Open AccessPosted Content
Unsupervised Abnormality Detection Using Heterogeneous Autonomous Systems
Reads0
Chats0
TLDR
A heterogeneous system that estimates the degree of an anomaly in unmanned surveillance drone by inspecting IMU (Inertial Measurement Unit) sensor data and real-time image in an unsupervised approach is demonstrated.Abstract:
Anomaly detection (AD) in a surveillance scenario is an emerging and challenging field of research. For autonomous vehicles like drones or cars, it is immensely important to distinguish between normal and abnormal states in real-time. Additionally, we also need to detect any device malfunction. But the nature and degree of abnormality may vary depending upon the actual environment and adversary. As a result, it is impractical to model all cases a-priori and use supervised methods to classify. Also, an autonomous vehicle provides various data types like images and other analog or digital sensor data, all of which can be useful in anomaly detection if leveraged fruitfully. To that effect, in this paper, a heterogeneous system is proposed which estimates the degree of abnormality of an unmanned surveillance drone, analyzing real-time image and IMU (Inertial Measurement Unit) sensor data in an unsupervised manner. Here, we have demonstrated a Convolutional Neural Network (CNN) architecture, named AngleNet to estimate the angle between a normal image and another image under consideration, which provides us with a measure of anomaly of the device. Moreover, the IMU data are used in autoencoder to predict abnormality. Finally, the results from these two algorithms are ensembled to estimate the final degree of abnormality. The proposed method performs satisfactorily on the IEEE SP Cup-2020 dataset with an accuracy of 97.3%. Additionally, we have also tested this approach on an in-house dataset to validate its robustness.read more
Citations
More filters
Posted Content
Anomaly Detection using Edge Computing in Video Surveillance System: Review
TL;DR: In this article, the authors surveyed various anomaly detection methods developed to detect anomalies in intelligent video surveillance systems and discussed the challenges and opportunities involved in anomaly detection at the edge and presented a systematic categorization of anomaly detection methodologies developed for ease of understanding.
Proceedings ArticleDOI
Optimization of Surface Plasmon Resonance Biosensor for Analysis of Lipid Molecules
TL;DR: In this article, the basic Kretschmann configuration and narrow groove grating were optimized to detect two different types of lipids known as phospholipid and eggyolk, which were used as analyte (sensing layer) and two different proteins namely tryptophan and bovine serum albumin (BSA) are used as ligand (binding site).
Posted Content
Optimization of Surface Plasmon Resonance Biosensor for Analysis of Lipid Molecules
TL;DR: This work uses finite-difference time-domain (FDTD) technique to perform quantitative analysis and finds that sensitivity increases when lipid concentration is increased and it is the highest for phospholipid and tryptophan combination when metal and lipid layer thicknesses are 45 nm and 30 nm respectively.
Posted Content
Anomaly Detection in Unsupervised Surveillance Setting Using Ensemble of Multimodal Data with Adversarial Defense
TL;DR: An unsupervised ensemble anomaly detection system to detect device anomaly of an unmanned drone analyzing multimodal data like images and IMU sensor data synergistically and applied adversarial attack to test the robustness of the proposed approach and integrated defense mechanism.
Proceedings ArticleDOI
Unsupervised Abnormality Detection Using Heterogenous Autonomous System
Kazi Mejbaul Islam,Rouhan Noor,Sayeed Shafayet Chowdhury,Tafannum Tahiat Ohi,Mohammad Redwan Islam,Chinmoy Kumer Roy,Nazmus Sakib +6 more
TL;DR: In this article, a heterogeneous system that estimates the degree of an anomaly in unmanned surveillance drone by inspecting IMU (Inertial Measurement Unit) sensor data and real-time image in an unsupervised approach is presented.
References
More filters
Siamese Neural Networks for One-shot Image Recognition
TL;DR: A method for learning siamese neural networks which employ a unique structure to naturally rank similarity between inputs and is able to achieve strong results which exceed those of other deep learning models with near state-of-the-art performance on one-shot classification tasks.
Proceedings Article
Unsupervised Representation Learning by Predicting Image Rotations
TL;DR: Gidaris et al. as discussed by the authors proposed to learn image features by training ConvNets to recognize the 2D rotation that is applied to the image that it gets as input, which provides a very powerful supervisory signal for semantic feature learning.
Journal ArticleDOI
A Review of Motion Planning Techniques for Automated Vehicles
TL;DR: A review of motion planning techniques implemented in the intelligent vehicles literature, with a description of the technique used by research teams, their contributions in motion planning, and a comparison among these techniques is presented.
Posted Content
Hypercolumns for Object Segmentation and Fine-grained Localization
TL;DR: Using hypercolumns as pixel descriptors, this work defines the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel, and shows results on three fine-grained localization tasks: simultaneous detection and segmentation, and keypoint localization.
Proceedings ArticleDOI
Real-World Anomaly Detection in Surveillance Videos
TL;DR: The experimental results show that the MIL method for anomaly detection achieves significant improvement on anomaly detection performance as compared to the state-of-the-art approaches, and the results of several recent deep learning baselines on anomalous activity recognition are provided.