Surveillance Camera System Research Articles

Development of a Key Method for the Optimization of Port Vessel Detection Based on an Improved Multi-Structural Morphology Approach

All over the world, many ports have implemented surveillance camera systems to monitor the vessels and activities around them. These types of systems are not very effective in accurately detecting activities around the port due to background noise and congestion interference at the sea surface. This is why it is difficult to accurately detect vessels, especially smaller vessels, when it turns dark. It is known that some vessels do not comply with maritime rules, particularly in port and safety zones; these must be detected to avoid incidents. For these reasons, in this study, we propose and develop an improved multi-structural morphology (IMSM) approach to eliminate all of this noise and interference so that vessels can be accurately detected in real time. With this new approach, the target vessel is separated from the sea surface background through the weighted morphological filtering of several datasets of structural components. Then, neighborhood-based adaptive fast median filtering is used to filter out impulse noise. Finally, a characteristic morphological model of the target vessel is established using the connected domain; this allows the sea surface congestion to be eliminated and the movement of vessels to be detected in real time. Multiple tests are carried out on a small and discrete area of moving vessels. The results from several collected datasets show that the proposed approach can effectively eliminate background noise and congestion interference in video monitoring. The detection accuracy rate and the processing time are improved by approximately 3.91% and 1.14 s, respectively.

Unveiling Users' Security and Privacy Concerns Regarding Smart Home IoT Products from Online Reviews

The Internet of Things (IoT) has revolutionized the global market with lifestyle products such as fitness trackers (FT), smart home speakers (SHS), and surveillance and security camera systems (SSCS). While offering convenience, these products also introduce potential security and privacy (S&P) risks to buyers, often going unnoticed. Consumers’ incomplete mental models of the risks involved and the information asymmetry between buyers and sellers only add to the problem. Understanding consumer concerns in online product reviews can play a crucial role in bridging the gap of such information asymmetry. By establishing a balanced flow of information between buyers and sellers, manufacturers can leverage genuine concerns expressed in reviews to enhance product features while educating users about misinformation in reviews. In this study, we collected FT, SHS, and SSCS product reviews from three Amazon domains: the US, the UK, and India. Using a keyword-based search method focused on S&P concerns, we discovered a considerable number of reviews expressing notable concerns regarding security and privacy. Our qualitative analysis revealed that data security is a common concern across all product types. Further, our quantitative analysis exposed significant geographic variations, with the concern ratio being higher in the US than in the UK for all device types and higher than in the Indian domain for security cameras. These findings highlight the need for tailored security measures and user awareness campaigns in different parts of the world to address the identified concerns effectively.

Multi-level traffic-responsive tilt camera surveillance through predictive correlated online learning

In urban traffic management, the primary challenge of dynamically and efficiently monitoring traffic conditions is compounded by the insufficient utilization of thousands of surveillance cameras along the intelligent transportation system. This paper introduces the multi-level Traffic-responsive Tilt Camera surveillance system (TTC-X), a novel framework designed for dynamic and efficient monitoring and management of traffic in urban networks. By leveraging widely deployed pan–tilt-cameras (PTCs), TTC-X overcomes the limitations of a fixed field of view in traditional surveillance systems by providing mobilized and 360-degree coverage. The innovation of TTC-X lies in the integration of advanced machine learning modules, including a detector–predictor–controller structure, with a novel Predictive Correlated Online Learning (PiCOL) methodology and the Spatial–Temporal Graph Predictor (STGP) for real-time traffic estimation and PTC control. The TTC-X is tested and evaluated under three experimental scenarios (e.g., maximum traffic flow capture, dynamic route planning, traffic state estimation) based on a simulation environment calibrated using real-world traffic data in Brooklyn, New York. The experimental results showed that TTC-X captured over 60% total number of vehicles at the network level, dynamically adjusted its route recommendation in reaction to unexpected full-lane closure events, and reconstructed link-level traffic states with best MAE less than 1.25 vehicle/hour. Demonstrating scalability, cost-efficiency, and adaptability, TTC-X emerges as a powerful solution for urban traffic management in both cyber–physical and real-world environments.

A detection and defense security system design for nuclear waste storage against stealth terrorists attack

Abstract The physical protection system (PPS) is one of the main systems used in nuclear facilities to protect these facilities from terrorist attacks, the possibility of bombing, sabotage, and theft. Installation of a security system for nuclear waste stores from the outside is necessary and very important for early detection and physiological deterrence greater than the internal security system. From this perspective, this work provides a solution for the protection of nuclear waste stores, which means detection and defense systems. This paper introduces an advanced security system and proposes a design for a detection and defense security system for nuclear waste storage against stealth terrorist attacks. The security system that is being suggested will have smart camera surveillance system, electric chock system, intense flashlight barrier, high-intensity sound barriers, and dual-side infrared rays. Three consecutive processes – detection, deterrence, and defense – will be operated around the building of the waste storage. The concept may be implemented by establishing an early detection system to detect any intrusion by terrorist attackers through a protected area surrounded by storage. The following step is deterring the attackers from completing their mission by installing advanced deterrence system and putting delay components along the path of their attack on the waste storage to complicate the mission. Then the defense system is operating to stop terrorist progress. Finally, the work make an evaluation process of the overall security system which has been designed by using EASI program to verify the accepted level of physical protection, maintain the validity and updates of security system components, and follow procedures, rules and requirements of the nuclear regulatory authority at the national level and meet the international IAEA concept and recommendations.

A proposed design for security system for nuclear waste warehouses against terrorists attack

A physical protection system (PPS) is one of the principal systems used in nuclear facilities for protection against terrorist attacks and the possibility of bombing, sabotage, and theft. This paper introduces the design of an advanced security system for nuclear waste warehouses against stealth terrorist attacks. This research paper takes a more original approach in addressing how a nuclear facility can detect and respond to a security incident. It does so through an interconnected security system that simultaneously practical and distinctive way. This PPS design allows the security system to achieve its main goals of detection and delay functions during any incident. Additionally, it places the intruder under attack from a successive defensive system which grants the response forces additional time to arrive and neutralize the threat completely.The proposed design of the security system will include dual-side infrared rays, high-intensive sound barriers, an intensive flashlight barrier, an electric chock system, and a smart camera surveillance system. Three consecutive processes, detection, deterrence, and defense will be operated around the waste storage building. This idea can be implemented by establishing an early detection system to detect any intrusion by terrorist attackers through a protected area surrounding the storage facility. The next step is deterring the attackers from completing their mission by placing an advanced deterrence system and putting delay elements along the path of their attack on the waste storage to complicate the mission. Then the defense system is operating to prevent terrorist progress. Finally, an evaluation process of the overall security system which has been designed by using EASI program is performed to verify the accepted level of physical protection, keep the security system component valid and updated, and follow procedures, rules and requirements of the nuclear regulatory authority at the national level and meet IAEA concept and recommendations at the international level.

Onboard Surveillance Camera Robotic Vehicle

Abstract: Surveillance cameras have been integrated with autonomous vehicles for various purposes like monitoring, guarding and spying. This research paper focuses on how to design, implement, deploy and evaluate a robotic vehicle with a surveillance camera system. This study is on both hardware and software architecture, choice of camera, image processing techniques as wellas communication protocol with other devices. Therefore, the suggested system aims at improving surveillance in addition with the number of sensors which can prevent any accident and can increase remote monitoring. The blynk server is used for the transmission of the data of various servers used in the system. Telegram bot is used to perform a two way communication with the system.

Vehicle counting application utilizing background subtraction method with large-scale camera data

In modern society, people are increasingly using cameras at home, in shops, and on the streets. Traffic systems have also invested in building more surveillance camera systems. The data collected by cameras contains valuable information for traffic regulation and recording traffic violations. The challenge is how to effectively use this data. In this article, we will discuss the use of real-time data from surveillance cameras on some roads in Da Nang City for vehicle counting using background subtraction methods. Additionally, we also tested the detection of red light violations to contribute to the development of a smart traffic system. So, the use of background subtraction in analyzing real-time data from surveillance cameras can greatly improve traffic management

A computer vision approach to monitor activity in commercial broiler chickens using trajectory-based clustering analysis

To monitor changes in broiler behaviour related to animal health and welfare, farmers typically observe their flocks using manual observation. However, due to the labour intensive and continuous aspect of this task, the analysis of broiler behaviour could be automated using camera technology. This paper proposes a proof-of-concept camera surveillance system based on the automated detection and tracking of broilers to monitor activity bouts using unsupervised 2D trajectory clustering. Firstly, a convolutional neural network-based detector was trained and tested on our labelled dataset which resulted in a precision, recall and f score of 0.98, 0.90 and 0.94, respectively. Using a tracking-by-detection approach, the proposed system was able to track chickens across video frames with a multi-object tracking accuracy of 74.7%. A component-based feature saliency Gaussian mixture model (CFSGMM) was subsequently generated and applied to objectively cluster the trajectories based on their spatiotemporal information. Nineteen features were extracted from the trajectories, representing both static and dynamic characteristics of broiler movement, and three activity classes were identified: ‘least active/resting,’ ‘active’ and ‘highly-active.’ The proposed method was validated on one-minute monocular video sequences. CFSGMM was applied to cluster 2D trajectories relating to broiler activity bouts within the commercial rearing environment with an agreement ranging from 6.0 to 99.7% when compared to human observation. We demonstrate the potential of the computer vision system to monitor overt, short-term changes in broiler activity associated with on-farm events and discuss the opportunities of leveraging the technology to monitor longer term changes in welfare state. It is anticipated that further development of the detection and tracking systems will improve the performance of the trajectory clustering method.

Design of a real-time crime monitoring system using deep learning techniques

Criminal Activities and Crime Monitoring System has long been a research topic. In this paper, we propose an effective Crime Monitoring System (CMS) that can detect a crime in real-time using a camera surveillance system and notify the appropriate law enforcement officer. The CMS was proposed to counterbalance human weaknesses such as inattention, slow reaction, and slacking, for example, in detecting crimes. The proposed CMS detects crime scenes by combining the mechanisms and functionalities of closed-circuit television (CCTV) cameras with various deep-learning methods and image-processing techniques. The CMS operates in three stages: weapon detection, violence detection, and face recognition. We used transfer learning models to detect weapons, and violence and used a face recognition algorithm to recognize faces. More specifically, to detect weapons YOLOv5, and MobileNetv2 to detect violence and used face recognition algorithms to recognize faces. The image dataset is used in CMS, while the video dataset is used to train the MobileNet-based violence detection model. In this case, frame-by-frame images extracted from video files were used to train the model. All of the models performed admirably. The weapon detection model detected four different weapon classes with greater than 80% accuracy. The violence detection model is also 95% accurate. The face recognition model had a 97% accuracy rate in detecting faces. The CMS's combined model was tested in a variety of real-world scenarios, and its performance was found to be outstanding. It was able to detect crime incidents and generate timely alarms, demonstrating its effectiveness in providing security and safety.

Global-local attention with triplet loss and label smoothed crossentropy for person re-identification

Person re-identification (Person Re-ID) is a research direction on tracking and identifying people in surveillance camera systems with non-overlapping camera perspectives. Despite much research on this topic, there are still some practical problems that Person Re-ID has not yet solved, in reality, human objects can easily be obscured by obstructions such as other people, trees, luggage, umbrellas, signs, cars, motorbikes. In this paper, we propose a multibranch deep learning network architecture. In which one branch is for the representation of global features and two branches are for the representation of local features. Dividing the input image into small parts and changing the number of parts between the two branches helps the model to represent the features better. In addition, we add an attention module to the ResNet50 backbone that enhances important human characteristics and eliminates irrelevant information. To improve robustness, the model is trained by combining triplet loss and label smoothing cross-entropy loss (LSCE). Experiments are carried out on datasets Market1501, and duke multi-target multi-camera (DukeMTMC) datasets, our method achieved 96.04% rank-1, 88,11% mean average precision (mAP) on the Market1501 dataset, and 88.78% rank-1, 78,6% mAP on the DukeMTMC dataset. This method achieves performance better than some state-of-the-art methods.

The new approach of a geolocation information system for offenders in the town of Kananga

This scientific theme addresses the establishment of a geolocation information system for perpetrators of offenses in the town of Kananga. This approach aims to use geolocation technologies to identify and locate people responsible for wrongdoing such as violations of the law in force in the town of Kananga. This system will therefore make it possible to collect precise data on offenders, which will facilitate their identification, prosecution and punishment. The objective is to improve the security and effectiveness of the measures taken to combat crime in the town of Kananga. This system could also help deter criminal acts by providing increased traceability of criminal activity. In this study, we organize our reflection around a few anchor points that we consider with regard to the general argument of this research. Apart from the introduction and the general conclusion, our subject includes four parts, in which we will specifically treat the analysis of the offense in Congolese law and its legal regime, an overview of geolocation (the geographic information system), the deployment of a surveillance camera system in the town of Kananga, as well as the modeling and implementation of a new geolocation system with a view to improving the pursuit of the offender.

FightNet deep learning strategy: An innovative solution to prevent school fighting violence

In this study, we introduce a new method to address the pressing issue of school violence using Artificial Intelligence (AI). School violence is a critical issue that affects the safety and well-being of students, teachers, and the school community as a whole. Violent behaviors, such as bullying, physical assaults, and weapon use, can have long-term effects on students’ psychological health and academic performance. To reduce these issues, we developed a lightweight Deep Learning model that can be integrated into a school’s surveillance camera system to quickly detect violent fighting behaviors for timely intervention by school staff. The proposed FightNet model consists of three components: MobileNetV2 backbone, Feature Pyramid Network (FPN) neck, and Centernet Object as a Point (COaP) head. By optimizing the hyperparameters of the model to extract keypoints in image frames from the COCO dataset, we applied an LSTM model to determine the temporal dependence of actions and classify them as “fighting” or “normal” using the UBI-Fights dataset. The FightNet model achieved mAP@0.5 of 45.34% and mAP@0.95 of 55.89% in estimating keypoints, and 72.68% accuracy and 71.69% F1-score in predicting actions. Based on these results, we conclude that the proposed model can effectively address the issue of school violence.

A Simulation-Based Approach to Evaluate the Performance of Automated Surveillance Camera Systems for Smart Cities

A surveillance camera is the typical device that makes up a surveillance camera system in a modern city. It will still be a representative surveillance unit in future scenarios such as in smart cities. Furthermore, as the demand for public safety increases, a massive number of surveillance cameras will be in use in the future, and an automated system that controls surveillance cameras intelligently will also be required. Meanwhile, installing a surveillance system without any verification system might not be cost-effective, so a simulation that evaluates the system’s performance is required in advance. For this reason, we introduce how to simulate a surveillance area and evaluate surveillance performance in this paper to assess a surveillance system consisting of large amounts of surveillance cameras. Our simulator defined the surveillance area as a pair of two-dimensional planes, which depend on various camera-related configurations. Both surveillance areas are used to determine if the moving object belongs to the coverage of a surveillance camera. In addition, our simulator adopts several performance indices to evaluate a surveillance camera system in terms of target detection and quality. The simulation study provides comprehensive results on how various components of the surveillance system affect the performance of the surveillance system, leading to the conclusion that building a sophisticated scheme to control a large number of surveillance cameras can provide a cost-effective and reliable surveillance system for smart cities.

An innovative method for human height estimation combining video images and 3D laser scanning.

Digitalization has increased the number of video surveillance systems that sometimes capture crime images. Traditional methods of human height estimation use projective geometry. However, sometimes they cannot be used because the video camera surveillance system is not available or has been moved and there are no reference lines on the frame. Scientific studies have developed a new method for human height estimation using 3D laser scanning. This model necessarily requires a series of approximations, which increase the final measurement error. To overcome this problem, in the present study, images of a subject are projected directly on the 3D model, estimating the height of the subject. This article describes the methodological approach adopted through the analysis of a real case study in a controlled environment executed by Carabinieri Forensic Investigation Department (Italy). The aim is to obtain a human anthropometric measure derived from frames extracted from the videos associated with the digital survey of the framed area obtained with 3D laser scanning and point cloud analysis. The result is the height estimation of five subjects filmed by a camera obtained through the combination of 2D images extracted by a DVR/surveillance systems with 3D laser scanning. Results show that most estimated measurements are less than the real measurement of the subject; it also depends on the posture of the subject while walking. Furthermore, results shows the differences between the real height and the estimated height with a statistical approach.

Computer vision models application in the current system on object detection tasks

The implementation of object detection algorithms would be helpful to the various fields of the current time. When object detection is applied to the surveillance camera system, it will be more efficient to locate crimes or find lost kids. This paper will investigate the performance of different object detection algorithms in a real-world scenario. With experimentation, CenterNet++ outperforms YOLO and MaskRCNN, two traditional and classic object detection algorithms, on the MS COCO dataset, which concludes that CenterNet++ can ensure both accuracy and speed.

LCA-GAN: Low-Complexity Attention-Generative Adversarial Network for Age Estimation with Mask-Occluded Facial Images

Facial-image-based age estimation is being increasingly used in various fields. Examples include statistical marketing analysis based on age-specific product preferences, medical applications such as beauty products and telemedicine, and age-based suspect tracking in intelligent surveillance camera systems. Masks are increasingly worn for hygiene, personal privacy concerns, and fashion. In particular, the acquisition of mask-occluded facial images has become more frequent due to the COVID-19 pandemic. These images cause a loss of important features and information for age estimation, which reduces the accuracy of age estimation. Existing de-occlusion studies have investigated masquerade masks that do not completely occlude the eyes, nose, and mouth; however, no studies have investigated the de-occlusion of masks that completely occlude the nose and mouth and its use for age estimation, which is the goal of this study. Accordingly, this study proposes a novel low-complexity attention-generative adversarial network (LCA-GAN) for facial age estimation that combines an attention architecture and conditional generative adversarial network (conditional GAN) to de-occlude mask-occluded human facial images. The open databases MORPH and PAL were used to conduct experiments. According to the results, the mean absolution error (MAE) of age estimation with the de-occluded facial images reconstructed using the proposed LCA-GAN is 6.64 and 6.12 years, respectively. Thus, the proposed method yielded higher age estimation accuracy than when using occluded images or images reconstructed using the state-of-the-art method.

Sensor Fusion in Autonomous Vehicle with Traffic Surveillance Camera System: Detection, Localization, and AI Networking.

Complete autonomous systems such as self-driving cars to ensure the high reliability and safety of humans need the most efficient combination of four-dimensional (4D) detection, exact localization, and artificial intelligent (AI) networking to establish a fully automated smart transportation system. At present, multiple integrated sensors such as light detection and ranging (LiDAR), radio detection and ranging (RADAR), and car cameras are frequently used for object detection and localization in the conventional autonomous transportation system. Moreover, the global positioning system (GPS) is used for the positioning of autonomous vehicles (AV). These individual systems' detection, localization, and positioning efficiency are insufficient for AV systems. In addition, they do not have any reliable networking system for self-driving cars carrying us and goods on the road. Although the sensor fusion technology of car sensors came up with good efficiency for detection and location, the proposed convolutional neural networking approach will assist to achieve a higher accuracy of 4D detection, precise localization, and real-time positioning. Moreover, this work will establish a strong AI network for AV far monitoring and data transmission systems. The proposed networking system efficiency remains the same on under-sky highways as well in various tunnel roads where GPS does not work properly. For the first time, modified traffic surveillance cameras have been exploited in this conceptual paper as an external image source for AV and anchor sensing nodes to complete AI networking transportation systems. This work approaches a model that solves AVs' fundamental detection, localization, positioning, and networking challenges with advanced image processing, sensor fusion, feathers matching, and AI networking technology. This paper also provides an experienced AI driver concept for a smart transportation system with deep learning technology.

Effect of video camera monitoring feedback on hand hygiene compliance in neonatal intensive care unit, an interventional study

BackgroundThe purpose of this study was to determine whether use of a video camera surveillance system for hand hygiene (HH) monitoring, video-based education, and feedback could improve the HH compliance in a neonatal intensive care unit (NICU). Methods and materialsThis was an interventional before-after trial conducted in a level-III NICU between July 2019 and June 2020. HH compliance was measured using randomly selected video-camera footage in the baseline, intervention, and maintenance periods. After the baseline, an intervention consisting of feedback and education with video scenarios was implemented. The primary outcome was change in HH compliance. The compliance rates were analyzed as an interrupted time series (ITS) with a segmented regression model adjusted for autocorrelation for each study period. ResultsWe identified a total of 8335 HH indications. There were non significant increases in the total compliance rate (9.0%, 95% CI -2% to 20%) at the time of intervention and in the compliance rate after intervention (0.26%, 95% CI -0.31% to 0.84%) per day. The hand hygiene compliance before patient contact significantly increased (19.8%, 95% CI, 4.8%-34.8%). Incorrect glove use improved non-significantly with the intervention (-3.4%, 95% CI -13.4% to 6.7%). ConclusionIn this study of HH monitoring using video-camera footage combined with an intervention including feedback and education, there were inconsistent improvements in HH compliance. However, these improvements were not sustained in the long term. Frequent feedback and education may be required to sustain high compliance.

Toward Deep Transfer Learning for Realistic Activity Recognition in Videos

Today, videos have become popular on the internet and specified in social network and media platforms such as Youbue, Ticktok, and Vimeo. Video understanding has attracted much attention in the research community in recent years. Automatically recognizing human activity in wild videos is a trending research topic with a wide range of applications in advertising, smarthome, and surveillance camera systems. Deep convolutional neural networks have become a new de facto visual recognition problem. It achieved much success in image recognition problems that are leveraged from the ImageNet dataset. Many researchers have applied CNNs to the video domain, but the results in realistic video still have many challenges, and the recognition rate is not as expected. Because the realistic activity in video is extremely small, we cannot train a large deep convolutional network to achieve good performance. In this work, we answer the question “how could we transfer the visual features from the ImageNet dataset into video for activity recognition tasks?”. We propose an approach based on the pretrained models from ImageNet for activity recognition in video that is based on transforming video into an image map for temporal information and a frame-based description for spatial information. We test our proposed approach on three datasets, UCF11, UCF50 and UCF101, and it achieves an accuracy of over 95% for the backbone of ResNet and over 88% for the backbone of MobileNet. The experimental results show that our proposed method is robust and efficient in wild video datasets.

Crime Anomaly Detection using CNN and Ensemble Model

Every single day, thousands of crimes are perpetrated, and hundreds may be probably taking place right now throughout the world. Without a doubt, crime is viewed as a social blight. Nothing can truly stop it, no matter what is done. Surveillance cameras, on the other hand, can dramatically minimize it. Using public surveillance camera systems to prevent, document, and minimize crime can be a cost-effective solution. Installing enough cameras to detect crimes in progress and integrating technology to automate the monitoring of the live stream from these cameras will result in the most effective systems. Because of its self-learning characteristics, the advanced Artificial Intelligence surveillance system is constantly learning and improving. The Deep Learning Algorithms applied in this work processes videos using electronic devices like cameras in real-time termed as image processing, saving both human resources and a great deal of time. The highest accuracy of 86.6% was attained by Ensemble Model, followed by Inception Model with SGD Optimizer, Leaky Relu Activation Function giving an accuracy of 83.43%. Hence, anomalies were detected efficiently using decision making in real-time surveillance scenarios.