CCTV Cameras Research Articles

CogniWatch: Advanced Scene Analysis for Threat Detection and Public Safety

Ensuring the safety of life and property through the deployment of high-quality CCTV cameras has become indispensable in our modern world. Manual monitoring of every moment is not feasible, and the unpredictable nature of human behavior makes distinguishing between suspicious and normal activities a formidable challenge. In this research, we introduce a novel approach utilizing Convolutional Neural Networks (CNN) to discern between suspicious and routine activities within an environment. Our proposed system is designed to automatically alert relevant authorities upon detecting potentially suspicious behavior. The effectiveness of any suspicious activity detection system hinges on several critical factors, including the quality of training data, the architecture of the Machine Learning model, and the operational environment. To maintain the system's accuracy and keep it adaptive to new and evolving threats, continuous monitoring, regular updates, and ongoing improvement are imperative. Our work underscores the importance of robust data sources and the careful design of CNN-based models to ensure the system's reliability in real-world applications. This research not only addresses the pressing need for automated surveillance but also emphasizes the significance of staying current and vigilant in the ever- changing landscape of safety and security. KeyWords: CNN, Object Detection, Anomaly, Threat, Hyperparameter Tunning.

ANALISIS TANGGUNG JAWAB PENGELOLA PARKIR TERHADAP KEHILANGAN BARANG MAHASISWA UIN JAKARTA

This research aims to determine the responsibility of parking managers for the loss of goods in parking areas considering that the increasing number of motorized vehicles in Indonesia creates additional problems in the required parking management system. Parking managers are responsible for the security of vehicles and goods in the parking area based on Article 1706 and Article 1714 of the Civil Code (KUHPerdata). Parking management is a matter of public law, but if a relationship exists between the parking manager and consumers, then the concept of certainty and the existence of rights and obligations will give rise to concepts in private law. In 2019, the National Consumer Protection Agency (BPKN) issued Circular Number 1 of 2019 concerning Consumer Protection regarding the Responsibilities of Parking Managers which emphasized that parking managers are responsible for lost goods that occur in the parking area. The parking manager can be held liable by the injured party on the basis of a breach of contract (negligence) in the goods custody agreement between the parking lot manager and the motorbike owner. In the case of lost items from UIN Jakarta students, the parking lot manager can be held responsible for the losses experienced by the student. Parking lot managers also have a moral responsibility to maintain the safety of goods entrusted to them by consumers. Efforts such as strict supervision, installing CCTV cameras, and providing experienced and trained parking attendants must be taken to prevent loss of goods from consumers.

REAL TIME DETECTION OF CHICKEN EGG QUANTITY

A common problem currently being faced in the chicken egg production home industry is difficulty in counting the number of eggs. Currently, calculating the number of eggs is still done manually, which is less than optimal and prone to errors, so many entrepreneurs often experience losses. The manual system currently used also has the potential for this to happen. The use of technology on an MSME scale among laying hen breeders has not been widely adopted, this is due to limited access and understanding of technology. One alternative solution to deal with this problem is to build a real-time computerized system. The system that will currently be built in this research uses GLCM feature extraction and the SVM classification method. This system will detect egg production via CCTV cameras and will be stored in a database to be displayed on the website. The advantage of this system is that egg entrepreneurs can monitor chicken egg yields in real time. The results of trials that have been carried out using GLCM feature extraction and the SVM classification method in calculating the number of eggs using the SVM method with a polynomial kernel are highly recommended for use in this research because it can achieve 95% accuracy.

IoT-Based academic monitoring system in Integrity Zone implementation

The Internet of Things (IoT) based academic monitoring system is implemented at the Manado State Polytechnic to achieve an Integrity Zone where educational institutions have good governance, are accountable, and are free from corruption. This research aims to design and implement an Internet of Things (IoT) based presence monitoring system. The system was developed for lecturers and students to record attendance using a microcontroller and display a QR Code on an Internet of Things (IoT) based OLED screen. Implementing this system aims to increase transparency, accountability, and the effectiveness of using lecturer time in teaching. The results are that the presence of lecturers and students can be validated through CCTV camera monitoring to display image data in real-time and table data on web pages. An application developed using Android that can be used by students and lecturers in taking attendance and sending data to the server. The server has two primary purposes: record attendance data and generate attendance reports based on user requests. System testing is carried out in a local network. The research results show that the subsystems and integrated systems work well.

Teacher’s Basic Behaviour as Motivation for Student Learning

Teachers are essential stakeholder that cannot be downplayed in education. As important as they are, their behaviour is so contagious that it can mar or help student learning. Teacher’s behaviour is a function of the characteristics of the teacher, his environment and the task in which the teacher engages. Teacher’s behaviour could be respect, relational, integrity, trust, enthusiasm among others. However, teacher’s behaviour that hinders learning are - Resistance to change, absenteeism, unpreparedness for class, inability to meet student needs. Moreover, teacher cannot just decide to misbehave for no just cause, there must have been underline factors responsible for teacher’s misbehaviour. Therefore, factors responsible for teacher’s misbehaviour are – Poor incentive, wrong conception of teaching profession, economic regression, non-inclusive of students’ diversity and culture, work related stress. The aforementioned thus, have implications on students learning. Teacher’s misbehaviour does encourage fall in morality, low self- esteem, increase in examination malpractice and so on. It is therefore, expected of the teachers to develop an appropriate behaviour such as optimistic, emotional intelligence skill, commitment to work and building positive relationship. In addition, the government and the school owners should establish and disseminate a code of conduct for teachers that will guide their behaviour, monitor teachers physically (inspection) and through technological gadget (CCTV camera); provide support for teachers at all levels (financially, academically, morally) to avoid misbehaviour.

Prediction and Prevention of Theft in Jewellery Shop

The internet of Things (IoT)-based total security is the most broadly used protection framework introduced by the technological developments. Sensors and cameras play a vital role in detecting movement and alerting the humans in lots of security applications. As these security gadgets are always accompanied with alarm systems, it is more popularly used for preventing the theft in public places like shopping malls and shops. In such areas, conventional CCTV cameras are usually used as it helps in non-stop human tracking, and detections of crimes. The proposed system is also on such intelligent security system capable of identifying mis-happenings in the public places. With real-time image feedback, the proposed device provides the owner with assurance even when they are not around. These studies examine the possibility of implementing automation technologies in the near future to provide complete protective control. The research suggests a fully automated security system that uses alarm messages and the internet of things (IoT) to predict and prevent unwanted activities in the jewellery shop.

Deep Learning and Geometry Flow Vector Using Estimating Vehicle Cuboid Technology in a Monovision Environment.

This study introduces a novel model for accurately estimating the cuboid of a road vehicle using a monovision sensor and road geometry information. By leveraging object detection models and core vectors, the proposed model overcomes the limitations of multi-sensor setups and provides a cost-effective solution. The model demonstrates promising results in accurately estimating cuboids by utilizing the magnitudes of core vectors and considering the average ratio of distances. This research contributes to the field of intelligent transportation by offering a practical and efficient approach to 3D bounding box estimation using monovision sensors. We validated feasibility and applicability are through real-world road images captured by CCTV cameras.

Quality Circle Approach Equipped with AI to Solve the Issue of Stray Cattle Detection and Identification in Small Cities to Avoid Accidents

The quality circle (QC) approach through its various problem identification tools has got the fame by solving several issues in Industries as well as in-service sectors. The present paper is focused on the issue of stray cattle roaming here and there and contributing to scattered trash, fatal accidents, and road blockings in various cities of India. To understand and identify the actual reasons this work is carried out and solutions have been proposed for a small town of Haryana. The quality circle was established with an aim to sort out the issue only with all the available resources like CCTV cameras, GOSHALAS, and social workers. The authors adopted a qualitative approach with a micro-level study for a small town. The quality circle approach equipped with Artificial Intelligence has been chosen to sort out the Stray cattle detection and identification issue to resolve the problem of scattered trash, fatal accidents, road blockings, and saving valuable lives of humans and animals. Keywords - Quality Circle, Artificial Intelligence, Stray Cattle detection, and recognition.

Drug-Free School Locality through Crime Prevention Strategies – The Case of Kerala

In a quest to understand crime hotspots, particularly those entangled with drug use, this study shifts its focus towards the locations themselves rather than the criminals, as recent criminology research reveals that crime incidents tend to cluster together in certain areas. Notably, drug-related crimes fall into this pattern, necessitating a robust approach to address these issues effectively. Kerala, witnessing a surge in drug-related instances involving youngsters near schools, becomes the canvas for this study. Seeking answers to the location of drug-related problems in Thiruvananthapuram's urban center, it delves into the environmental factors that amplify drug use. Spatial aspects of school localities that trigger such activities come under scrutiny, employing theories, literature studies, and case analyses to forge strategies that can transform spaces and minimize contact between peddlers and children. The Central Government School, East Fort, Kerala, and its immediate 500m vicinity emerge as the focal area for in-depth analysis. Spotlighting the transit area near the school as the epicenter of drug-related incidents, the study advocates security and surveillance enhancements in the region. Moreover, other contributing factors such as nearby beverage outlets, vacant spaces, unauthorized vendors, unmaintained dumping areas, and parking lots are identified as facilitators for illegal dealings. Proposed strategies encompass the installation of CCTV cameras, heightened police surveillance around the market area, pathway segregation, adequate transit shelters, and territorial boundaries to restrict unauthorized individuals. Worth noting, the study relies on reported cases from the State Crime Record Bureau, Vazhuthacadu, thereby not accounting for unreported incidents. To strengthen future investigations, the incorporation of analytical tools becomes a paramount consideration. By weaving together these elements, this study endeavors to craft a unique perspective on crime hotspots and drug-related concerns within Kerala's dynamic urban landscape.

De-identifying transmission system using wireless channel as differential privacy noise and deep neural networks

In order to deal with the unprecedented problem of data privacy in deep-learning based computer vision technologies, we propose a de-identifying transmission system that utilizes a wireless channel as differential privacy (DP) noise and is constructed using deep neural networks. By following the Gaussian mechanism of DP, we present that the signal received at a receiver can be considered as a Gaussian mechanism. Then, we discuss the relationship between the signal-to-noise ratio of a received signal and the privacy budget of DP, and introduce how to control transmit power to achieve a specific privacy budget. The proposed system can be divided into three parts, named transmitter, wireless channel, and receiver. The transmitter and receiver are constructed by using deep-learning networks. The transmitter consists of an image encoder network based on a neural network and a power control module that controls the transmit power for adjusting the level of de-identification. The wireless channel acts as differential privacy noise, and anonymizes the transmitted image feature vector extracted from the transmitter’s image encoder network. The receiver includes a post-processing network and an image decoder network, which are also implemented by using deep neural networks. The post-processing network is proposed for high-quality decoded face images at the receiver, which maps received feature vectors perturbed by a wireless channel back into the latent space of deep-learning based image encoder and decoder networks. Finally, extensive qualitative and quantitative evaluations confirm that the proposed system can well de-identify transmitted face images only by controlling the transmit power while maintaining the usefulness of decoded face images. The proposed system shows that the Recall@1 is smaller than 5.2 and the face detection probability is larger than 90 % at SNR=2 dB. Since the de-identification process is performed by wireless channel noise, the proposed system does not require de-identification processing at a transmitter, and thus there is no burden on the transmitter to anonymize face images. Moreover, the additional advantage of this proposed system is that the level of de-identification can be controlled only by changing the transmit power. This proposed de-identification system can be utilized in a wireless image acquisition scenario where images are captured from a wireless edge, such as a CCTV camera, and then sent to a server while protecting people’s privacy.

Factors Affecting Travel Behaviour Change towards Active Mobility: A Case Study in a Thai University

This study investigates the factors influencing travel behaviour change towards active mobility (AM) in the context of a suburban university in Thailand. The research framework involves developing a qualitative questionnaire for a SWOT analysis. The outcomes of this analysis inform the creation of a quantitative questionnaire called the Stated Preference Survey. This survey collects opinions from 400 randomly selected individuals representing various demographics in the study area. The collected data are then analysed using a binary logistic regression model to explore the relationship between independent variables (such as demographics, travel characteristics, and perceptions of infrastructure and amenities) and the likelihood of individuals adopting AM. The results indicate that the demographic variables, such as gender and income, played a significant role, with males and higher-income individuals showing lower likelihood of adopting AM. The presence of well-designed infrastructure with aesthetic features and rest areas along pedestrian and bicycle paths positively influenced behaviour change. Safety and security measures, including protective measures against motorcycles on pedestrian paths, installing CCTV cameras, and safe crossings, also played a crucial role. However, promotional efforts through media and applications did not significantly contribute to behaviour change. Policymakers and urban planners can use these insights to effectively encourage AM.

Simple device to thinking eye: Journey of CCTV cameras

Simple device to thinking eye: Journey of CCTV cameras

Electronic Device Control System through Voice Assistant with Rapid Application Development (RAD) Method

The purpose of this research was to assist each householder controling electronic devices when traveling in a quite distance. Therefore, apply microcontroller technology in the form of an electronic device control system via voice commands was necessity in other that it can cover a wide distance when it was connected to the internet. In this research, Voice command was controlled through a voice assistant on the user's cellphone. The way to implement it was by using several microcontroller components, including the NodeMCU ESP8266 and ESP32-CAM modules which function as indoor surveillance camera. whereas other supporting components, used FTDI as a USB to connect the ESP32-CAM as the power source, relays as automatic switches that could supply or cut off current electric to the electronic devices, and jumper cables as a link to components. Then, the system was tested both software and hardware used to find out whether the system was running well as expected. The workflow of the electronic device control system through this voice assistant began with the user giving voice commands through the voice assistant to control electronic devices both to turn on and off devices and to open CCTV cameras. The results of research showed that the voice assistant can properly accepted the voice commands given with a time span of 1 second for each command to turn on or turn off electronic devices. Likewise with the camera from the ESP32-CAM which functioned properly so that the browser can displayed indoor live stream video. That's why, the electronic device control system via voice assistant had been successfully designed and running properly using all the components mentioned above. So that users can controled electronic devices even though they were far from home by utilizing the existing internet connection now.

Differences in substratum preferences and behaviour within the invasive Corbicula species complex

Abstract Clams from the Corbicula species complex of Asian origin are invasive all over the world, currently extending their distribution to waters of the natural thermal regime in Central European areas. Features linking the clams to their habitats in newly invaded areas have not been fully examined. These include substratum preferences and mobility, which may be key to determining potential niche overlap with native bivalves and gaining a better knowledge of their potential active dispersal and impact. Therefore, our aim was to determine the substratum preferences, horizontal locomotion and burrowing behaviour of three Corbicula morphospecies from Poland, Central Europe: two populations of undetermined Corbicula sp. from an artificially heated habitat and water of the natural thermal regime (cold water), as well as Corbicula leana, and Corbicula fluminea (from artificially heated and cold water, respectively). To determine the preferred substratum range, we used pairwise choice tests with a range of muddy, sandy, and gravelly substrata, as well as zebra mussel shells. Then, we conducted behavioural observations (locomotion and burrowing) by CCTV cameras on substrata found as preferred and non‐preferred by clams. All morphospecies preferred fine‐grained over coarser substrata. C. fluminea from cold water had the widest range of substratum preferences. By contrast, C. leana from artificially heated water and Corbicula sp. from cold water showed the narrowest substratum preferences and spent the longest time deeply burrowed. The longest duration of burrowing activity was noted on non‐preferred coarser substrata, which may indicate difficulties in burrowing. On non‐preferred coarse substrata, C. fluminea (cold water) crawled more than the other morphospecies. Our results show that sediment preferences and behaviour (burrowing and locomotion) differ among various Corbicula morphospecies in Europe, probably also varying their invasive potential. This knowledge is important for determining the overlap of habitat preferences of non‐native Corbicula clams with native bivalves, which is critical for determining potential competition strength, impact, and/or displacement. Our results also indicate that habitats with fine sediments could be more threatened by Corbicula invasions.

The Crimes Accompanying Rapid Urbanisation Take Place in Kampala City, Uganda

Purporse :This study examined the urban policing paradox in Uganda with specific regard to how rapid urbanisation poses challenges for policing and urban peace enforcement in Kampala city. The specific objectives of this study were to explore the crimes accompanying rapid urbanisation in Kampala city; examine the role of the Uganda Police Force in urban policing and peace enforcement in Kampala city; analyse the challenges of urban policing and peace enforcement in Kampala city and finally explore the current responses by the Uganda Police Force in enhancing urban peace enforcement in Kampala city. The study employed two theories:the social contract and broken windows. Methodology : Different materials and sources were used during data collection, which included documentary reviews, key informant interviews and focus group discussions. Findings :The study found out that Kampala city remains a vulnerable place to urban insecurity primarily due to an ever increasing population, coupled with the challenges that hinder effective policing in the city. Population increase in Kampala was found out to be leading to an exponential increase in the number of slums and informal settlements which breed criminality in the city. Among the common crimes were theft, drug abuse, forgery, domestic violence, murder, cybercrimes especially fordgery and terrorism. The relationship between crime and urbanization in Kampala city included an ever increasing population, informal settlements, inadequate planning, corruption and logistical challenges within the Uganda Police Force. However, the study revealed that the Uganda Police Force has made various milestones like the CCTV Cameras, forensics capabilities , 999 communication system, in promoting peace and security in Kampala city.

CNN-Based Smart Parking System

Due to the increased number of cars, outdoor parking is one of the critical problems. Moreover, the management of the parking system is also considered a difficult task. Humans, on the other hand, were acclimated to efficiently parking their automobiles by providing them with the precise location of parking in advance of their arrival. As a result of human inefficiency, it was unsuccessful and ultimately increased the compliance cost. As a result of the development of the notion of the Internet of Things. A lot of systems were installed regarding smart parking systems that are decreasing the cost but also contain a huge impact on the reduction of emissions from cars. While it is possible to integrate Internet of Things (IoT) devices into automobiles, such an approach will necessitates the deployment of additional infrastructure, which will raise the cost, and also it is not feasible within current infrastructure configurations. Then there's the fact that CCTV technology is widely available and also small enough to fit into any parking area without being noticeable. In this paper, Convolution Neural Network (CNN) based smart parking system is designed and implemented. The CNN is used to detect vacant and occupied parking spaces through CCTV cameras and provide feedback to the passengers. Furthermore, the proposed approach is using CNR and PKLot datasets for ensuring the effectiveness of the model. This was developed to solve the issues of time, cost, and accuracy with the existing systems. As a result, the proposed model provides excellent results in terms of accuracy. Moreover, it is cost-effective and saves time.

Utilization of Stabilizer Technology in Lights for Motorcycle

The purpose of this research is to design a tool to solve a problem where motorcyclists are often distracted by other motorcyclists' lights that go directly to the face/eyes so, that it can result in disruption of visibility at night which is not uncommon to cause accidents. The usual stabilizer consists of 2 servos that are used to move objects vertically and horizontally which are used to stabilize the movement of objects or to direct objects to the desired position such as an optical stabilizer on a cellphone camera or like a CCTV camera that can adjust the direction of the camera's view, stabilizer can also be applied to LED lights or flashlights that are used to direct the lights to the desired position, so if the tool is applied to motorcycle spotlights it can prevent the lights from pointing to the faces of other riders by adjusting the position of the spotlights. The method used in this research is an experimental research method where we will test this stabilizer in several road conditions such as inclines, derivatives, turns, and so on. After that we will compare the results of applying stabilizer technology to motorcycle lights and without using a stabilizer, whether using a stabilizer will reduce the impact of spotlights that directly hit the face/eyes which can interfere with vision or not. The results show that the application of a stabilizer on a motorcycle can reduce the impact of spotlights that directly hit the face/eyes. This is because the stabilizer can adjust the tilt angle of the lamp automatically so that the lamp lighting remains facing the road. So, it can be concluded that the stabilizer on the motorcycle lights can reduce the impact of spotlights that directly hit the face/eyes resulting in impaired vision of other motorists. This research is expected to create a useful tool for motorcyclists to prevent unwanted things from happening.

Suspicious Activity Detection Using Machine Learning

Abstract: Various technologies have been utilized to implement the safety of life and property byinstalling high quality CCTV cameras. It is not possible to manually monitor each and every moment activity. Furthermore, in practical scenario the most unpredictable one is human behaviour and it is very difficult to find whether it is suspicious or normal. In this work the notion of CNN is used to detect suspicious or normal activity in an environment, and a systemis proposed that sends an alert message to the similarity authority, in case of predicting a suspicious activity. It's worth noting that the effectiveness of a suspicious activity detection system relies on the quality of the training data, the architecture of the Machine Learning model, and the deployment environment. Ongoing monitoring, regular updates, and continuousimprovement are important for maintaining the system's accuracy and adapting it to new and emerging types of suspicious activities

Acknowledgment of patient in sense behaviors using bidirectional ConvLSTM

AbstractRecognizing patient activity in real‐time from video or images collected by a CCTV camera available in the hospital during a Covid‐19 situation has proven challenging. The dilemma of patient activity recognition is identifying and recognizing a patient's various actions in a series of videos. The process presented in our paper needs to achieve unrestricted, generic behavior in videos. Detecting events in any video is often difficult because we use Bidirectional ConvLSTM to create a robust patient in the sense behaviors (PSB) framework capable of eliminating certain barriers. To begin this paper by proposing a new Bidirectional ConvLSTM for establishing a stable PSB scheme. Our proposed model is capable of accurately predicting patient's behaviors like seated, standing, and so on. Using Bidirectional ConvLSTM, learning information from a pre‐trained model is an excellent place to start for rapidly developing a new PSB system using a current PSB database, as both the source and target datasets are critical. All parameters are frozen in a pre‐trained PSB device. Then, using the UCI and HMDB51 dataset to train the model, variables and local relations are progressively fixed. A novel PSB framework is developed using the target dataset. Relevant tests are conducted using commonly used research indices to assess prediction precision accuracy. They acknowledge six patient's behavior with a weighted accuracy rate of 92%. For recognizing novel activity, laying, the precision of a corresponding prediction is the best, 91%, of all six test results. The proposed work uses bidirectional ConvLSTM with modified activation layers to sense the patients' behavior. This article may be a patient activity recognition system to identify an individual. It takes a clip of COVID‐19 patients as input and looks for matches inside the hold‐on images.

ELECTRONIC INFORMATION AS EVIDENCE

The widespread use of digital technology both in everyday life and in law enforcement raises the question of the use of digital information in evidence in criminal proceedings. However, there is still no single definition. Thus, quite often the term "digital information" is defined as information in the form of signals of any physical nature, recorded on computer media, the content and / or properties of which establish the presence or absence of circumstances to be proved in criminal proceedings. It is important to understand that such information can be created, transmitted, stored, etc. not only with the help of computer technology, but also with the use of other equipment (dictaphones, digital cameras, camcorders, smartphones, etc.).
 Analysis of the state of the issue. Digital information is objective. This is due to the fact that its fixation on digital media occurs without processing by human consciousness - in the form in which it objectively existed, regardless of the perception of the person who fixes it. Most often, this information is created outside the framework of criminal proceedings not to bring it to the attention of the pre-trial investigation or court, but for a completely different purpose. For example, CCTV cameras can be installed for security purposes or to prevent and combat crime. Making a video eliminates the participation of the human factor, because the recording of the event is automatic. As a result, the information obtained in this way is objective.
 The current CPC does not contain the concept of "electronic evidence", but the analysis of other procedural codes (including CAS, CPC and CPC) allows us to establish that this concept means information in electronic (digital) form that contains information about the circumstances relevant to the case , in particular, electronic documents (text documents, graphics, plans, photographs, video and audio recordings, etc.), websites (pages), text, multimedia and voice messages, metadata, databases and other data in electronic form.