With the increased usage of video communication technologies, the requirement for secure video data transfer has grown more critical than ever. Video encryption methods are critical in preventing unauthorized access to sensitive video data while it is provided across insecure networks. This study compares several video encryption algorithms, including symmetric and asymmetric key-based encryption methods. The goal of this research is to compare the security, computational complexity, and transmission overhead of several video encryption techniques. The research includes an examination of well-known encryption algorithms that include AES (Advanced Encryption Standard), RSA (Rivest-Shamir-Adelman) and DES (Data Encryption Standard), as well as variants on these techniques. Furthermore, this work offers a hybrid video encryption method that combines symmetric and asymmetric key-based encryption approaches to provide good security while being computationally simple. The experimental results reveal that the proposed method is more successful and effective than existing video encryption techniques. The suggested method used to secure video data communication over unsecured networks such as the internet, assuring the video data s secrecy, integrity, and authenticity.

System is used independently, for sudden emergencies, the traditional security protection system can t inform the staff relevant situations comprehensively and automatically. It is not conductive for the staff to catch early warning and handle emergency events. Meanwhile, the management of independent subsystems is complicated. So, establishment of a unified management and control platform is proposed to integrate sorts of information. The paper elaborates information integration architecture based on video surveillance, supporting technologies and linkage application functions. By establishing logical relationship, all subsystems are integrated into a united and interactive security protection system which has the ability of automatic identification, automatic forecasting and processing. It reflects the economic philosophy that equipment utilization maximization.

In the field operation, crossing the fence is a common illegal behavior, which needs to be paid attention to. Especially, the live part of the power station site is mixed with the power outage part, and some construction workers cross the fence to enter the live area, which can easily cause safety problems. The power station has a wide range of operations, and the manual monitoring method is inefficient. With the popularization of video monitoring devices in power stations, this paper proposes a detection and identification method for fence crossing violations based on video monitoring. The method extracts video frames as input, uses convolution to extract temporal and spatial features, and classifies and regresses the features fused in time and space, which can effectively identify fence crossing behaviors. Finally, a video processing platform is built to process alarms for illegal operations. Engineering practice shows that the method shown in the article can effectively predict the illegal crossing of the fence in the power station and improve the intelligent monitoring level of the power station.

Video anomaly detection in the surveillance video is one of the essential components of the intelligent video surveillance system. However, anomaly detection remains an ill-defined problem, despite the diverse applications due to its rareness and equivocal nature. A Long Short Term Memory - Variational Autoencoder (LSTM-VAE) model is proposed to detect video anomalies. The model consists of a spatial encoder comprised of convolutional layers, a temporal encoder as well as a decoder comprised of Convolutional LSTM (ConvLSTM), and a spatial decoder consisting of transposed convolution layers. The generative model is trained only on normal video clips with the objective of minimizing the reconstruction error. Then, the trained model is tested on the test video sequences comprised of both normal and abnormal incidents. The reconstruction error corresponding to the test frame sequences having video anomalies will be very high as the model is not trained to reconstruct them. Subsequently, the corresponding frames will have a low regularity score. An appropriate threshold regularity score is set to segregate the anomaly frames from the normal ones. Frames having a regularity score less than the set threshold value are considered as anomalous frames. The model is developed by using one of the publicly available bench-marked video anomaly datasets, i.e., UCSD Ped2. The performance metrics of the proposed model are promising.

A smart university is supposed to be a safe university. At this moment we observe multiple cameras in different locations in the Hall University and rooms to detect suspicious behavior such as violation, larceny or persons in a state of alcohol or drug intoxication. Samples of the video footage is monitored 24/7 by operators in control rooms. Currently the recorded videos are visual assessed after a suspicious event has occurred. There is a requirement for realtime surveillance with smart cameras which can detect, track and analyze suspicious behavior over place and time. The expanding number of cameras requires an enormous measure of observing operators. This paper proposes a distributed intelligent surveillance system based on smart cameras. We seek to improve the Quality of Experience QoE operator side or QoEvideo surveillance expressed in function of i- resource availability constraints, ii- false detection of suspicious behavior, iii- define an optimal perimeter for intrusion detection (subset of cameras, network parameters required . . . ).

Smart Surveillance Systems are becoming an important aspect of our lives, reducing man labour and additionally increasing the accuracy of detection by reducing false positives. Specifically for an ATM, Surveillance system is very crucial because of the transactions happening being sensitive along with that drop-box containing confidential documents like cheques and bank forms. Hence, there is a need to develop a fool-proof system which can handle a lot of load and perform various surveillance tasks. Moreover, the systems also need to have network security to protect the data from being illegally traced and changed. In this paper, we will be reviewing and comparing various smart surveillance system methods which involve various technologies.

Understanding dynamic human behavior based on online video has many applications in security control, crime surveillance, sports, and industrial IoT systems. This paper solves the problem of classifying video data recorded on surveillance cameras in order to identify fragments with instances of shoplifting. It is proposed to use a classifier that is a symbiosis of two neural networks: convolutional and recurrent. The convolutional neural network is used for extraction of features from each frame of the video fragment, and the recurrent network for processing the temporal sequence of processed frames and subsequent classification.

With the development of technology, the technological informationization of the security network video surveillance service industry has become the demand of the times. How to improve the functions of the video surveillance system and build an open security integrated monitoring management platform has become the research point of this article. This article intends to build a video surveillance system based on database technology to meet the multi-functional requirements of the surveillance system. This article mainly uses experimental methods to test the data of the monitoring system designed in this article, and then uses the comparative method to compare the speed of the three methods to calculate the data, and the data results are obtained. According to the experiment, the data processing time of the binary algorithm in the video surveillance system is within 15s. Image detection in database technology uses binary algorithms to operate and analyze it more quickly.

Surveillance is an observation of a place, large areas, behavior, or a variety of activities to acquire information, influence, manage, or guide it. When people talk about surveillance solutions, the growing demand for large area monitoring becomes one of the key trends in the security industry. Surveillance video is used in real-time to watch known threats. Suspicious activities through surveillance video are a major topic in image processing and deep learning research.Residential area security is very much important to people nowadays. The proposed system is concerned with the development of a surveillance video framework in the residential area to detect any type of suspicious robbery activity. This system makes effective use of deep learning techniques of yolo, this includes techniques like object detection and eventually identifying the actions required to prevent robberies.Surveillance cameras are used here to remotely monitor a residential area or building by transmitting recorded images or videos to a control station to thwart suspicious activities. As a result, deep learning techniques are employed to achieve outstanding detection of suspicious actions that yielded positive results..

In recent years, in order to continuously promote the construction of safe cities, security monitoring equipment has been widely used all over the country. How to use computer vision technology to realize effective intelligent analysis of violence in video surveillance is very important to maintain social stability and ensure people s life and property safety. Video surveillance system has been widely used because of its intuitive and convenient advantages. However, the existing video monitoring system has relatively single function, and generally only has the functions of monitoring video viewing, query and playback. In addition, relevant researchers pay less attention to the complex abnormal behavior of violence, and relevant research often ignores the differences between violent behaviors in different scenes. At present, there are two main problems in video abnormal behavior event detection: the video data of abnormal behavior is less and the definition of abnormal behavior in different scenes cannot be clearly distinguished. The main existing methods are to model normal behavior events first, and then define videos that do not conform to the normal model as abnormal, among which the learning method of video space-time feature representation based on deep learning shows a good prospect. In the face of massive surveillance videos, it is necessary to use deep learning to identify violent behaviors, so that the machine can learn to identify human actions, instead of manually monitoring camera images to complete the alarm of violent behaviors. Network training mainly uses video data set to identify network training.

As an important component of security systems, the number of video surveillance systems is growing rapidly year by year. However, video surveillance systems often have many network security problems, and there is no perfect solution at present. To address these security issues, we propose a TPM-based security enhancement design for video surveillance systems. We enhance the security of the video surveillance system from the perspective of its own environmental security, video data security and device authentication, combined with the TPM module s trusted metrics, trusted authentication and key management mechanisms. We have developed and implemented a prototype video surveillance system and conducted experiments. The experimental results show that the framework we designed can greatly enhance the security of the video surveillance system while ensuring performance.

Wearables Security 2022 - One of the biggest new trends in artificial intelligence is the ability to recognise people s movements and take their actions into account. It can be used in a variety of ways, including for surveillance, security, human-computer interaction, and content-based video retrieval. There have been a number of researchers that have presented vision-based techniques to human activity recognition. Several challenges need to be addressed in the creation of a vision-based human activity recognition system, including illumination variations in human activity recognition, interclass similarity between scenes, the environment and recording setting, and temporal variation. To overcome the above mentioned problem, by capturing or sensing human actions with help of wearable sensors, wearable devices, or IoT devices. Sensor data, particularly one-dimensional time series data, are used in the work of human activity recognition. Using 1D-Convolutional Neural Network (CNN) models, this works aims to propose a new approach for identifying human activities. The Wireless Sensor Data Mining (WISDM) dataset is utilised to train and test the 1D-CNN model in this dissertation. The proposed HAR-CNN model has a 95.2\%of accuracy, which is far higher than that of conventional methods.

Control room video surveillance is an important source of information for ensuring public safety. To facilitate the process, a Decision-Support System (DSS) designed for the security task force is vital and necessary to take decisions rapidly using a sea of information. In case of mission critical operation, Situational Awareness (SA) which consists of knowing what is going on around you at any given time plays a crucial role across a variety of industries and should be placed at the center of our DSS. In our approach, SA system will take advantage of the human factor thanks to the reinforcement signal whereas previous work on this field focus on improving knowledge level of DSS at first and then, uses the human factor only for decision-making. In this paper, we propose a situational awareness-centric decision-support system framework for mission-critical operations driven by Quality of Experience (QoE). Our idea is inspired by the reinforcement learning feedback process which updates the environment understanding of our DSS. The feedback is injected by a QoE built on user perception. Our approach will allow our DSS to evolve according to the context with an up-to-date SA.

Smart city management is going through a remarkable transition, in terms of quality and diversity of services provided to the end-users. The stakeholders that deliver pervasive applications are now able to address fundamental challenges in the big data value chain, from data acquisition, data analysis and processing, data storage and curation, and data visualisation in real scenarios. Industry 4.0 is pushing this trend forward, demanding for servitization of products and data, also for the smart cities sector where humans, sensors and devices are operating in strict collaboration. The data produced by the ubiquitous devices must be processed quickly to allow the implementation of reactive services such as situational awareness, video surveillance and geo-localization, while always ensuring the safety and privacy of involved citizens. This paper proposes a modular architecture to (i) leverage innovative technologies for data acquisition, management and distribution (such as Apache Kafka and Apache NiFi), (ii) develop a multi-layer engineering solution for revealing valuable and hidden societal knowledge in smart cities environment, and (iii) tackle the main issues in tasks involving complex data flows and provide general guidelines to solve them. We derived some guidelines from an experimental setting performed together with leading industrial technical departments to accomplish an efficient system for monitoring and servitization of smart city assets, with a scalable platform that confirms its usefulness in numerous smart city use cases with different needs.

Protection of private and sensitive information is the most alarming issue for security providers in surveillance videos. So to provide privacy as well as to enhance secrecy in surveillance video without affecting its efficiency in detection of violent activities is a challenging task. Here a steganography based algorithm has been proposed which hides private information inside the surveillance video without affecting its accuracy in criminal activity detection. Preprocessing of the surveillance video has been performed using Tunable Q-factor Wavelet Transform (TQWT), secret data has been hidden using Discrete Wavelet Transform (DWT) and after adding payload to the surveillance video, detection of criminal activities has been conducted with maintaining same accuracy as original surveillance video. UCF-crime dataset has been used to validate the proposed framework. Feature extraction is performed and after feature selection it has been trained to Temporal Convolutional Network (TCN) for detection. Performance measure has been compared to the state-of-the-art methods which shows that application of steganography does not affect the detection rate while preserving the perceptual quality of the surveillance video.

Based on the campus wireless IPv6 network system, using WiFi contactless sensing and positioning technology and action recognition technology, this paper designs a new campus security early warning system. The characteristic is that there is no need to add new monitoring equipment. As long as it is the location covered by the wireless IPv6 network, personnel quantity statistics and personnel body action status display can be realized. It plays an effective monitoring supplement to the places that cannot be covered by video surveillance in the past, and can effectively prevent campus violence or other emergencies.

To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can efficiently exploit the translation motion of the moving objects, it is susceptible to other types of affine motion and object occlusion/deocclusion. Recently, deep learning has been used to model the high-level structure of human pose in specific actions from short videos and then generate virtual frames in future time by predicting the pose using a generative adversarial network (GAN). Therefore, modelling the high-level structure of human pose is able to exploit semantic correlation by predicting human actions and determining its trajectory. Video surveillance applications will benefit as stored “big” surveillance data can be compressed by estimating human pose trajectories and generating future frames through semantic correlation. This paper explores a new way of video coding by modelling human pose from the already-encoded frames and using the generated frame at the current time as an additional forward-referencing frame. It is expected that the proposed approach can overcome the limitations of the traditional backward-referencing frames by predicting the blocks containing the moving objects with lower residuals. Our experimental results show that the proposed approach can achieve on average up to 2.83 dB PSNR gain and 25.93% bitrate savings for high motion video sequences compared to standard video coding.

With the rapid development of artificial intelligence, video target tracking is widely used in the fields of intelligent video surveillance, intelligent transportation, intelligent human-computer interaction and intelligent medical diagnosis. Deep learning has achieved remarkable results in the field of computer vision. The development of deep learning not only breaks through many problems that are difficult to be solved by traditional algorithms, improves the computer's cognitive level of images and videos, but also promotes the progress of related technologies in the field of computer vision. This paper combines the deep learning algorithm and target tracking algorithm to carry out relevant experiments on basketball motion detection video, hoping that the experimental results can be helpful to basketball motion detection video target tracking.

Video summarization aims to improve the efficiency of large-scale video browsing through producting concise summaries. It has been popular among many scenarios such as video surveillance, video review and data annotation. Traditional video summarization techniques focus on filtration in image features dimension or image semantics dimension. However, such techniques can make a large amount of possible useful information lost, especially for many videos with rich text semantics like interviews, teaching videos, in that only the information relevant to the image dimension will be retained. In order to solve the above problem, this paper considers video summarization as a continuous multi-dimensional decision-making process. Specifically, the summarization model predicts a probability for each frame and its corresponding text, and then we designs reward methods for each of them. Finally, comprehensive summaries in two dimensions, i.e. images and semantics, is generated. This approach is not only unsupervised and does not rely on labels and user interaction, but also decouples the semantic and image summarization models to provide more usable interfaces for subsequent engineering use.

One of the biggest studies on public safety and tracking that has sparked a lot of interest in recent years is deep learning approach. Current public safety methods are existent for counting and detecting persons. But many issues such as aberrant occurring in public spaces are seldom detected and reported to raise an automated alarm. Our proposed method detects anomalies (deviation from normal events) from the video surveillance footages using deep learning and raises an alarm, if anomaly is found. The proposed model is trained to detect anomalies and then it is applied to the video recording of the surveillance that is used to monitor public safety. Then the video is assessed frame by frame to detect anomaly and then if there is match, an alarm is raised.

In recent years, in order to continuously promote the construction of safe cities, security monitoring equipment has been widely used all over the country. How to use computer vision technology to realize effective intelligent analysis of violence in video surveillance is very important to maintain social stability and ensure people's life and property safety. Video surveillance system has been widely used because of its intuitive and convenient advantages. However, the existing video monitoring system has relatively single function, and generally only has the functions of monitoring video viewing, query and playback. In addition, relevant researchers pay less attention to the complex abnormal behavior of violence, and relevant research often ignores the differences between violent behaviors in different scenes. At present, there are two main problems in video abnormal behavior event detection: the video data of abnormal behavior is less and the definition of abnormal behavior in different scenes cannot be clearly distinguished. The main existing methods are to model normal behavior events first, and then define videos that do not conform to the normal model as abnormal, among which the learning method of video space-time feature representation based on deep learning shows a good prospect. In the face of massive surveillance videos, it is necessary to use deep learning to identify violent behaviors, so that the machine can learn to identify human actions, instead of manually monitoring camera images to complete the alarm of violent behaviors. Network training mainly uses video data set to identify network training.