Closed-circuit Television Video Research Articles

Identification of factors affecting fattening efficiency of commercial pig herds and analysis of their impact at different performance levels

Improving fattening efficiency is an important goal of breeding commercial pigs, especially for the large-scale pig farms. Fattening efficiency index (FEI) can be used to evaluate the fattening efficiency. The aim of this study was to identify the factors affecting the fattening efficiency of commercial pigs in large-scale pig farms and further study the impact of these factors on the production performance of commercial pig batches at different production levels. The data of 9,570 batches was mainly consisted of four parts (farm facilities, general information of piglets, production performance of nursery pigs and finishing pigs). A total of 28 variables were evaluated by the multi-variable linear regression models. The differences in production factors significantly correlated with FEI at piglets-finishing stage were compared among high-performing (HP), moderate-performing (MP), and low-performing (LP) batches of commercial pigs during the nursery and finishing stage. Among the 28 variables, 18 were significantly correlated with fattening efficiency (P < 0.05), including 11 continuous variables and seven discrete variables. The significant differences among the 11 consecutive variables in the HP, MP, and LP batches of commercial pigs mostly persisted from the piglets-nursery stage to the growing-finishing stage, ultimately affecting the FEI at piglets-finishing stage. For the seven significant discrete variables, the HP batches had a lower proportions in owned source of piglets, number of the purchasing piglets in spring and winter, number of batches in the East and North regions and five-way crossbred pigs, while a higher proportions in the use of closed circuit television video (CCTV) and wastes treatment system. The fattening efficiency of commercial pigs in large-scale pig farms was comprehensively affected by farm facilities, piglets, and production performance at nursery and finishing stage. The low fattening efficiency may have started at the end of nursery stage.

Efficient Method of Road Outlier Recognition Using Deep Learning Coupled with Data Augmentation Approach

In recent years, Closed-circuit Television (CCTV) cameras have been playing a vital role in the surveillance of both public and private areas. The primary objective of surveillance is to monitor human behavior and road conditions. In the real-world situation, detecting, and recognizing abnormal activities poses significant challenges due to the densely crowded environment and the complex nature of transportation systems. These factors make it difficult to automatically identify various anomalies that occur while traveling, leading to emergencies, and endangering human life and property. In response to these challenges, contemporary Road Outlier Recognition Surveillance Systems (RORSS) have been deployed to monitor and mitigate abnormalities on streets, highways, and roads. This research specifically investigated conventional as well as human-centered road anomalies encompassing snatching, accidents, fighting, and car fires. The proposed Real-time Road Outlier Recognition methodology is formulated as a classification task, involving the analysis and processing of real-time CCTV videos. The proposed study investigated different types of Convolutional Neural Network (CNN) pre-trained models with the Data Augmentation (DA) approach to address the frame variance problem in real-time videos. Furthermore, we introduced a benchmark real-world Road Outlier Dataset (ROD) containing roads, streets, and highways videos and images that presented different road anomalies performed by vehicles and humans. Experimentation using different pre-trained CNN models i.e., VGG19, InceptionV3, ResNet50, and DenseNet201 with a data augmentation approach has been performed on the ROD dataset. The experimental results demonstrated that the InceptionV3 model performed best with the augmentation approach as compared to other deep learning models that achieved the best accuracy of 98.80% in recognizing road anomalies

A Novel Approach for Surveillance Compression using Neural Network Technique

The integration of closed-circuit television (CCTV) monitoring is crucial in the field of video processing, which provides an efficient method for comprehensive surveillance. However, a key challenge associated with this practice is its substantial demand for storage space. Typically, surveillance footage is stored in hard disk drives, and due to limited storage spaces, it is deleted after some time. To address this issue, an innovative method for compressing CCTV video, named object detection-based surveillance compression (ODSC), is introduced. Our ODSC model is divided into two steps: -i) depending upon the objects in the video, determine the significant and non-significant frames of surveillance video using the neural network approach YOLOv5s &amp; YOLOv7-tiny and Yolov8s ii) construct the video of significant frames. Following a comprehensive analysis of the experimental outcomes, it is noted that YOLOv8s stands out with a remarkable detection accuracy of 99.7% on the COCO dataset. Our ODSC approach is reducing the storage space greatly and achieving an average compression ratio of up to 96.31% using YOLOv8s, which surpasses the existing state-of-the-art methods.

Analysis and comparison of various deep learning models to implement suspicious activity recognition in CCTV surveillance

The paper aims to analyze and compare various deep learning (DL) algorithms in order to develop a Suspicious Activity Recognition (SAR) system for closed-circuit television (CCTV) surveillance. Automated systems for detecting and classifying suspicious activities are crucial as technology’s role in safety and security expands. This paper addresses these challenges by creating a robust SAR system using machine learning techniques. It analyzes and compares evaluation metrics such as Precision, Recall, F1 Score, and Accuracy using various deep learning methods (convolutional neural network (CNN), Long short-term memory (LSTM) – Visual Geometry Group 16 (VGG16), LSTM – ResNet50, LSTM – EfficientNetB0, LSTM – InceptionNetV3, LSTM – DenseNet121, and Long-term Recurrent Convolutional Network (LRCN)). The proposed system improves threat identification, vandalism deterrence, fight prevention, and video surveillance. It aids emergency response by accurately classifying suspicious activities from CCTV footage, reducing reliance on human security personnel and addressing limitations in manual monitoring. The objectives of the paper include analyzing existing works, extracting features from CCTV videos, training robust deep learning models, evaluating algorithms, and improving accuracy. The conclusion highlights the superior performance of the LSTM-DenseNet121 algorithm, achieving an overall accuracy of 91.17% in detecting suspicious activities. This enhances security monitoring capabilities and reduces response time. Limitations of the system include subjectivity, contextual understanding, occlusion, false alarms, and privacy concerns. Future improvements involve real-time object tracking, collaboration with law enforcement agencies, and performance optimization. Ongoing research is necessary to overcome limitations and enhance the effectiveness of CCTV surveillance.

Deep Learning-Based Video Compression for Surveillance Footage

The utilization of closed-circuit television (CCTV) monitoring plays a pivotal role in the realm of video processing, providing an effective means for vigilant surveillance. However, a significant challenge associated with this practice is the substantial demand it places on storage space. Traditionally, surveillance footage is stored on hard disk drives, and due to limited storage capacities, it often necessitates periodic deletion. To tackle this issue, we have introduced an innovative method for compressing CCTV video, named “Detection-Based video Compression” (DBVC). Our DBVC model is a two-step process. In the first step, we employ advanced neural network approaches such as Mask-RCNN and YOLOv4 to determine active and idle frames within the surveillance video. These cutting-edge techniques enable precise identification of objects and events of interest in the video feed. In the second step, we construct a new video composed solely of the active frames, eliminating redundant or uneventful segments. After conducting a comprehensive analysis of the experimental results, it is evident that Mask-RCNN stands out with an impressive detection accuracy of 98% on the COCO dataset, making it a robust choice for identifying objects and events in the surveillance footage. Consequently, we chose to leverage the output generated by Mask-RCNN and YOLOv4 for subsequent processing stages. Our DBVC approach is a breakthrough in video compression technology, significantly reducing the storage space required for CCTV footage. In fact, it achieves an average compression ratio of up to 85% when using YOLOv4, surpassing the capabilities of existing state-of-the-art compression methods. This innovation not only optimizes storage efficiency but also maintains a high level of surveillance data integrity, making it a valuable advancement in the field of CCTV video processing and storage management.

Early fire detection technique for human being using deep learning algorithm

Fire and smoke detection in today’s world is a must, especially in clustered areas where a quick response can prevent significant damages and save lives. Early detection plays a significant role in preventing the fire from spreading by alerting the emergency response personnel. It may not be possible to install traditional fire and smoke detectors everywhere. As a result, incorporating fire and smoke detection into existing closed circuit television (CCTV) systems in various places can provide a warning to the appropriate authorities, allowing for quick action to prevent the fire from spreading. This work aims in developing an early fire and smoke prediction model with CCTV footage images and video frames. The images and videos are collected from multiple datasets available online. A convolutional neural network (CNN) model is developed for early detection and prevention of the spreading of fire and compares it with transfer learning models ResNet50 and VGG19. The model obtain an accuracy of around 94% using CNN model, 95% using VGG19 and 98% using ResNet 50. A model with high accuracy can replace traditional fire detection systems which can be both cost-effective and easy to implement to existing surveillance cameras.

Users' Information Security Awareness of Home Closed-Circuit Television Surveillance

Closed-circuit television (CCTV) surveillance cameras are widely used in public and private areas around the world. It is primarily used for tracking individuals and preventing criminal activities. It is necessary to balance the benefits of video surveillance and the risks it poses to individuals' right to privacy. The existing studies raised privacy issues of installing CCTV in public places. However, there is a lack of studies investigating users’ awareness of information security and privacy limitations in installing CCTV in private places. Thus, in this study, the author evaluated users' information security awareness of the value of CCTV and other forms of video surveillance. In-person interviews were conducted in Riyadh province, Kingdom of Saudi Arabia. A total of 77 individuals responded to the interview. A qualitative analysis was conducted to evaluate the participants’ perception of CCTV usage. The outcome of the analysis revealed four themes: Privacy invasion, privacy awareness, dilemmas in implementing security, and preventive measures. The findings revealed that the participants required strict privacy policies for installing CCTV video monitoring systems in private areas. In addition, they understood that CCTV is effectively reducing the fear of crime. The research contributes to understanding users' general awareness of information security and offers the necessary steps to protect the user's privacy in a CCTV surveillance environment. In addition, a data-sharing framework is recommended to share the data in a secure environment. Furthermore, researchers can utilize the study findings in conducting further similar investigative studies.

A Digital Twin Dam and Watershed Management Platform

This paper presents an innovative digital twin dam and watershed management platform, K-Twin SJ, that utilizes real-time data and simulation models to support decision-making for flood response and water resource management. The platform includes a GIS-based geospatial digital twin of the entire Sumjin dam and river water system in Korea, with high-precision geospatial topography and facility information for dams and rivers (watershed area 4913 km2, river length 173 km, and 91 water infrastructures). The platform synchronizes real-time data such as rainfall, dam and river water levels, flow rate, and closed-circuit television (CCTV), and incorporates three hydraulic and hydrological simulation models for efficient dam operation considering the river conditions. AI technology is also used to predict the river water level and suggest optimal dam discharge scenarios. Additionally, the platform includes a geotechnical safety evaluation module for river levees, advanced drone monitoring for dams and rivers, and an AI CCTV video surveillance function. The digital-twin-based platform supports efficient decision-making for smart flood responses and contributes to reducing flooding damage and optimal operation through better smart water management.

Fusion of CCTV Video and Spatial Information for Automated Crowd Congestion Monitoring in Public Urban Spaces

Crowd congestion is one of the main causes of modern public safety issues such as stampedes. Conventional crowd congestion monitoring using closed-circuit television (CCTV) video surveillance relies on manual observation, which is tedious and often error-prone in public urban spaces where crowds are dense, and occlusions are prominent. With the aim of managing crowded spaces safely, this study proposes a framework that combines spatial and temporal information to automatically map the trajectories of individual occupants, as well as to assist in real-time congestion monitoring and prediction. Through exploiting both features from CCTV footage and spatial information of the public space, the framework fuses raw CCTV video and floor plan information to create visual aids for crowd monitoring, as well as a sequence of crowd mobility graphs (CMGraphs) to store spatiotemporal features. This framework uses deep learning-based computer vision models, geometric transformations, and Kalman filter-based tracking algorithms to automate the retrieval of crowd congestion data, specifically the spatiotemporal distribution of individuals and the overall crowd flow. The resulting collective crowd movement data is then stored in the CMGraphs, which are designed to facilitate congestion forecasting at key exit/entry regions. We demonstrate our framework on two video data, one public from a train station dataset and the other recorded at a stadium following a crowded football game. Using both qualitative and quantitative insights from the experiments, we demonstrate that the suggested framework can be useful to help assist urban planners and infrastructure operators with the management of congestion hazards.

Building Occupancy Detection and Localization Using CCTV Camera and Deep Learning

Occupancy information plays a key role in analyzing and improving building energy performance. The advances of Internet of Things (IoT) technologies have engendered a shift in measuring building occupancy with IoT sensors, in which cameras in closed-circuit television (CCTV) systems can provide richer measurements. However, existing camera-based occupancy detection approaches cannot function well when scanning videos with a number of occupants and determining occupants’ locations. This article aims to develop a novel deep-learning-based approach for better building occupancy detection based on CCTV cameras. To do so, this research proposes a deep-learning model to detect the number of occupants and determine their locations in videos. This model consists of two main modules, namely, feature extraction and three-stage occupancy detection. The first module presents a deep convolutional neural network to perform residual and multibranch convolutional calculation to extract shallow and semantic features, and constructs feature pyramids through a bidirectional feature network. The second module performs a three-stage detection procedure with three sequential and homogeneous detectors which have increasing Intersection over Union (IoU) thresholds. Empirical experiments evaluate the detection performance of the approach with CCTV videos from a university building. Experimental results show that the approach achieves the superior detection performance when compared with baseline models.

An Autonomous Framework for Real-Time Wrong-Way Driving Vehicle Detection from Closed-Circuit Televisions

Around 1.3 million people worldwide die each year because of road traffic crashes. There are many reasons which cause accidents, and driving in the wrong direction is one of them. In our research, we developed an autonomous framework called WrongWay-LVDC that detects wrong-way driving vehicles from closed-circuit television (CCTV) videos. The proposed WrongWay-LVDC provides several helpful features such as lane detection, correct direction validation, detecting wrong-way driving vehicles, and image capturing features. In this work, we proposed three main contributions: first, the improved algorithm for road lane boundary detection on CCTV (called improved RLB-CCTV) using the image processing technique. Second is the Distance-Based Direction Detection (DBDD) algorithm that uses the deep learning method, where the system validates and detects wrong-driving vehicles. Lastly, the Inside Boundary Image (IBI) capturing feature algorithm captures the most precise shot of the wrong-way-of-driving vehicles. As a result, the framework can run continuously and output the reports for vehicles’ driving behaviors in each area. The accuracy of our framework is 95.23%, as we tested with several CCTV videos. Moreover, the framework can be implemented on edge devices with real-time speed for functional implementation and detection in various areas.

A Real-Time Crowdsensing Framework for Potential COVID-19 Carrier Detection Using Wearable Sensors

Artificial intelligence has been utilized extensively in the healthcare sector for the last few decades to simplify medical procedures, such as diagnosis, prognosis, drug discovery, and many more. With the spread of the COVID-19 pandemic, more methods for detecting and treating COVID-19 infections have been developed. Several projects involving considerable artificial intelligence use have been researched and put into practice. Crowdsensing is an example of an application in which artificial intelligence is employed to detect the presence of a virus in an individual based on their physiological parameters. A solution is proposed to detect the potential COVID-19 carrier in crowded premises of a closed campus area, for example, hospitals, corridors, company premises, and so on. Sensor-based wearable devices are utilized to obtain measurements of various physiological indicators (or parameters) of an individual. A machine-learning-based model is proposed for COVID-19 prediction with these parameters as input. The wearable device dataset was used to train four different machine learning algorithms. The support vector machine, which performed the best, received an F1-score of 96.64% and an accuracy score of 96.57%. Moreover, the wearable device is used to retrieve the coordinates of a potential COVID-19 carrier, and the YOLOv5 object detection method is used to do real-time visual tracking on a closed-circuit television video feed.

A Vision-Based Collision Monitoring System for Proximity of Construction Workers to Trucks Enhanced by Posture-Dependent Perception and Truck Bodies’ Occupied Space

In the study, an automated visualization of the proximity between workers and equipment is developed to manage workers’ safety at construction sites using the convolutional-neural-network-based image processing of a closed-circuit television video. The images are analyzed to automatically transform a hazard index visualized in the form of a plane map. The graphical representation of personalized proximity in the plane map is proposed and termed as safety ellipse in the study. The safety ellipse depending on the posture of workers and the area occupied by the hazardous objects (trucks) enable to represent precise proximity. Collision monitoring is automated with computer vision techniques of artificial-intelligence-based object detection, occupied space calculation, pose estimation, and homography.

Pedestrian Localization in a Video Sequence Using Motion Detection and Active Shape Models

There is increasing interest in video object detection for many situations, such as industrial processes, surveillance systems, and nature exploration. In this work, we were concerned with the detection of pedestrians in video sequences. The aim was to deal with issues associated with the background, scale, contrast, or resolution of the video frames, which cause inaccurate detection of pedestrians. The proposed method was based on the combination of two techniques: motion detection by background subtraction (MDBS) and active shape models (ASM). The MDBS technique aids in the identification of a moving region of interest in the video sequence, which potentially includes a pedestrian; then, the ASM algorithm actively finds and adjusts the silhouette of the pedestrian. We tested the proposed MDBS + ASM method with video sequences from open repositories, and the results were favorable in scenes where pedestrians were in a well-illuminated environment. The mean fit error was up to 4.5 pixels. In contrast, in scenes where reflections, occlusions, or pronounced movement are present, the identification was slightly affected; the mean fit error was 8.3 pixels in the worst case. The main contribution of this work was exploring the potential of the combination of MDBS and ASM for performance improvements in the contour-based detection of a moving pedestrian walking in a controlled environment. We present a straightforward method based on classical algorithms which have been proven effective for pedestrian detection. In addition, since we were looking for a practical process that could work in real-time applications (for example, closed-circuit television video or surveillance systems), we established our approach with simple techniques.

Primary Contacts Identification for COVID-19 Carriers from Surveillance Videos

COVID-19 (Coronavirus disease of 2019) is caused by SARS-CoV2 (Severe Acute Respiratory Syndrome Coronavirus 2) and it was first diagnosed in December 2019 in China. As of 25th Aug 2021, there are 165 million confirmed COVID-19 positive cases and 4.4 million deaths globally. As of today, though there are approved COVID-19 vaccine candidates only 4 billion doses have been administered. Until 100% of the population is safe, no one is safe. Even though these vaccines can provide protection against getting seriously ill and dying from the disease, it does not provide 100% protection from getting infected and passing it on to others. The more the virus spreads; it has more opportunity to mutate. So, it is mandatory to follow all precautions like maintaining social distance, wearing mask, washing hands frequently irrespective of whether a person is vaccinated or not. To prevent spread of the virus, contact tracing based on social distance also becomes equally important. The work proposes a solution that can help with contact tracing/identification, knowing the infected persons recent travel history (even within the city) for few days before being assessed positive. While the person would be able to give the known contacts with whom he/she has interacted with, he/she will not be aware of who all were in proximity if he/she had been in public places. The proposed solution is to get the CCTV (Closed-Circuit Television) video clips from those public places for the specific date and time and identify the people who were in proximity—i.e., not followed the safe distance to the infected person. The approach uses YOLO V3 (You Only Look Once) which uses darknet framework for people detection. Once the infected person is located from the video frames, the distance from that person to the other people in the frame is found, to check if there is a violation of social distance guideline. If there is, then the people violating the distance are extracted and identified using Facial detection and recognition algorithms. Two different solutions for Face detection and Recognition are implemented and results compared—Dlib based models and OpenCV (Open Source Computer Vision Library) based models. The solutions were studied for two different CCTV footages and the results for Dlib based models were better than OpenCV based models for the studied videos.

Real-Time Pedestrian Conflict Prediction Model at the Signal Cycle Level Using Machine Learning Models

Compared with traditional traffic studies, real-time safety analyses can be better incorporated into proactive traffic management strategies to improve traffic safety. However, few studies have investigated the real-time pedestrian safety model. Intersections usually have mixed traffic conditions with more pedestrian-vehicle interactions. This paper uses conflict indicators, PET (Post Encroachment Time) and TTC (Time to Collision) to identify pedestrians’ conflicts from CCTV (closed-circuit television) videos. The high-resolution traffic data from the Automated Traffic Signal Performance Measures (ATSPM) system are used to derive traffic flow-related variables. The pedestrian exposure is also estimated. Pedestrians’ conflicts are predicted using multiple machine learning models and Logistic Regression. The resampling methods, random over-sampling, and random under-sampling are compared. The best model, Extreme Gradient Boosting (XGBT) with random over-sampling method can achieve AUC (area under the ROC curve) value of 0.841 and recall value of 0.739 on the test data set. The proposed model can predict pedestrians’ conflicts one cycle ahead, which can be 2–3 min. The proposed model has the potential to be implemented in the Connected and Automated Vehicles (CAV) environment to adjust signal timing accordingly and enhance traffic safety.

Earthquake Reconnaissance Data Sources, a Literature Review

Earthquakes are one of the most catastrophic natural phenomena. After an earthquake, earthquake reconnaissance enables effective recovery by collecting data on building damage and other impacts. This paper aims to identify state-of-the-art data sources for building damage assessment and provide guidance for more efficient data collection. We have reviewed 39 articles that indicate the sources used by different authors to collect data related to damage and post-disaster recovery progress after earthquakes between 2014 and 2021. The current data collection methods have been grouped into seven categories: fieldwork or ground surveys, omnidirectional imagery (OD), terrestrial laser scanning (TLS), remote sensing (RS), crowdsourcing platforms, social media (SM) and closed-circuit television videos (CCTV). The selection of a particular data source or collection technique for earthquake reconnaissance includes different criteria depending on what questions are to be answered by these data. We conclude that modern reconnaissance missions cannot rely on a single data source. Different data sources should complement each other, validate collected data or systematically quantify the damage. The recent increase in the number of crowdsourcing and SM platforms used to source earthquake reconnaissance data demonstrates that this is likely to become an increasingly important data source.

Automation for sewer pipe assessment: CCTV video interpretation algorithm and sewer pipe video assessment (SPVA) system development

This research aims at improving the automation of the sewer pipe assessment process, specifically in terms of the development of a closed-circuit television (CCTV) video interpretation algorithm and sewer pipe video assessment (SPVA) system. A novel video interpretation algorithm for sewer pipes (VIASP) is proposed to use the labeled video (which is labeled by an automated defect detector) as the input in order to extract the useful information from the video, with the final output being the sewer pipe assessment report in textual format. To develop the VIASP, an optimization algorithm using simulated annealing (SA) is employed to determine the optimal human-defined parameters for the VIASP. A prototype of the SPVA system is developed to show how the developed automation techniques can fit into the daily workflow of sewer pipe assessment work. The effectiveness of the proposed method is validated in a case study.

Development of the Wits Face Database: an African database of high-resolution facial photographs and multimodal closed-circuit television (CCTV) recordings.

Forensic facial comparison is a commonly used, yet under-evaluated method employed in medicolegal contexts across the world. Testing the accuracy and reliability of facial comparisons requires large scale controlled and matching facial image databases. Databases that contain images of individuals on closed-circuit television (CCTV), with matching formal and informal photographs are needed for this type of research. Although many databases are available, the majority if not all are developed in order to improve facial recognition and face detection algorithms through machine learning, with very limited if any measure of standardisation. This paper aims to review the available databases and describe the development of a high resolution, standardised facial photograph and CCTV recording database of male Africans. The database is composed of a total of 6220 standardised and uncontrolled suboptimal facial photographs of 622 matching individuals in five different views, as well as corresponding CCTV footage of 334 individuals recorded under different realistic conditions. A detailed description of the composition and acquisition process of the database as well as its subdivisions and possible uses are provided. The challenges and limitations of developing this database are also highlighted, particularly with regard to obtaining CCTV video recordings and ethics for a database of faces. The application process to access the database is also briefly described.

A steerable pyramid autoencoder based framework for anomaly frame detection of water pipeline CCTV inspection

Closed-circuit television (CCTV) is being widely adopted in water pipeline inspection. The inspector needs to spend a long time to watch the recorded video during the office-based survey and can get fatigue easily. An automated process can release the inspector’s work load and ensure the consistent quality of the survey. However, a fully automated survey of varied structural discontinuities still remains as a challenge. This study aims to first identify the anomaly frames of the CCTV video, which contain the major anomalies captured from the internal surface of the pipe. Thus, the inspector can focus more on these anomaly frames. In this paper, an anomaly frame detection framework based on steerable pyramid autoencoder (SPAE) is proposed. The SPAE can generate discriminative representations to be used in the prediction. Both the parameter optimization and comparative studies for the proposed SPAE were carried out in this research. The experimental results demonstrate that this novel SPAE algorithm can achieve 0.984 accuracy and 0.984 F1-score, which outperforms other state-of-the-art methods selected for comparison. Thus, the proposed framework can significantly improve the accuracy and efficiency for anomaly frame detection, which will highly facilitate the pipeline condition assessment through the CCTV inspection.