CCTV Surveillance Research Articles

Unveiling Rare Patterns: Anomaly Detection in CCTV Footage for Safeguarding Home Premises

Abstract Protecting residential properties through CCTV surveillance has become a crucial aspect of contemporary living. In the age of data-driven security, detecting unusual and infrequent patterns within CCTV footage is of significant importance. Conventional anomaly detection methods often need help to handle the intricacies and distinctiveness of home environments, where family members and potential intruders co-exist. To address these challenges, this research incorporates extensive datasets, various machine-learning techniques, and thorough evaluation measures to pinpoint rare patterns that might signal threats to residential premises. These findings provide valuable insights for homeowners, security professionals, and developers working on surveillance systems.

Legal Implications of Covert CCTV Surveillance: Liability for Offenders and Obligations of Premises Owners

This study employs a normative juridical approach, specifically utilizing the statutory method, to analyze the legal repercussions of clandestine CCTV surveillance. Drawing from primary legal sources such as Law Number 11 of 2008 concerning Information and Electronic Transactions, Law Number 27 of 2022 concerning Protection of Personal Data, Law Number 44 of 2008 concerning Pornography, and the Criminal Code, this research delves into the ethical and legal dimensions surrounding the installation of covert cameras in public and private spaces. Results indicate that clandestine CCTV recording infringes upon individual privacy and security rights, posing serious ethical and legal challenges. Moreover, this study elucidates the responsibilities of property owners where such surveillance occurs. The implications underscore the imperative for stringent legal measures to safeguard personal privacy and uphold ethical standards in surveillance practices. Highlights : Hidden CCTV installations breach individual privacy and security rights, raising significant legal concerns. Analysis of primary legal sources reveals the complex interplay between electronic transactions laws, personal data protection regulations, and statutes addressing pornography and criminal offenses. Property owners bear responsibility in ensuring ethical and lawful surveillance practices within their premises, necessitating clear legal guidelines and enforcement mechanisms. Keywords: CCTV surveillance, legal consequences, privacy rights, statutory approach, ethical standards.

Assessment of Its Implementation on Safety on Yamuna Expressway

With the promise of fast connectivity between Greater Noida and Agra, the Yamuna Expressway represents modern infrastructure in India. Amidst all this splendor, though, is a grave worry: security. In order to reduce hazards and improve safety standards, this article investigates the complex network of obstacles that has been encountered while implementing safety measures on the highway. Numerous accidents, including fatalities, have been a recurring problem on the Yamuna Expressway since its opening. The expressway's relatively straight and smooth construction makes it easy for drivers to speed and act irresponsibly, which is the main cause of these incidents. Drivers disregard safety protocols and speed limits with complete disregard for the consequences, which is worsened by the lack of effective enforcement of traffic regulations. The absence of necessary safety elements is one of the primary obstacles to guaranteeing safety on the Yamuna Expressway. Poor lighting, inadequate signage, and restricted emergency services are some of the initial shortcomings that have greatly impacted drivers' ability to navigate safely, especially in bad weather or at night. There have been ongoing attempts to resolve safety problems, but the results have been mixed. The expressway's safety infrastructure has been strengthened by the implementation of measures such as crash barriers, better signage, expanded CCTV surveillance, and more police patrolling. Unfortunately, problems with corruption within law enforcement agencies, a lack of staff, and limited resources make it difficult to apply these restrictions effectively. The Yamuna Expressway can only be made safer with a comprehensive plan. A culture of safety among drivers can be greatly enhanced by public awareness programs that promote responsible driving and emphasize the repercussions of reckless driving. Intelligent transportation systems (ITS) integrate cutting-edge tech to improve traffic management and accident prevention via tools like speed cameras, automatic toll collecting, and real-time traffic monitoring. The Yamuna Expressway is an impressive example of India's infrastructure, yet it will remain unfulfilled until the critical problem of safety is resolved. The Yamuna Expressway has the potential to become a model of safe and efficient transportation for the millions of people who use it every day if we recognize the problems, find lasting solutions, and encourage everyone to do their part to keep everyone safe.

Enhancing Surveillance Vision with Multi-Layer Deep Learning Representation

This paper aimed to develop a method for generating sand–dust removal and dehazed images utilizing CycleGAN, facilitating object identification on roads under adverse weather conditions such as heavy dust or haze, which severely impair visibility. Initially, the study addressed the scarcity of paired image sets for training by employing unpaired CycleGAN training. The CycleGAN training module incorporates hierarchical single-scale Retinex (SSR) images with varying sigma sizes, facilitating multiple-scaled trainings. Refining the training data into detailed hierarchical layers for virtual paired training enhances the performance of CycleGAN training. Conventional sand–dust removal or dehazing algorithms, alongside deep learning methods, encounter challenges in simultaneously addressing sand–dust removal and dehazing with a singular algorithm. Such algorithms often necessitate resetting hyperparameters to process images from both scenarios. To overcome this limitation, we proposed a unified approach for removing sand–dust and haze phenomena using a single model, leveraging images processed hierarchically with SSR. The image quality and image sharpness metrics of the proposed method were BRIQUE, PIQE, CEIQ, MCMA, LPC-SI, and S3. In sand–dust environments, the proposed method achieved the highest scores, with an average of 21.52 in BRISQUE, 0.724 in MCMA, and 0.968 in LPC-SI compared to conventional methods. For haze images, the proposed method outperformed conventional methods with an average of 3.458 in CEIQ, 0.967 in LPC-SI, and 0.243 in S3. The images generated via this proposed method demonstrated superior performance in image quality and sharpness evaluation compared to conventional algorithms. The outcomes of this study hold particular relevance for camera images utilized in automobiles, especially in the context of self-driving cars or CCTV surveillance systems.

Fugitive Location Identification System Using Photo Matching Across Distributed Surveillance Networks

Abstract: Using image matching algorithms from distributed CCTV surveillance networks, this research suggests a criminal identification method. This method aims to increase the effectiveness and efficiency of identifying and apprehending criminals by using the capabilities of networked surveillance cameras. The distributed CCTV network and the matching algorithm make up the two primary parts of the suggested system. The vast array of security cameras that make up the distributed CCTV network are positioned in different areas, including streets, buildings, and public areas. These cameras provide data to a central computer by taking pictures of people in real time.

Anomaly Detection in CCTV Surveillance

CCTV surveillance systems are routinely utilized to maintain the safety and security of public and private locations. However, manually watching surveillance footage may be tiresome and time-consuming, making it difficult to recognize and respond to possible threats quickly. In this research, we offer a real-time danger detection system for CCTV monitoring that uses deep learning models to identify and categorize degrees of high movement in video frames. Our system is able to continuously monitor surveillance footage in real-time and identify potential threats such as abuse, burglaries, explosions, shootings, fighting, shoplifting, road accidents, arson, robbery, stealing, assault, and vandalism by treating videos as segments and defining anomalous (threatening) and normal (safe) segments. We conducted extensive tests on a huge collection of CCTV video to evaluate the effectiveness of our system and obtained encouraging findings. Our solution has the potential to greatly increase the efficiency and efficacy of CCTV surveillance, allowing for faster reaction times and improved individual security. We use multiple instance learning (MIL) to automatically develop a deep anomaly ranking model that predicts high anomaly scores for anomalous video segments by treating normal and anomalous films as bags and video segments as instances. In addition, we apply sparsity and temporal smoothness requirements in the ranking loss function to improve anomaly localization during training. In addition, we present a novel large-scale, first-of-its-kind dataset comprising 128 hours of video. It comprises of 1900 uncut real-world surveillance movies with 13 actual anomalies such as fights, car accidents, burglary, robbery, and so on, as well as typical activities. This dataset may be used for two different purposes. First, global anomaly detection, which takes into account all abnormalities in one group and all normal activity in another. Secondly, for identifying every one of the thirteen unusual actions. Comparing our experimental results to state-of-the-art methodologies, we find that our MIL method for anomaly detection produces a considerable increase on anomaly detection performance. We provide the findings from many recent deep learning baselines concerning the identification of aberrant behavior. These baselines' poor recognition performance indicates how difficult our dataset is, and it also provides additional room for investigation in the future.

Calibration of pedestrian ingress model based on CCTV surveillance data using machine learning methods.

Machine learning methods and agent-based models enable the optimization of the operation of high-capacity facilities. In this paper, we propose a method for automatically extracting and cleaning pedestrian traffic detector data for subsequent calibration of the ingress pedestrian model. The data was obtained from the waiting room traffic of a vaccination center. Walking speed distribution, the number of stops, the distribution of waiting times, and the locations of waiting points were extracted. Of the 9 machine learning algorithms, the random forest model achieved the highest accuracy in classifying valid data and noise. The proposed microscopic calibration allows for more accurate capacity assessment testing, procedural changes testing, and geometric modifications testing in parts of the facility adjacent to the calibrated parts. The results show that the proposed method achieves state-of-the-art performance on a violent-flows dataset. The proposed method has the potential to significantly improve the accuracy and efficiency of input model predictions and optimize the operation of high-capacity facilities.

Study on Service Quality and Priorities of Pedestrian Path Development in Malioboro Area to Support Sustainable Urban Mobility

This article aims to study the service quality and prioritize the development of pedestrian paths in the Malioboro area to support sustainable urban mobility. Malioboro is one of the commercial and tourist centers in Yogyakarta city, historically known for its pedestrian-friendly pathways. Challenges such as pedestrian circulation issues, inadequate pedestrian facilities, conflicts between pedestrians and motorized vehicles, and problems with drop-off and stop zones for less organized transportation contribute to the low service quality in the Malioboro area. This study adopts a quantitative approach using direct observation and a questionnaire distributed to 132 pedestrian path users. The collected data is analyzed using descriptive analysis techniques and Importance Performance Analysis (IPA) to understand the existing conditions, quality, and priority of pedestrian path services in the Malioboro area. The study results indicate that the service quality of pedestrian paths in Malioboro faces several challenges. Factors such as motor vehicle traffic density, lack of quality pedestrian infrastructure, and pedestrians' unsafe behavior contribute to the low service quality. The pedestrian satisfaction analysis using the Customer Satisfaction Index (CSI) revealed a satisfaction rate of 69.19%, categorizing it as "adequate." However, improvements in pedestrian path services are necessary based on the significance of the Malioboro area and its high appeal to pedestrians. The goal is to achieve good or even perfect satisfaction in terms of service quality. An analysis of interests was conducted, resulting in the identification of four quadrants with distinct characteristics. These quadrants serve as a valuable guide for enhancing the quality of pedestrian path services. Quadrant 1 encompasses attributes such as crossing facilities, CCTV surveillance, protection from weather conditions (rain, heat, cold), and parking convenience. Despite their high importance, these variables received low satisfaction ratings from respondents. Enhancing both the quantity and quality of these variables is crucial. Policymakers should pay special attention to these four variables and implement concrete measures to surpass the "adequate" assessment and attain better pedestrian service satisfaction. By implementing these measures, it is expected that Malioboro can serve as an example in supporting sustainable urban mobility by providing good and safe services for pedestrians. This study can also provide guidance and input for the government and relevant stakeholders in decision-making regarding pedestrian path infrastructure development in similar areas.

Effective flame detection and classification using deep feature of QuickDenseNet and Ensemble Score Voted SVM

Fire poses a significant threat to both lives and property, necessitating effective early detection measures. Despite challenges in identifying smoke and fire in their initial stages, we have devised a cost-efficient visual detection system. Early fire detection enhances its potential effectiveness. CCTV surveillance systems are now commonplace in developed countries, serving as tools for periodic monitoring of various locations. However, fluctuating ambient light conditions, camera angles, and seasonal variations can introduce data distortions, occlusions, and impact model accuracy. To address these issues, we’ve implemented a method combining deep learning networks and machine learning strategies for flame detection and direction classification. Our innovative QuickDenseNet extracts dense features from segmented flame video frames. We introduce the Ensemble Score Voted SVM (ESV-SVM), employing SVM as the primary learner and score voting as the auxiliary learner. Our approach is rigorously evaluated through simulations, measuring accuracy and various Key Performance Indices (KPIs), including Precision, F1-score, Recall, Correlation, Error, FPR, and Correlation Coefficients. Remarkably, our proposed method achieves an impressive precision rate of approximately 99.5%.

공공주택 경비원의 업무실무와 민간경비 환경

Abuse of security guards is not a problem of yesterday or today. Gapjil(abuse of power), or harassment, of security guards has been raised as a constant social problem in our society. 「The Enforcement Decree of the Apartment Housing Management Act」 was revised for the purpose of improving working conditions, including preventing illegal instructions or orders to security guards. However, the treatment of security guards in their work is not improving. In particular, due to the conflict between the security duties under the 「Security Business Act」 and the security duties under the 「Apartment Housing Management Act」, the duties of security guards working in apartment complexes are different, so there is a need to provide clear duties regarding this. Accordingly, this study sought to discuss the specifics of the security duties of apartment security guards. To achieve this research purpose, interviews were conducted with security guards working in apartment complexes, security companies and apartment complex managers, representatives of apartment residents, and police science professors.
 As a result of the study, apartment security guards presented the main tasks of theft and fire, prevention of danger, patrol, crime prevention, CCTV surveillance, and outsider access management. However, in contrast, representatives of apartment residents and managers of apartment complexes were presented with roles that, in addition to the main duties of security guards, include parcel storage, parking management, and even assisting with the general work of the management office. Based on the results of this study, we attempted to discuss the work of apartment security guards, and it is expected that this study will be used as basic practical data for security work as well as academic discussions in private security work.

Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy

Real-time video surveillance, especially CCTV systems, requires fast and accurate face detection. Object detection models with slow inference times are ineffective in real-time. This study addresses this challenge by improving the inference speed of the YOLOv8 model, a leading object detection framework known for its accuracy and speed. We focus on pruning the model's architecture, particularly the P5 head section, which detects larger objects. According to Bochkovskiy's 2020 research, this modification enhances the model's performance specifically for medium and small objects in CCTV footage. The standard YOLOv8 model and its modified version were compared for inference time, mean Average Precision (mAP), and model weight. The pruned YOLOv8 model cuts inference time by 15.56%, from 4.5 ms to 3.8 ms, and reduces model weight. The advantages mentioned above are offset by a 1.6% decrease in mean average precision. This research advances object detection technology by demonstrating architectural modifications' efficacy. These changes make the model faster and lighter, making it suitable for real-time surveillance. The accuracy trade-off is slight. The implications of these findings are crucial for implementing efficient object detection systems in CCTV surveillance. These findings also lay the groundwork for future research to improve such systems' speed-accuracy trade-off.

A Systematic Review of Using Machine Learning and Natural Language Processing in Smart Policing

Smart policing refers to the use of advanced technologies such as artificial intelligence to enhance policing activities in terms of crime prevention or crime reduction. Artificial intelligence tools, including machine learning and natural language processing, have widespread applications across various fields, such as healthcare, business, and law enforcement. By means of these technologies, smart policing enables organizations to efficiently process and analyze large volumes of data. Some examples of smart policing applications are fingerprint detection, DNA matching, CCTV surveillance, and crime prediction. While artificial intelligence offers the potential to reduce human errors and biases, it is still essential to acknowledge that the algorithms reflect the data on which they are trained, which are inherently collected by human inputs. Considering the critical role of the police in ensuring public safety, the adoption of these algorithms demands careful and thoughtful implementation. This paper presents a systematic literature review focused on exploring the machine learning techniques employed by law enforcement agencies. It aims to shed light on the benefits and limitations of utilizing these techniques in smart policing and provide insights into the effectiveness and challenges associated with the integration of machine learning in law enforcement practices.

Smart CCTV Surveillance System with Visitor Management System, Face Detection, Fire Alarm, Parking Assistant for Residential Areas

Abstract: The "Smart CCTV Surveillance System" stands as a revolutionary solution at the nexus of security, cutting-edge technology, and user-centric design. Anchored by features such as real-time facial recognition, trustworthiness recognition, and comprehensive threat detection, the system redefines the paradigm of surveillance and access control. Beyond addressing the critical challenges of unauthorized access and security threats, this project introduces a robust fire alarm feature. By integrating sophisticated algorithms for real-time fire detection, the system ensures swift response to potential emergencies. Alongside this, the project streamlines visitor management through automation, optimizing registration, check-in, and check-out processes. The addition of parking assistance enhances the overall user experience, guiding visitors to available parking spaces and mitigating congestion. In essence, the "Smart CCTV Surveillance System" not only establishes an impregnable security infrastructure but also envisions a future where technology seamlessly collaborates with human needs, fostering environments that are not just secure but also smarter and more user-friendly

A Multi-Modal Approach for Age and Gender Revelation for Enhanced Voting Systems

Abstract: Humanity has made advancements in innovation pushing the boundaries of what was deemed impossible. With the help of cutting edge technology we can now determine a persons age and orientation by analyzing their image or video footage. This paperprovides an overview of the process including the techniques, strategies and algorithms involved. Unlike methods that treated these aspects separately this approach seamlessly integrates them all. It emphasizes the significance of this breakthrough. Explores its applications, in our daily lives. The main objective of this endeavor is to develop an age and orientation detector that utilizes Convolutional Neural Networks (CNN) and OpenCV to analyze features in images. Furthermore this paper showcases real world scenarios where this technology can be applied. Ranging from security services CCTV surveillance and law enforcement, to dating apps and matrimonial websites. Age and orientation estimations are determined based on image characteristics.

Implementasi Sanksi Denda Elektronik Traffic Law Enforcement (E-Tle)

Every motorized vehicle driver must comply with traffic rules and regulations. This aims to ensure the safety of motorized vehicle drivers and other road users. But because of the increase in the number of motorized vehicles, the accident rate continues to increase every year and the number of victims continues to increase, which is one of the bad factors in the increase in the number of motorized vehicles in Indonesia. This factor occurs due to the driver's human negligence, starting from lack of sleep, fatigue, carelessness, and low rider discipline. The police enforced it with fines but it was still frequently violated by motorists. Therefore, the existence of electronic tickets (E-TLE) using CCTV surveillance cameras, is expected to help reduce violations and reduce the level of road accidents. This study raises problems by looking at the obstacles experienced in the implementing E-TLE ticket fines and the obstacles experienced in the implementing E-TLE ticket fines in the jurisdiction of the Surabaya City Police. This research uses empirical juridical research. The results of this study are the obstacles that traffic police officers face when applying ETLE fines are: Unclear ETLE cameras, lots of fake license plates, E-tickets that are not on target, Accessibility of the application network, E-ticket services that are just In Time, integration of data that has not been uploaded, lack of socialization and the community does not have the E-Tilang application. And the obstacles faced by traffic police officers when applying ETLE fines are: factors of law enforcers who still accept bribes and lack of understanding of Law Number 22 of 2009 concerning Road Traffic and Transportation, Community factors, namely the lack of understanding of the community in driving on the highway and the lack of knowledge about traffic violations, and application system factors and electronic devices where there are still errors in their use and CCTV cameras that are not clear in photographing violating motorists.

IoT forensics: Exploiting log records from the DAHUA technology CCTV systems.

CCTV surveillance systems are ubiquitous IoT appliances. Their forensic examination has proven critical for investigating crimes. DAHUA Technology is a well-known manufacturer of such products. Despite its global market share, research regarding digital forensics of DAHUA Technology CCTV systems is scarce and currently limited to extracting their video footage, overlooking the potential presence of valuable artifacts within their log records. These pieces of evidence remain unexploited by major commercial forensic software, yet they can hide vital information for an investigation. For instance, these log records document user actions, such as formatting the CCTV system's hard drive or disabling camera recording. This information can assist in attributing nefarious actions to specific users and hence can be invaluable for understanding the sequence of events related to incidents. Therefore, in this paper, several DAHUA Technology CCTV systems are thoroughly analyzed for these unexplored pieces of evidence, and their forensic value is presented.

Identification of Trajectory Anomalies on Video Surveillance Systems

Recently, CCTV surveillance applications have remarkably developed for public welfare. However, the investigation of different techniques for online implementation is always significantly restricted. Numerous implementations propose for detecting irregularities of moving objects in the videotape. Performance of fuzzy in trajectory's anomaly is one of the most robust detection procedures. In this paper, the authors propose a fuzzy implemented trajectory anomalies detection technique with the help of some parameters such as velocity, path deviation, and size of the moving objects. The critical aspect of the framework is a compact set of highly descriptive features extracted from a novel cell structure that helps us define support regions in a coarse-to-fine fashion. This paper also illustrates a small outline of different detection techniques. The authors also exhibit the outcome of experiments on the Queen Mary University of London junction dataset (QMUL).

THE USE AND IMPACT OF ICT AMONG STUDENTS AND TEACHERS:A CASE STUDY WITH REFERENCE TO MILAGRES COLLEGE MANGALURU

Purpose: Realizing the modern trends of ICT, Milagres College Mangalore has initiated and installed all possible ICT related facilities. The college has made extra efforts to provide the ICT facilities for UG students, staff and faculty members to promote and develop the teaching-learning process. Therefore, an attempt is made to take up this topic as a case study to analyze the impact of ICT and its contribution on Education at Milagres College, Mangaluru, D.K, and India. Methodology: The fundamental facts are gathered from primary and secondary sources. Structured surveys are used to gather primary data, and books, articles, and websites are used to collect secondary data. The respondents are chosen using the convenience sample approach. The studys sample size is 50, and the participants are staff and students of Milagres College in Mangalore. Findings: The results of the study showed that the integration of ICT has contributed in creating better atmosphere of teaching learning process. As a result, it has helped teachers to be more engaged, productive,interactive and dynamic in learning teaching environments at Milagres College. The college has provided Internet facilities to every class room, WI -fi on every floor, LCD projectors in every class room. Facilities such as well-set Computer Lab with internet facility, E-Library facility in the reading room and NLIST and Easylib Library Management Softwares, Milagres Learning Management System (MLMS), Enterprise Resource Planning (ERP) Education Administration Management, E-Content recording and publishing, Power Point Presentation, YouTube Videos, CCTV surveillance security system, Biometric Attendance System, Online and digital Payment System, Social Media Platforms, Intercom communication system, Google Meet, Zoom and WebEx online classrooms platforms etc. are been used for teaching learning process and administrative purposes. Originality: This case study discusses the management initiatives that have facilitated the college beyond the campus, through online teaching learning initiatives and analyses the impact of these efforts on knowledge dissemination and a teacher productivity (Eengagement) Paper type: Case study KEY WORDS: ICT, LMS, E-Library, Easylib, ERP, Teaching Learning Process, Resource, Perception, Communication, Promotion, Management, Engagement.

Form follows function: Applying photographic content analysis to forensic firearm identification.

Drawing forensic conclusions from an image or a video is known as "photographic content analysis." It involves the analysis of an image, as well as objects, actions, and events depicted in images or video. In recent years, photographic depictions of objects suspected as illegal firearms have substantially increased, appearing on CCTV surveillance footage, captured by mobile phones and shared on social media. However, the law in Israel states that a person can be charged with illegally possessing a firearm only if it can be proven that the object is capable of shooting with lethal bullet energy. This becomes more challenging in cases where the firearm was not physically seized, and the evidence exclusively consists of images and video. In this study, photographic content analysis was applied to images and video where objects suspected as commercial or improvised firearms had been depicted. An image and event sequence reconstruction video databases of both firearms and replicas were created in order to better define firearm-specific functional morphological features. We demonstrate that it is possible to classify an object as a firearm by analyzing the functional, and not only the esthetic, morphology in images and video. It is also shown that event sequence reconstruction in video may be used to infer that an object suspected as a firearm has the capacity to shoot by confirming the occurrence of a shooting act or shooting process. Thus, photographic content analysis may be used to forensically establish that an object depicted in an image or a video is a firearm by ruling out other known scenarios, and without physically seizing it.

IoT forensics: Exploiting unexplored log records from the HIKVISION file system.

CCTV surveillance systems are IoT products that can be found almost everywhere. Their digital forensic analysis often plays a key role in solving crimes. However, it is common for these devices to use proprietary file systems, which frequently hinders a complete examination. HIKVISION is a well-known manufacturer of such devices that typically ships its products with its proprietary file system. The HIKVISION file system has been analyzed before but that research has focused on the recovery of video footage. In this paper, the HIKVISION file system is being revisited regarding the log records it stores. More specifically, these log records are thoroughly examined to uncover both their structure and meaning. These unexplored pieces of evidence remain unexploited by major commercial forensic software, yet they can contain critical information for an investigation. To further assist digital forensic examiners with their analysis, a Python utility, namely the Hikvision Log Analyzer, was developed as part of this study that can automate part of the process.