Abnormal Activity Detection Research Articles

Abnormal Crowd Detection in Public Places using OpenCV and Deep Learning

Abstract: The rapid development of object detection algorithm as led to its widespread application in security, such as facial recognition and crowd surveillance. However, real-time tracking of an individual is very challenging, especially in crowded places where the person might be in part or entirely occluded for some period. Hence, this paper objective is to create abnormal activity detection in public places focusing only on people. This system does not just detect a person in real-time but in addition, uses the information it as learned to track the trajectory of the person until they exit the frame of the camera. The system uses the algorithm called YOLO for the person detection. The system was able to successfully detect the abnormal activity in public places and detect crowded group of people in live

Detection of Abnormal Activities from Various Signals Based on Statistical Analysis

Detection of Abnormal Activities from Various Signals Based on Statistical Analysis

Detection of Abnormal Activity Using Ensemble Deep Learning Model with Object Detection Network

Detection of Abnormal Activity Using Ensemble Deep Learning Model with Object Detection Network

Optimized Skeleton graph based CNN for Human Abnormal Detection in Video Streams

Human Action Recognition (HAR) is the process of understanding human actions and behavior. HAR has a broad range of applications, and it has been focused on increasing the attention in various domain of computed vision. Abnormal detection from video stream is vigorous to guarantee the security in both outside spaces with the internal. Furthermore, the abnormal actions are really infrequent and rare, which makes the supervision process more challenging and difficult. In this research, skeleton graph-based Convolutional Neural Network (CNN) is devised for human abnormal activity detection. Here, the skeleton graph-based CNN (Skeleton graph_CNN) is devised based on the concept of classical convolution and skeleton graph generation. The human action recognition classifies the human actions into normal and abnormal class. The abnormal actions from the recognized outcome are detected with Skeleton graph_CNN, which provides the various actions of human as an output. The Skeleton graph_CNNgenerates the skeleton shaped human structure by connecting the joints within the frame to consecutive frames. Moreover, the HAR is carried out using IITB-Corridor Dataset based on metrics, such as testing accuracy of 0.961, sensitivity of 0.956 and specificity of 0.960, correspondingly.

Detection of Abnormal Activity to Alert the Nearby Persons via M-DNN Based Surveillance System

In today's environment, video surveillance is critical. When artificial intelligence, machine learning, and deep learning were introduced into the system, the technology had progressed much too far. Different methods are in place using the above combinations to help distinguish various wary activities from the live tracking of footages. Human behavior is the most unpredictable, and determining whether it is suspicious or normal is quite tough. In a theoretical setting, a deep learning approach is utilized to detect suspicious or normal behavior and sends an alarm to the nearby people if suspicious activity is predicted. In this paper, data fusion technique is used for feature extraction which gives an accurate outcome. Moreover, the classes are classified by the well effective machine learning approach of modified deep neural network (M-DNN), that predicts the classes very well. The proposed method gains 95% accuracy, as well the advanced system is contrast with previous methods like artificial neural network (ANN), random forest (RF) and support vector machine (SVM). This approach is well fitted for dynamic and static conditions.

Neurological Disorder Detection of Brain Abnormal Activities Using a New Enhanced Computer-aided Model

In the field of neurodevelopmental disorders, Autism Spectrum Disorders (ASD) are recognized as one of the dramatically increased etiologically and clinically heterogeneous diseases. Although, increasing the number of children who have difficulties in communication or suffer from sudden malfunction of the brain, the current diagnostic approaches for those kind of disease are time-consuming and are mainly based on clinical interviews. In this paper, a new enhanced diagnostic model is introduced addressing many of the challenges which threats the analysis of Electroencephalography (EEG) signals. A preprocessing stage is proposed to choose the key segment of EEG channel and remove the artifacts in the EEG signals to enhance their quality. The proposed model uses a set of discriminative features based on discrete wavelet transform (DWT) such as skewness, standard division, shannon entropy and relative wave energy. Also, extracting cross correction between brain regions to detect abnormal connectivity and synchronization. Two EEG datasets are used to verify the accuracy of the proposed model. The fusion of two EEG dataset helps in building a more generalized mode to diagnose epilepsy and ASD. In the fused dataset, the combination of the mentioned features and Random Forest have produced a very promising diagnosis result with minimum diagnostic time, with an average accuracy equals to 96.78%. The proposed model obtained better classification accuracy compared to the existing methods.

Multi-classifier Combined Anomaly Detection Algorithm Based On Feature Map In Underground Coal Mine

The detection of abnormal activities in deep learning is of great significance for preventing the occurrence of abnormal disasters in mine production. As the underground scenes of coal mines are characterized by much noise and uneven light, the traditional manual feature extraction method has little obvious effect in the underground and low accuracy of anomaly detection. To solve the above problems, a feature extraction method combining CNN+LSTM is proposed. Secondly, the obtained features are matched by graph structure. Finally, multiple classifiers are used to classify the features before and after matching. In this paper, experiments are carried out in coal mine dataset and UCSDped1 dataset respectively, and comparisons are made with some classical algorithms. Experimental show that the algorithm achieves high recognition accuracy in different abnormal event datasets.

Back Propagation Classification of EEG for Brain-Computer Interface

The diagnosis system presents to classify the Electroencephalogram (EEG) brain signal of patient to distinguish between normal and abnormal which are tumor and epilepsy with better classification accuracy. To design automated classification of EEG signals for the detection of normal and abnormal activities using Wavelet transform and Artificial Neural Network (ANN) Classifier is considered. Here, the system uses the back propagation with feed forward for classification which follows the ANN classification with data set training. For training, the statistical principal features will be extracted with facilitate of data base samples. The test sample is going to be classified using ANN classifier parameters and its features. The system gives better performance accuracy for different test samples.

Back Propagation Classification of EEG for Brain-Computer Interface

The diagnosis system presents to classify the Electroencephalogram (EEG) brain signal of patient to distinguish between normal and abnormal which are tumor and epilepsy with better classification accuracy. To design automated classification of EEG signals for the detection of normal and abnormal activities using Wavelet transform and Artificial Neural Network (ANN) Classifier is considered. Here, the system uses the back propagation with feed forward for classification which follows the ANN classification with data set training. For training, the statistical principal features will be extracted with facilitate of data base samples. The test sample is going to be classified using ANN classifier parameters and its features. The system gives better performance accuracy for different test samples.

A Real-time framework for detection of abnormal activities in videos using CFS and BoF classifiers

A Real-time framework for detection of abnormal activities in videos using CFS and BoF classifiers

A Power Dissipation Monitoring Circuit for Intrusion Detection and Botnet Prevention on IoT Devices

Recently, there has been a sharp increase in the production of smart devices and related networks, and consequently the Internet of Things. One concern for these devices, which is constantly becoming more critical, is their protection against attacks due to their heterogeneity and the absence of international standards to achieve this goal. Thus, these devices are becoming vulnerable, with many of them not even showing any signs of malfunction or suspicious behavior. The aim of the present work is to introduce a circuit that is connected in series with the power supply of a smart device, specifically an IP camera, which allows analysis of its behavior. The detection circuit operates in real time (real-time detection), sampling the supply current of the device, processing the sampled values and finally indicating any detection of abnormal activities, based on a comparison to normal operation conditions. By utilizing techniques borrowed by simple power analysis side channel attack, it was possible to detect deviations from the expected operation of the IP camera, as they occurred due to intentional attacks, quarantining the monitored device from the rest of the network. The circuit is analyzed and a low-cost implementation (under 5US$) is illustrated. It achieved 100% success in the test results, showing excellent performance in intrusion detection.

Multilevel Privacy Controlling Scheme to Protect Behavior Pattern in Smart IoT Environment

Traditional approaches generally focus on the privacy of user’s identity in a smart IoT environment. Privacy of user’s behavior pattern is an important research issue to address smart technology towards improving user’s life. User’s behavior pattern consists of daily living activities in smart IoT environment. Sensor nodes directly interact with activities of user and forward sensing data to service provider server (SPS). While availing the services provided by a server, users may lose privacy since the untrusted devices have information about user’s behavior pattern and it may share data with adversary. In order to resolve this problem, we propose a multilevel privacy controlling scheme (MPCS) which is different from traditional approaches. MPCS is divided into two parts: (i) behavior pattern privacy degree (BehaviorPrivacyDeg), which works as follows: firstly, frequent pattern mining‐based time‐duration algorithm (FPMTA) finds the normal pattern of activity by adopting unsupervised learning. Secondly, patterns compact algorithm (PCA) is proposed to store and compact the mined pattern in each sensor device. Then, abnormal activity detection time‐duration algorithm (AADTA) is used by current triggered sensors, in order to compare the current activity with normal activity by computing similarity among them; (ii) multilevel privacy design model: we have divided privacy of users into four levels in smart IoT environment, and by using these levels, the server can configure privacy level for users according to their concern. Multilevel privacy design model consists of privacy‐level configuration protocol (PLCP) and activity design model. PLCP provides fine privacy controls to users while enabling users to set privacy level. In PLCP, we introduce level concern privacy algorithm (LCPA) and location privacy algorithm (LPA), so that adversary could not damage the data of user’s behavior pattern. Experiments are performed to evaluate the accuracy and feasibility of MPCS in both simulation and real‐case studies. Results show that our proposed scheme can significantly protect the user’s behavior pattern by detecting abnormality in real time.

In Situ Abnormal Behaviours Detection

This work describes a ‘detection of abnormal activities and health-related changes’ system for an elderly person at her/his home. The analysis is based on the data collected by a domotic box of the market. The box was initially designed to continuously recognize the owner’s daily activities in order to anticipate anomalies and consequently prevent health complications and enhance the rate of disease prevention. The box uses non-intrusive home automation sensors to detect the activity level of the occupants. It is equipped also with other technologies, including humidity sensors, bed and chair sensors to name a few. In order to build a system capable of intercepting warning signs for early intervention, we adopt a Hidden Markov Model based approach that we will initialize beforehand with the activity sequences of the user within a given period. The outcomes of the model paves the way for deducting the final judgement and reporting a relevant context-aware alert to healthcare service experts. Other statistical processes might complete this behavioural analysis later on to enhance the alerts accuracy.

Abnormal Activity Detection and Notification Platform for Real-Time Ad Hoc Network

As aging society era is getting near, number of elders who live alone is increasing. These people often need special care. Due to this reason, we propose Abnormal Activity Detection and Notification Platform (AADN) for Real-Time Ad Hoc Network which can help taking care of these people. The proposed platform relies on human tracking using cameras that are installed in different rooms inside the house. AADN will take as input images from the cameras to process and output activity in the form of human pose and objects with their relative distant to the detected human. Relationship Degree of Human Object Interaction (RD-HOI) will be analyzed every minute and be used to distinguish abnormal behavior by means of decision tree. In addition, activities will be used to generate routine behavior log and AADN will notify the person in charge of taking care of the subject if the detected activity differs from the routine. The proposed platform can achieve human pose accuracy of up to 99.66% by using COCO with VGG-NB model and can correctly identify object 68% of the time. Our experiments showed that AADN could notify abnormal activity by using RD-HOI when human and harmful objects were clearly visible in the picture and could correctly notify abnormal activity when time spent in a certain activity differed from the routine by a certain threshold given sufficient amount of data.

Large-Scale Datastreams Surveillance via Pattern-Oriented-Sampling

Monitoring large-scale datastreams with limited resources has become increasingly important for real-time detection of abnormal activities in many applications. Despite the availability of large datasets, the challenges associated with designing an efficient change-detection when clustering or spatial pattern exists are not yet well addressed. In this article, a design-adaptive testing procedure is developed when only a limited number of streaming observations can be accessed at each time. We derive an optimal sampling strategy, the pattern-oriented-sampling, with which the proposed test possesses asymptotically and locally best power under alternatives. Then, a sequential change-detection procedure is proposed by integrating this test with generalized likelihood ratio approach. Benefiting from dynamically estimating the optimal sampling design, the proposed procedure is able to improve the sensitivity in detecting clustered changes compared with existing procedures. Its advantages are demonstrated in numerical simulations and a real data example. Ignoring the neighboring information of spatially structured data will tend to diminish the detection effectiveness of traditional detection procedures. Supplementary materials for this article are available online.

Abnormal activity detection in surveillance video scenes

Automated detection of abnormal activity assumes a significant task in surveillance applications. This paper presents an intelligent framework video surveillance to detect abnormal human activity in an academic environment that takes into account the security and emergency aspects by focusing on three abnormal activities (falling, boxing and waving). This framework designed to consist of the two essential processes: the first one is a tracking system that can follow targets with identify sets of features to understand human activity and measure descriptive information of each target. The second one is a decision system that can realize if the activity of the target track is normal or abnormal” then energizing alarm when recognized abnormal activities.

A survey on video-based Human Action Recognition: recent updates, datasets, challenges, and applications

Human Action Recognition (HAR) involves human activity monitoring task in different areas of medical, education, entertainment, visual surveillance, video retrieval, as well as abnormal activity identification, to name a few. Due to an increase in the usage of cameras, automated systems are in demand for the classification of such activities using computationally intelligent techniques such as Machine Learning (ML) and Deep Learning (DL). In this survey, we have discussed various ML and DL techniques for HAR for the years 2011–2019. The paper discusses the characteristics of public datasets used for HAR. It also presents a survey of various action recognition techniques along with the HAR applications namely, content-based video summarization, human–computer interaction, education, healthcare, video surveillance, abnormal activity detection, sports, and entertainment. The advantages and disadvantages of action representation, dimensionality reduction, and action analysis methods are also provided. The paper discusses challenges and future directions for HAR.

Abnormal activity detection using shear transformed spatio-temporal regions at the surveillance network edge

This paper presents a method of detecting abnormal activity in crowd videos while considering the direction of the dominant crowd motion. One main goal of our approach is to be able to run at the edge of the surveillance network close to the surveillance cameras so as to reduce network congestion and decision latency. To capture motion features while considering the direction of dominant crowd direction we propose a generalised shear transform based spatio-temporal region. To detect abnormal activity, an autoencoder based method is adopted considering the requirement for running the method at the network edge. During training, the autoencoder learns motion features for each spatio-temporal region from video frames containing normal activity. While testing, those motion features from each spatio-temporal region that cannot be reconstructed satisfactorily by the autoencoder indicate abnormal activity. This approach allows coarse localisation as well as detection of abnormal activity. The approach demonstrated $\mathcal {O}(n)$ behaviour with ability to work at higher frame rates by trading off accuracy. The approach has been verified against recent works on standard abnormal activity datasets: UCSD dataset and Subway dataset.

Detecting Abnormal Activities using Computer Vision in Big Data Framework

The abnormal behaviour of any person can be detected using computer vision. This is an important area in the field of research which is driven by wide variety of domains like intelligent video surveillance. Various techniques can be used in the field of computer vision feature extraction and description scheme. In this paper we have shown the comparison of all the techniques and method used in computer vision for the detection of abnormal activities.

Social Multimedia Security and Suspicious Activity Detection in SDN using Hybrid Deep Learning Technique

Social multimedia traffic is growing exponentially with the increased usage and continuous development of services and applications based on multimedia. Quality of Service (QoS), Quality of Information (QoI), scalability, reliability and such factors that are essential for social multimedia networks are realized by secure data transmission. For delivering actionable and timely insights in order to meet the growing demands of the user, multimedia analytics is performed by means of a trust-based paradigm. Efficient management and control of the network is facilitated by limiting certain capabilities such as energy-aware networking and runtime security in Software Defined Networks. In social multimedia context, suspicious flow detection is performed by a hybrid deep learning based anomaly detection scheme in order to enhance the SDN reliability. The entire process is divided into two modules namely – Abnormal activities detection using support vector machine based on Gradient descent and improved restricted Boltzmann machine which facilitates the anomaly detection module, and satisfying the strict requirements of QoS like low latency and high bandwidth in SDN using end-to-end data delivery module. In social multimedia, data delivery and anomaly detection services are essential in order to improve the efficiency and effectiveness of the system. For this purpose, we use benchmark datasets as well as real time evaluation to experimentally evaluate the proposed scheme. Detection of malicious events like confidential data collection, profile cloning and identity theft are performed to analyze the performance of the system using CMU-based insider threat dataset for large scale analysis.