Closed-Circuit Television (CCTV) systems are essential in modern security setups because they provide continuous surveillance, acting as both a deterrent and a critical tool for monitoring and evidence collection. Unlike human guards who can be limited by fatigue and blind spots, CCTV cameras offer consistent, 24/7 coverage of key areas. They fill gaps in the current security system by enabling real-time monitoring and recording incidents for later review, ensuring that potential security breaches are detected and addressed more effectively. (...) This enhances overall security effectiveness and reduces the reliance on human intervention. The integration of Artificial Intelligence and Machine Learning (AIML) techniques with existing CCTV networks presents a promising approach to address critical challenges in urban environments. This project examines how AIML can be leveraged for crowd management, crime prevention, and work monitoring using CCTV infrastructure. For crowd management, AIML enables automated crowd counting and density estimation, facilitating efficient allocation of resources during events and emergencies. In crime prevention, AIML algorithms analyze video feeds in real-time to detect suspicious activities and identify anomalies, aiding law enforcement in proactive interventions. Additionally, AIML enhances workplace monitoring by tracking productivity metrics, ensuring compliance with safety protocols, and optimizing operational workflows. Through these applications, AIML empowers cities and organizations to improve public safety, enhance operational efficiency, and make data-driven decisions based on insights derived from CCTV footage. The integration of AIML with existing CCTV networks represents a transformative advancement in urban surveillance and management practices, offering scalable solutions for diverse urban challenges. (shrink)

including public spaces, businesses, and homes. However, traditional systems often rely on basic motion detection and manual monitoring, which can miss critical security threats or aggressive behaviors, particularly those indicated by human gestures. Existing methods, such as facial recognition and motion-based alerts, may lack the sensitivity and accuracy needed for effective risk assessment related to hand gestures. To address these limitations, this paper proposes an advanced system that integrates hand gesture recognition into real-time CCTV surveillance. Using OpenPose for gesture (...) recognition and MediaPipe for feature extraction, the system can identify potentially threatening gestures, such as clenched fists or aggressive pointing. Once a high-risk gesture is detected, the system automatically triggers alerts to the nearest police station and authorized personnel through SMS, email, and mobile app notifications. Additionally, the system uses geolocation to ensure that alerts are sent to the appropriate authorities in the vicinity. This proactive approach enables immediate response and improves the effectiveness of surveillance systems, allowing for quicker threat detection and intervention. The integration of hand gesture recognition enhances traditional CCTV systems, providing a more intelligent and responsive security solution that aims to reduce response times and mitigate security risks. (shrink)

The proposed system employs AI technologies to analyze hand gestures in real-time as it functions for emergency alert transmission through CCTV camera feeds but works independently from verbal or physical signals. The system operates with Python-based technologies and OpenCV for live video streaming alongside MediaPipe for hand landmark detection through a standard webcam. The system detects predefined gestures including emergency signals through closed fists combined with stop gestures using open palms and victory signs by checking the relative landmark positions (...) on hands. In case the system detects an emergency gesture it retrieves positioning data through IPbased geolocation before automatically sending a message with gesture details and timestamp and coordinates. The system distributes the alert distribution task to different threads to maintain live video streaming processing continuity. The system contains a cooldown function that blocks subsequent alerts when they occur within short time periods. Low-end hardware and accessibility through lack of sensor dependency enable the system to deliver efficient operations. The system provides discreet signals for emergency help requests which prove useful to endangered individuals and people with disabilities and medical patients in crisis situations. Future improvements will create facial authentication capability in addition to SMS monitoring and mobile software release which will turn this product into a life-saving solution for public protection agencies. (shrink)

In a recent article in Respublica, Jesper Ryberg argues that CCTV can be compared to a little old lady gazing out onto the street below. This article takes issue with the claim that government surveillance can be justified in this manner. Governments have powers and responsibilities that little old ladies lack. Even if CCTV is effective at preventing crime, there may be less intrusive ways of doing so. People have a variety of legitimate interests in privacy, and protection (...) for these is important to their status as free and equal citizens. Consequently, though necessary, effectiveness is insufficient to justify CCTV in a democracy. (shrink)

In this paper I critique the ethical implications of automating CCTV surveillance. I consider three modes of CCTV with respect to automation: manual, fully automated, and partially automated. In each of these I examine concerns posed by processing capacity, prejudice towards and profiling of surveilled subjects, and false positives and false negatives. While it might seem as if fully automated surveillance is an improvement over the manual alternative in these areas, I demonstrate that this is not necessarily the (...) case. In preference to the extremes I argue in favour of partial automation in which the system integrates a human CCTV operator with some level of automation. To assess the degree to which such a system should be automated I draw on the further issues of privacy and distance. Here I argue that the privacy of the surveilled subject can benefit from automation, while the distance between the surveilled subject and the CCTV operator introduced by automation can have both positive and negative effects. I conclude that in at least the majority of cases more automation is preferable to less within a partially automated system where this does not impinge on efficacy. (shrink)

The "Smart and Effective Real-time Management of Street Parking" project is designed to enhance urban parking enforcement through the use of advanced machine learning and computer vision technologies. The system leverages CCTV cameras to continuously monitor parking spaces, detecting their availability and instances where vehicles are incorrectly parked. By analyzing video feeds, the system identifies parking violations and extracts license plate numbers using Optical Character Recognition (OCR). Notifications are promptly sent to drivers regarding their parking status, ensuring timely enforcement (...) of parking regulations. This approach focuses on effective management of parking resources and compliance with regulations. The system’s real-time capabilities contribute to a significant reduction in urban congestion by promoting orderly parking practices and efficient use of parking resources. Implementation of this technology supports enhanced urban planning initiatives by providing valuable data insights into parking patterns and violations, thus fostering a more organized, sustainable, and efficient urban environment. (shrink)

Near the end of December 2019, the globe was hit with a major crisis, which is nothing but the coronavirusbased pandemic. The authorities at the train station should also keep in mind the need to limit the spread of the covid virus in the event of a global pandemic. When it comes to controlling the COVID-19 epidemic, public transportation facilities like train stations play a pivotal role because of the proximity of so many people who may be exposed to the (...) virus. Using common place CCTV cameras and deep learning with simple online and real-time (DeepSORT) methods, this study develops social distance monitoring using a YOLOv4 identification of a Surveillance Object Model. Based on experiments conducted with a minicomputer equipped with an Intel 11th Gen Intel(R) Core(TM) i3-1115G4 at 3.00GHz, 2995 Mhz, two Core(s), four Logical processor, four gigabytes of random-access memory (RAM), this paper makes use of CCTV surveillance, which was put into practice at the Guindy railway station, Chennai, Tamilnadu in India in order to detect the violation of social distancing. (shrink)

‘Torture porn’ films centre on themes of abduction, imprisonment and suffering. Within the subgenre, protagonists are typically placed under relentless surveillance by their captors. CCTV features in more than 45 contemporary torture-themed films (including Captivity, Hunger, and Torture Room). Security cameras signify a bridging point between the captors’ ability to observe and to control their prey. Founded on power-imbalance, torture porn’s prison-spaces are panoptical. Despite failing to encapsulate contemporary surveillance’s complexities (see Haggerty, 2011), the panopticon remains a dominant paradigm (...) within surveillance studies because it captures essential truths about the psychologies of self-governance and interdependency. This chapter will use torture porn’s panoptical spaces and captor-captive relationships as a springboard into examining those broader philosophical issues regarding selfhood. In the torture-space, cameras signify the control to which captives must submit. Since they are threatened with death, the surveillance dynamic appears to entirely subjugate these prisoners. However, the captive must undertake some agency in the oppression. Much of the captor’s implied threat is enacted by the captives, who brutalise one another to save themselves. The captor’s apparent omniscience is translated into omnipotence only because the captives forsake self-control – opting to engage in violent, contra-social behaviours – out of fear. Thus, it is implied that self-ownership is the bedrock of stable, interdependent sociality. To inspire horror, the opposite is depicted: fractured groups comprised of paranoid, self-invested individuals. By submitting to external pressure, these “weak” individuals empower their tormentor. Captives are not only encouraged to enact their own suppression, but also to internalise culpability for the suffering they undergo. Despite being threatened with erasure, torture porn’s protagonists are spotlighted in these films. Abductees dominate the screen-time, and their suffering drives the narrative forward. Torturers are often motivated solely by their victims’ agony. In many cases, torture is designed specifically for each hyper-individualised captive. These forms of emphasis imply that captives are the stimulus for their own victimisation. The captor’s exaggerated interest in the prisoners is perversely flattering: captives are implied to be worthy of the captor’s maniacal attention, which is reified by the CCTV cameras. In torture porn’s scenarios, it is not immediately clear who has greater control over the individual: the captor or the captive themselves. By dissecting how self-preservation, self-governance, and self-centredness manifest in torture porn, this chapter seeks to examine the dialectical qualities of liberty, interdependency and autonomy. (shrink)

COVID-19 pandemic caused by novel coronavirus is continuously spreading until now all over the world. The impact of COVID-19 has fallen on almost all sectors of development. The healthcare system is going through a crisis. Many precautionary measures have been taken to reduce the spread of this disease where wearing a mask is one of them. In this paper, we propose a system that restricts the growth of COVID-19 by finding out people who are not wearing any facial mask in (...) a smart city network where all the public places are monitored with Closed-Circuit Television (CCTV) cameras. While a person without a mask is detected, the corresponding authority is informed through the city network. A deep learning architecture is trained on a dataset that consists of images of people with and without masks collected from various sources. The trained architecture achieved 98.7% accuracy on distinguishing people with and without a facial mask for previously unseen test data. It is hoped that our study would be a useful tool to reduce the spread of this communicable disease for many countries in the world. (shrink)

During an epidemic, it is very important to follow the instructions issued by the official authorities. One big step at this point is Social Distancing. It is very difficult for the authorities to keep a detailed look at whether social distancing norms are being followed or not. We meet situations where instead of following these rules patiently, people become frightened and often crowd the space. Therefore, for simple monitoring for the authorities (e.g. police officers) we propose a solution using the (...) Deep Learning process that will notify them as soon as a public violation occurs i.e., if the number of people is above the specified limit (the limit on the number of people that are allowed to be in one place at a time, specified by the government) or if the distance among two people is less than the specified limit. This program will not only reduce the effort and effort required to manually inspect each and every nearby location, but also help in saving time with the help of fast analysis in simple terms, CCTV cameras will help simultaneously monitor each public places. (shrink)

A subdiscipline has emerged around AI ethics, which is comprised of a wide array of individuals: computer scientists, ethicists, cognitive scientists, roboticists, legal professionals, economists, sociologists, gender, and race theorists. This has led to a very interesting branch of research, addressing issues surrounding the development and use of AI. This chapter will give a very brief snapshot of some of the most pertinent ethical concerns. Many of the issues in the Big Data Ethics chapter in this collection are often applicable (...) to AI ethics, because of the data that these technologies retrieve, store, and use, so will not be duplicated here.1 -/- While data-related issues are not new or unique to AI, AI does hold the potential to dramatically retrieve and analyze data that would not be possible otherwise. Data is being used in unique and transformative ways, such as the use of facial recognition to identify individuals from photos or CCTV; AI robots to retrieve live video feed about the patient(s) that it is monitoring; or in new ways, such as self-driving cars collecting an abundance of data about our surroundings, how we drive, and passengers in the car. There is the potential to infringe on individuals’ privacy, restriction of resources, or at worst, the creation of a surveillance society. (shrink)

Anamoly detection in videos plays an important role in various real-life applications. Most of traditional approaches depend on utilizing handcrafted features which are problem-dependent and optimal for specific tasks. Nowadays, there has been a rise in the amount of disruptive and offensive activities that have been happening. Due to this, security has been given principal significance. Public places like shopping centers, avenues, banks, etc. are increasingly being equipped with CCTVs to guarantee the security of individuals. Subsequently, this inconvenience is making (...) a need to computerize this system with high accuracy. Since constant observation of these surveillance cameras by humans is a near-impossible task. It requires workforces and their constant attention to judge if the captured activities are anomalous or suspicious. Hence, this drawback is creating a need to automate this process with high accuracy. Moreover, there is a need to display which frame and which parts of the recording contain the uncommon activity which helps the quicker judgment of that unordinary action being unusual or suspicious. Therefore, to reduce the wastage of time and labour, we are utilizing deep learning algorithms for Automating Threat Recognition System. Its goal is to automatically identify signs of aggression and violence in real-time, which filters out irregularities from normal patterns. We intend to utilize different Deep Learning models (CNN and RNN) to identify and classify levels of high movement in the frame. From there, we can raise a detection alert for the situation of a threat, indicating the suspicious activities at an instance of time and spray the smoke spray. (shrink)

en the increasing importance of human target detection in various security applications, many existing systems face challenges related to cost, accuracy, and adaptability. This work presents the development of a machine learning-based system called Human Target Detection and Acquisition, designed to assist security personnel in the detection and tracking of human targets through an adaptive and cost-effective approach. In this, standard CCTV cameras provide visual data, which intelligent algorithms process to identify and track human targets, even in challenging conditions. (...) The system offers user-specific dashboards: administrators can monitor detections and adjust system parameters, while security personnel receive real-time alerts and tracking information. Additionally, it supports continuous improvement through its machine learning capabilities, allowing for enhanced performance over time without the need for hardware upgrades. The architecture of the platform relies on TensorFlow, OpenCV, and database integration for efficient handling of video processing and data management. Initial testing suggests that it can provide accurate and reliable human target detection while significantly reducing costs compared to hardwareintensive solutions. Future work includes expanding the system's capabilities to handle multiple camera feeds simultaneously and implementing more advanced tracking algorithms. (shrink)

Developing countries have always relied on motorcycles as their primary mode of transportation, but unfortunately, the number of motorcycle accidents has been on the rise in recent years. One of the leading causes of fatalities in these accidents is the lack of helmet usage by motorcyclists. To ensure that motorcyclists wear helmets, traditional methods include manual monitoring by traffic police at intersections or the use of CCTV footage to identify those not wearing a helmet. However, these methods require significant (...) human effort and intervention. This system proposes an automated approach to identify non-helmeted motorcyclists and retrieve their license plate information from CCTV footage. The system first differentiates moving objects as motorcycles or non-motorcycles. For classified motorcyclists, the system identifies whether they are wearing helmets or not. If the motorcyclist is not wearing a helmet, the system extracts the license plate number using an OCR algorithm. In this project CNN and yolo algorithms are used for recognition of person with and without helmet as well as triple riding detection. The violated person number plate is detected if its visible. (shrink)

Suspicious Activity Detection System is a real-time monitoring and analysis tool developed using Python with Tkinter, OpenCV, and Image AI libraries. The system integrates a modern graphical user interface (GUI) to facilitate video processing, frame generation, and suspicious activity detection from both live camera feeds and prerecorded CCTV footage. Leveraging the DenseNet121 deep learning model for image classification, the system processes video frames to identify potential suspicious activities, employing temporal consistency and confidence thresholding to enhance detection accuracy. Key features (...) include live feed toggling, video recording with timestamped storage, and automated frame extraction, with suspicious frames flagged and saved for further review. The GUI, styled with a sleek dark theme and gradient aesthetics, provides intuitive controls and dual text areas for logging frame generation and detection results. Advanced visualization overlays detection metrics on frames, while the system ensures robust error handling and resource cleanup. Designed for security applications, this tool demonstrates a scalable approach to real-time video analysis, balancing usability and performance. Future enhancements could include multicamera support and expanded activity classification capabilities. (shrink)

Real-time monitoring systems use surveillance videos to automatically detect motorcycle helmet requirements and triple-riding violations, which protect road safety. Deep learning methods currently show practical worth for addressing surveillance system constraints because they have developed superior capabilities in object detection and classification. The models deliver poor results repeatedly because they are limited by low-resolution video, together with adverse weather conditions, as well as problems from occlusions and deficient illumination conditions. The issue of recognizing multiple individuals riding together on one motorcycle (...) requires better solution methods because it remains unresolved. YOLOv8 operates in real-time to detect both helmet violations and multiple riders on vehicles using CCTV video and webcam feeds. The detection system reaches a 95% accuracy level, thereby establishing itself as an effective monitoring method in automated traffic control. A YOLOv8 detection model serves for detecting triple riders, along with YOLOv8-based detection of helmet violations. The model has tailored detection skills since its training with helmet-specific data enables it to monitor properly non-helmeted riders. The system supplies capabilities for processing video and image data, which helps it create visual violation marks for practical realworld applications. Quality evaluation of the system happens through precision and recall metrics, which measure its reliable operation functions. The method utilizes publicly available data and self-collected information to solve illumination conditions and issues that affect detection systems. The evolution of traffic rule enforcement systems has improved thanks to the resolution of implementation problems. The research application proves how deep learning transforms surveillance systems, which advances road safety through system improvements. Better traffic management possibilities, combined with improved efficiency and innovation, enable wider expansion of safety programs in urban areas. (shrink)

With the rise in road traffic accidents, there is a growing need for intelligent systems that can detect incidents promptly and alert the concerned authorities without relying on human intervention. This project presents an AI-powered accident detection and reporting system that utilizes YOLO (You Only Look Once), a real-time object detection algorithm, to automatically identify vehicular accidents from live CCTV camera feeds. The system is designed to continuously monitor intersections or roadways, and when an accident is detected, it immediately (...) triggers an alert by sending an HTTP request to a specified URL endpoint (e.g., local host: 3000). A separate Python-based listener module runs on the backend, continuously listening to this port. Upon receiving the detection alert, it notifies the control room or relevant personnel, allowing them to take immediate action such as dispatching emergency services or informing nearby hospitals. This ensures faster response times and improves the chances of saving lives. The entire workflow is automated from accident detection to alert generation minimizing human delay and enhancing road safety. The system is also lightweight and can be deployed on edge devices connected to surveillance infrastructure. In essence, this project aims to provide a low-latency, high-accuracy, real-time accident monitoring system, thereby offering a practical and scalable solution for modern smart city transportation networks. (shrink)

It is especially hard, at present, to read the newspapers without emitting a howl of anguish and outrage. Philosophy can heal some wounds but, in this case, political action may prove a better remedy than philosophy. It can therefore feel odd trying to think philosophically about surveillance at a time like this, rather than joining with like-minded people to protest the erosion of our civil liberties, the duplicity of our governments, and the failings in our political institutions - including our (...) political parties – revealed by the succession of leaks dripping away this the summer. Still, philosophy can help us to think about what we should do, not merely what we should believe. Thus, in what follows I draw on my previous work on privacy, democracy and security, in order to highlight aspects of recent events which – or so I hope – may prove useful both for political thought and action. (shrink)

Study shows that mask-wearing is a critical factor in stopping the COVID-19 transmission. By the time of this article, most states have mandated face masking in public space. Therefore, real-time face mask detection becomes an essential application to prevent the spread of the pandemic. This study will present a face mask detection system that can detect and monitor mask-wearing from camera feeds and alert when there is a violation. The face mask detection algorithm uses a haar cascade classifier to find (...) facial features from the camera feed and then utilizes it to detect the mask-wearing status. With the increasing number of cases all over the world, a system to replace humans to check masks on the faces of people is greatly needed. This system satisfies that need. This system can be employed in public places like transport stations and malls. It will be of great help in companies and huge establishments where there will be a lot of workers. Alongside this, we have used basic concepts of transfer learning in neural networks to finally output the presence or absence of a face mask in an image or a video stream. Experimental results show that our model performs well on the test data with 100 percent and 99 percent precision and recall, respectively. We are making a savvy framework that will identify whether the specific user has worn the mask or not and further tell the accuracy level of the detection. Our framework will be python and AI-based which will be safe and quick for implementation. This system will be of great help there because it is easy to obtain and store the data of the employees working in that Company and will very easily find the people who are not wearing the mask and a will be sent to that respective person to take Precautions not wearing a mask. Potential delays are analyzed, and efforts are made to reduce them to achieve real-time detection. The experiment result shows that the presented system achieves a real-time 45fps 720p Video output, with a face mask detection response of 0.15s and the accuracy of detection 99%. (shrink)