classification algorithms, and the rest of the data are used for solving the computer vision problems. Several techniques have been developed to solve this problem (Mantini and Shah, 2019b;Sitara and Mehtre, 2019) based on sophisticated image processing and deep learning techniques intended to classify each frame as tampered or not. However, these techniques achieve good results only at the cost of an extensive amount of training data and computing power.…”

mentioning

confidence: 99%

A New Robust Scalable Singular Value Decomposition Algorithm for Video Surveillance Background Modelling

Roy¹,

Basu²,

Ghosh³

2021

Preprint

View full text Add to dashboard Cite

A basic algorithmic task in automated video surveillance is to separate background and foreground objects. Camera tampering, noisy videos, low frame rate, etc., pose difficulties in solving the problem. A general approach which classifies the tampered frames, and performs subsequent analysis on the remaining frames after discarding the tampered ones, results in loss of information. We propose a robust singular value decomposition (SVD) approach based on the density power divergence to perform background separation robustly even in the presence of tampered frames. We also provide theoretical results and perform simulations to validate the superiority of the proposed method over the few existing robust SVD methods. Finally, we indicate several other use-cases of the proposed method to show its general applicability to a large range of problems.

show abstract