CCTV Research Articles

SIMILARITY CHECKING OF CCTV IMAGES USING PEARSON CORRELATION: IMPLEMENTATION WITH PYTHON

Video surveillance technology, such as CCTV, is increasingly common in various applications, including public safety and business surveillance. Analyzing and comparing images from CCTV systems is essential for ensuring safety and security. This research implements the Pearson Correlation method in Python to measure the similarity of CCTV images. Pearson Correlation, which assesses the linear relationship between two variables, is employed to compare the pixel values of two images, resulting in a coefficient that indicates the degree of similarity. We used a quantitative approach with experiments on two scenarios to test the program's effectiveness in measuring image similarity. The results demonstrate that Pearson Correlation is highly effective in distinguishing between identical and other images, providing a more accurate and comprehensive assessment of image similarity compared to histogram analysis. However, the findings are constrained by the specific scenarios and dataset utilized. Further research with more diverse empirical data is required to generalize these results across a broader range of CCTV conditions.

Accelerated Data Engine: A faster dataset construction workflow for computer vision applications in commercial livestock farms

Large-scale, high-quality dataset was the foundation of developing advanced artificial intelligence applications. However, creating such a benchmark dataset in a professional field, such as precision management of animals, was always a challenge because of the costly and labor-intensive process of annotation and review. This study introduced a novel workflow named Accelerated Data Engine (ADE), designed to efficiently produce representative and high-quality computer vision datasets from raw animal surveillance footage. By incorporating referring and grounding models (R&G models) as auto-annotators, along with a distillation mechanism for dataset-auditors, ADE significantly speeded up the dataset construction process. The new workflow received natural language inputs as referrals to identify animal instances, delineated their body shapes, and then refined the auto-annotated data through a selection process. To demonstrate the efficacy of ADE, three 30-minute surveillance video samples featuring pigs, sheep, and cattle were discussed in this study. The results indicated the R&G models effectively annotated animals across various farms, while distillation mechanisms could identify various detection errors, balance the data representations, refine annotations, and verify the data quality. Two high-quality cattle datasets (6.5 k and 486 frames), including 26 k and 2.5 k cattle instances, were generated through the ADE workflow from 24-hour surveillance videos on a commercial cattle farm and made publicly available. The proposed dataset has achievable performance between 74.6 %∼84.1 %. The ADE workflow saved 78.4 % of manual work compared to the traditional dataset construction workflow (approximately 141 h). This pioneering approach empowered the fast creation of benchmark animal datasets and would enhance computer vision applications in the livestock production industry in the future.

Efficient Deep Learning Methods for Detecting Road Accidents by Analyzing Traffic Accident Images

Speed is one of the major factors in car crashes. Many lives could have been saved if emergency services had been alerted to the disaster and arrived in time. For the sake of protecting valuable human lives, an effective automatic accident detection system with prompt reporting of the accident scene to emergency services is essential. Therefore, this research proposes some effective Deep Learning techniques that properly recognize the incidence of accidents. The paper introduces two different techniques for image classification, with a particular focus on distinguishing between accident and non-accident images. The dataset used for the proposed model is taken from Kaggle, which is a collection of CCTV images. The first approach is a hybridized TL-ML method that employs transfer learning techniques that use different pre-trained versions of convolutional neural networks to extract features from image datasets. These extracted features are then fed into various machine learning classifiers to categorize the images as either Accident or Non-accident. To make the final decision, a voting classifier is utilized to choose the best classification outcome from the set of previously employed machine learning classifiers. In the second method, a modified Convolutional Neural Network (CNN) called SpinalNet is adopted. The performance of these models was evaluated by comparing them with each other and with a customized CNN base model. SpinalNet consistently surpassed the other models in terms of Precision, Recall, F1-Score, and Accuracy, demonstrating its outstanding capabilities.

Comparative Analysis of Deep Learning Algorithms in Fire Detection

As technology advances rapidly, deep learning applications, a subset of machine learning, are becoming increasingly relevant in various aspects of our lives. Essential daily applications like license plate recognition and optical character recognition are now commonplace. Alongside current technological progress, the development of future-integrated technologies such as suspicious situation detection from security cameras and autonomous vehicles is also accelerating. The success and accuracy of these technologies have reached impressive levels. This study focuses on the early and accurate detection of forest fires before they cause severe damage. Using primarily forest fire images from datasets obtained from Kaggle, various deep learning algorithms were trained via transfer learning using MATLAB. This approach allowed for comparing different deep learning algorithms based on their efficiency and accuracy in detecting forest fires. High success rates, generally exceeding 90%, were achieved.

VIOLENCE PREDICTION IN SURVEILLANCE VIDEOS

Forecasting violence has become a critical obstacle in the field of video monitoring to guarantee public safety. Lately, YOLO (You Only Look Once) has become a popular and effective method for detecting weapons. However, identifying and forecasting violence remains a challenging endeavor. Additionally, the classification results had to be enhanced with semantic information. This study suggests a method for forecasting violent incidents by utilizing Yolov9 and ontology. The authors employed Yolov9 to identify and categorize weapons and individuals carrying them. Ontology is utilized for semantic prediction to assist in predicting violence. Semantic prediction happens through the application of a SPARQL query to the identified frame label. The authors developed a Threat Events Ontology (TEO) to gain semantic significance. The system was tested with a fresh dataset obtained from a variety of security cameras and websites. The VP Dataset comprises 8739 images categorized into 9 classes. The authors examined the outcomes of using Yolov9 in conjunction with ontology in comparison to using Yolov9 alone. The findings show that by combining Yolov9 with ontology, the violence prediction system's semantics and dependability are enhanced. The suggested system achieved a mean Average Precision (mAP) of 83.7 %, 88% for precision, and 76.4% for recall. However, the mAP of Yolov9 without TEO ontology achieved a score of 80.4%. It suggests that this method has a lot of potential for enhancing public safety. The authors finished all training and testing processes on Google Colab's GPU. That reduced the average duration by approximately 90.9%. The result of this work is a next level of object detectors that utilize ontology to improve the semantic significance for real-time end-to-end object detection.

Estimating Rainfall Intensity Using an Image-Based Convolutional Neural Network Inversion Technique for Potential Crowdsourcing Applications in Urban Areas

High-quality rainfall data are essential in many water management problems, including stormwater management, water resources management, and more. Due to the high spatial–temporal variations, rainfall measurement could be challenging and costly, especially in urban areas. This could be even more challenging in tropical regions with their typical short-duration and high-intensity rainfall events, as some of the undeveloped or developing countries in those regions lack a dense rain gauge network and have limited resources to use radar and satellite readings. Thus, exploring alternative rainfall estimation methods could be helpful to back up some shortcomings. Recently, a few studies have examined the utilisation of citizen science methods to collect rainfall data as a complement to the existing rain gauge networks. However, these attempts are in the early stages, and limited works have been published on improving the quality of such data. Therefore, this study focuses on image-based rainfall estimation with potential usage in citizen science. For this, a novel convolutional neural network (CNN) model is developed to predict rainfall intensity by processing the images captured by citizens (e.g., by smartphones or security cameras) in an urban area. The developed model is merely a complementary sensing tool (e.g., better spatial coverage) to the existing rain gauge network in an urban area and is not meant to replace it. This study also presents one of the most extensive datasets of rain image data ever published in the literature. The estimated rainfall data by the proposed CNN model of this study using images captured by surveillance cameras and smartphone cameras are compared with observed rainfall by a weather station and exhibit strong R2 values of 0.955 and 0.840, respectively.

Private Cctv Liability Under Biometric Data Protection Rules

The penetration of technology that is increasingly developing has a lot of impact on human life. Increasing technology also results in the rapid development of home security equipment, especially Closed-Circuit Television cameras (hereinafter mentioned as CCTV). The right to privacy, to which everyone is entitled to personal self- protection Doctrinal legal research is a crucial aspect in recognizing various societal problems. Doctrinal research combines a systematic analysis of the provisions of legislation and the legal principles contained in it or derived from it, but also the logical and rational order of legal propositions and principles. Doctrinal legal research methods involve the analysis of legal propositions or legal concepts on which the main study is based. Case base approach demands the researcher to understand the reasons that used by the judges or another adjudicator until it reaches the final decision. Most personal data protection laws around the world distinguish between regular personal data and biometric data. At the beginning, Article 4 paragraph (1) of EU GDPR regular personal data commonly define on the laws as a set of data that able to identify a natural person either from electronic or non-electronic devices. Under the data protection laws regime especially GDPR, UK Data Protection Law and Indonesia Data Protection Law, mitigation during a data protection failure involving household CCTV systems typically involves taking immediate steps to minimize the impact of the breach Furthermore, stated in the Fairhurst v Woodard case homeowner could be held liable for failure to protect the personal data if they use camera on the outside boundary of their house and they could face hefty fine and/or tools removal. Finally, this writing contributes to undergoing discourse on cyber law field especially in data protection law and provide insights for academician, practitioner, and society.

The use of convolutional neural networks for abnormal behavior recognition in crowd scenes

This study introduces the Abnormality Converging Scene Analysis Method (ACSAM) to detect abnormal group behavior using monitored videos or CCTV images in crowded scenarios. Abnormal behavior recognition involves classifying activities and gestures in continuous scenes, which traditionally presents significant computational challenges, particularly in complex crowd scenes, leading to reduced recognition accuracy. To address these issues, ACSAM employs a convolutional neural network (CNN) enhanced with Abnormality and Crowd Behavior Training layers to accurately detect and classify abnormal activities, regardless of crowd density. The method involves extracting frames from the input scene and using CNN to perform conditional validation of abnormality factors, comparing current values with previous high values to maximize detection accuracy. As the abnormality factor increases, the identification rate improves with higher training iterations. The system was tested on 26 video samples and trained on 34 samples, demonstrating superior performance to other approaches like DeepROD, MSI-CNN, and PT-2DCNN. Specifically, ACSAM achieved a 12.55% improvement in accuracy, a 12.97% increase in recall, and a 10.23% enhancement in convergence rate. These results suggest that ACSAM effectively overcomes the computational challenges inherent in crowd scene detection, offering a robust solution for real-time abnormal behavior recognition in crowded environments.

Learning 3D human–object interaction graphs from transferable context knowledge for construction monitoring

We propose a novel framework for detecting 3D human–object interactions (HOI) in construction sites and a toolkit for generating construction-related human–object interaction graphs. Computer vision methods have been adopted for construction site safety surveillance in recent years. The current computer vision methods rely on videos and images, with which safety verification is performed on common-sense knowledge, without considering 3D spatial relationships among the detected instances. We propose a new method to incorporate spatial understanding by directly inferring the interactions from 3D point cloud data. The proposed model is trained on a 3D construction site dataset generated from our crafted simulation toolkit. The model achieves 54.11% mean interaction over union (mIOU) and 72.98% average mean precision(mAP) for the worker–object interaction relationship recognition. The model is also validated on PiGraphs, a benchmarking dataset with 3D human–object interaction types, and compared against other existing 3D interaction detection frameworks. It was observed that it achieves superior performance from the state-of-the-art model, increasing the interaction detection mAP by 17.01%. Besides the 3D interaction model, we also simulate interactions from industrial surveillance footage using MoCap and physical constraints, which will be released to foster future studies in the domain.

METHOD OF MONITORING TRAFFIC FLOWS USING THE BRIEFCAM SYSTEM

Urban logistics forms the backbone of modern cities, ensuring the efficient movement of goods and services. With growing urbanisation and traffic congestion, optimising traffic flows has become crucial. The study monitors traffic flows using BriefCam software to enhance sustainable urban logistics. Cost-effective surveillance systems like CCTV generate vast data, opening new opportunities for improving traffic flow monitoring. Traditional methods, while reliable, are limited by labour intensity, cost, and accuracy. BriefCam software optimises vehicle monitoring through structured methodologies, including collection of data, filter application, result validation, and data generation. Utilising this data provides insights to improve traffic management, urban transport speed, and sustainable logistics practices. Modern cities use affordable CCTV systems, operating 24/7 and accumulating vast data suitable for automated traffic monitoring. Traditional methods require significant labour and costs, whereas floating car data (FCD) offers real-time traffic data collection, despite some reliability issues. BriefCam provides an innovative approach with a structured methodology for monitoring vehicles, aiding in sustainable urban logistics by optimising traffic flows and improving urban transport speed. The article provides a detailed look at the methods used in the study, the process of using BriefCam to monitor vehicles, the filters applied for detailed analysis, techniques for verifying the results, and general conclusions drawn from the study. Efficient traffic management based on this analysis can lead to additional measures during peak hours, optimising traffic lights, and increasing lanes. Knowing the time frames when freight vehicle numbers rise helps businesses plan deliveries to avoid peak congestion, enhancing logistics efficiency. BriefCam software offers immediate insights for reducing congestion, enhancing safety, and improving urban quality of life. Integrating digital approaches with traditional methods provides a comprehensive view of traffic dynamics, which aids urban planners and policymakers in optimising strategies, reducing emissions, and creating better living conditions in cities. Keywords: traffic monitoring, urban traffic management, intelligent transport systems, freight traffic flow.

A new approach to video summary generation

This paper describes a video summary approach for an actual video file that provides a rapid way to assess its information. This is a difficult task to identify relevant or informative sections. When the original video demands knowledge of its content, we build a video summary via extracting in-depth characteristics of each original video. Video summarization deals with the generation of a condensed version of the original video by including meaningful frames or segments while eliminating redundant information provides a concise and accurate representation of the original video clips by providing the most representative summary with increased interest through the application of a matching function between the current and prior frames. The primary goal of this work is to give a strategy for recording video clips using security cameras and converting them into a short video to provide a clear analysis of the video by reducing excess and extracting the key video contents into the real video. In a lengthy video clip, viewers may not have enough time to see the full thing. The viewer may be interested in seeing a specific topic under the label "Important". It may be composed of pieces that may be shared on social media and communicate the semantics of long videos, particularly video snippets that must be submitted to Internet. To browse, will be needed a network with adequate bandwidth. That is, non-affiliated video streaming, indexing, and retrieval of video content makes it valuable to viewers.

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

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

Impact of vandalism on avian nest-box studies: challenges and strategies for research and conservation

Human interaction with nature often exhibits negative aspects, such as vandalism, which involves the destruction of or damage to property. Unfortunately, very little is known about the extent, causes, and frequency of this phenomenon. Therefore, in this paper, we investigate a scale of vandalism in studies using nest-boxes in Poland. Data from published papers (n = 256) indicated that researchers are aware of the devastation and destruction of nest-boxes, but often lacking detailed reports. We further validated this data through emails or phone calls to the authors. Surprisingly, only 14 (5.5%) papers mentioned vandalism, and during interviews, we found that vandalism occurred in 51.7% of studies. In response to vandalism, researchers have taken measures to reduce the scale of damages, such as hanging boxes far from paths and roads, placing them above 3 m from the ground, or, more recently, using security cameras. Although vandalism was quite common, its scale was rather marginal, with some local exceptions. For a better understanding of this phenomenon, we suggest including more detailed information on vandalism in future papers, which could aid in the interpretation of scientific data, as well as in nature conservation.

Data safety prediction using YOLOv7+G3HN for traffic roads

Pulau Pinang has introduced several measures to enhance traffic safety and promote sustainability, including the installation of CCTV systems and the implementation of smart solutions and green technology as part of the Penang 2030 vision, aligning with the Sustainable Development Goals (SDGs). However, despite these efforts, road accidents persist due to non-optimised detection models, incomplete data from manual reporting, and technological constraints in real-time video analysis and predictive modelling. This study evaluates the effectiveness of the YOLOv7+G3HN framework for vehicle detection and near-miss analysis, with a focus on the influence of video quality on detection performance. The research aims to understand how high- and low-quality video inputs affect the accuracy and computational efficiency of detection algorithms. High[1]quality videos resulted in significantly faster computation times for vehicle detection than low-quality videos, highlighting the importance of video resolution in optimising detection processes. Despite the robustness of the algorithm, with no errors detected in both video qualities, higher miss detection rates in low-quality videos suggest that lower resolution may compromise detection accuracy and the effectiveness of monitoring systems. Near-miss analysis revealed that high-quality videos had a lower probability of near-miss occurrences than low-quality videos, highlighting the importance of video resolution for detection efficacy. These findings emphasise the critical role of high-resolution video inputs in enhancing detection accuracy and reliability, advocating for their implementation to optimise vehicle detection and improve road safety. Additionally, YOLOv7+G3HN outperforms YOLOv7 in both accuracy and speed. The study concludes that the YOLOv7+G3HN framework is effective for vehicle detection and near-miss analysis, provided that video quality is considered in system design and implementation.

Improving the evidential value of low-quality face images with aggregation of deep neural network embeddings

In forensic facial comparison, questioned-source images are usually captured in uncontrolled environments, with non-uniform lighting, and from non-cooperative subjects. The poor quality of such material usually compromises their value as evidence in legal proceedings. On the other hand, in forensic casework, multiple images of the person of interest are usually available. In this paper, we propose to aggregate deep neural network embeddings from various images of the same person to improve the performance in forensic comparison of facial images. We observe significant performance improvements, especially for low-quality images. Further improvements are obtained by aggregating embeddings of more images and by applying quality-weighted aggregation. We demonstrate the benefits of this approach in forensic evaluation settings with the development and validation of common-source likelihood ratio systems and report improvements in Cllr both for CCTV images and for social media images.

Electromagnetic Compatibility Issues in 400-MHz-Band Wireless Medical Telemetry Systems and Their Management Using Simplified Methods for Safe Operation.

Wireless medical telemetry systems (WMTSs) are typical radio communication-based medical devices that monitor various biological parameters, such as electrocardiograms and respiration rates. In Japan, the assigned frequency band for WMTSs is 400 MHz. However, the issues accounting for poor reception in WMTS constitute major concerns. In this study, we analyzed the effects of electromagnetic interferences (EMIs) caused by other radio communication systems, the intermodulation (IM) effect, and noises generated from electrical devices on WMTS and discussed their management. The 400-MHz frequency band is also shared by other radio communication systems. We showed the instantaneous and impulsive voltages generated from the location-detection system for wandering patients and their potential to exhibit EMI effects on WMTS. Further, we presented the IM effect significantly reduces reception in WMTS. Additionally, the electromagnetic noises generated from electrical devices, such as light-emitting diode lamps and security cameras, can exceed the 400 MHz frequency band as these devices employ the switched-mode power supply and/or central processing unit and radiate wideband emissions. Moreover, we proposed and evaluated simple and facile methods using a simplified spectrum analysis function installed in the WMTS receiver and software-defined radio for evaluating the electromagnetic environment.

Assessing opportunities for enhanced lighting energy conservation via occupancy and daylight monitoring

Efficient energy utilization in buildings is crucial for sustainability. This work proposes an intelligent system that leverages computer vision techniques and CCTV images to assess indoor lighting energy usage based on occupancy, artificial lighting, and daylight conditions. Object detection models - You Only Look Once (YOLO) version 3 (v3) and v8 are employed to detect people, lights, and windows, achieving promising accuracies of 94.9 ​%, 73.3 ​%, and 98.7 ​%, respectively. The system categorizes scenarios as energy-efficient, wasteful, or neutral by integrating these outputs, highlighting opportunities for improving efficiency by harmonizing lighting infrastructure with occupancy and daylight exposure. Performance analyses, including training and validation metrics, are presented. This study demonstrates the potential of computer vision and AI for optimizing energy utilization, enabling sustainable building operation and promoting energy-positive occupant behaviors through sensor-driven methodologies.

INTERNAL CONTROL ON MILITARY ASSETS ACCORDING TO MILK AL-DAULAH IN ISLAMIC ECONOMIC LAW

This article aims to examine the internal control system of national military assets in Indonesia at the Kuta Alam Banda Aceh barracks, reviewed according to the concept of milk al-daulah. The approach taken by the author is a juridical-empirical study. The research findings indicate that to address issues in the internal control system of assets in the Indonesian National Army (TNI) at the Kuta Alam Banda Aceh barracks, a holistic approach is required to effectively tackle existing challenges. It is crucial to update and refine the inventory process to ensure that asset data is more accurate and current. Implementing an integrated, technology-based asset management system will facilitate tracking and monitoring. Furthermore, asset maintenance should be scheduled regularly and its implementation should be ensured to prevent damage that could increase repair costs. Enhancements in surveillance technology, such as modern CCTV and access control systems, are essential to reduce the risk of theft and damage. Compliance with policies should be strengthened through intensive training and consistent enforcement to ensure procedures are properly followed. Risk management also needs improvement with more effective and proactive mitigation strategies. Additionally, the use of advanced technology can support efficiency in asset management and reporting. Transparency should be increased by providing clear and accessible reporting mechanisms, while budget management should be improved to ensure efficient allocation. Regular personnel training is important to keep their skills relevant, and routine audits and evaluations should be conducted to maintain the effectiveness of the internal control system.

Sensing Human Emotion using Emerging Machine Learning Techniques

Human emotion recognition using machine learning is a new field that has the potential to improve user experience, lower crime, and target advertising. The ability of today's emotion detection systems to identify human emotions is essential. Applications ranging from security cameras to emotion detection are readily accessible. Machine learning-based emotion detection recognises and deciphers human emotions from text and visual data. In this study, we use convolutional neural networks and natural language processing approaches to create and assess models for emotion detection. Instead of speaking clearly, these human face expressions visually communicate a lot of information. Recognising facial expressions is important for human-machine interaction. Applications for automatic facial expression recognition systems are numerous and include, but are not limited to, comprehending human conduct, identifying mental health issues, and creating artificial human emotions. It is still difficult for computers to recognise facial expressions with a high recognition rate. Geometry and appearance-based methods are two widely used approaches for automatic FER systems in the literature. Pre-processing, face detection, feature extraction, and expression classification are the four steps that typically make up facial expression recognition. The goal of this research is to recognise the seven main human emotions anger, disgust, fear, happiness, sadness, surprise, and neutrality using a variety of deep learning techniques (convolutional neural networks).

Good news urban tourism researchers! 19 ways to enhance the usefulness of your observational video analysis research

PurposeThe present article encourages urban tourism researchers use pre-recorded (like YouTube, TikTok and security camera footage) and self-recorded video data in research. The author highlighted the benefits of doing so for urban tourism scholars, as well as ways in which these investigators can use the observational video analysis technique to produce convincing findings and advance their field.Design/methodology/approachTo accomplish the purpose, the author reviewed 25 scholarly articles on the topic from several fields.FindingsOne benefit of observational video analysis research (OVAR), the author highlighted, was the ability of scholars in different locations to simultaneously observe interactions, the focus of the study, in their natural setting and discuss them. This practice is not possible with traditional ethnographic research. Also, one way the author mentioned researchers can accomplish rigor in their OVAR project is through multimodal transcription. With multimodal transcription, verbal and non-verbal happenings in videos are transliterated and later analyzed.Research limitations/implicationsIt is hoped because of the present article, increased use of the technique in urban tourism research will be seen.Originality/valueThe present article is the first, to the best of the author’s knowledge, to detail how rigor can be accomplished in OVAR in urban tourism.