Search

Given the global importance and limited availability of phosphate, optimizing the use of this critical resource and minimizing its wastage are of paramount importance. In this context, this paper proposes an innovative architecture for the implementation of an intelligent video surveillance system specifically designed for open-pit phosphate mines. The proposed architecture is designed to meet the overall functional requirements of a surveillance system in the challenging environment of open-pit mining, while aligning with the guidelines of the Mine 4.0 revolution. It incorporates advanced technologies that address the critical challenges of latency, data security, and transparency commonly encountered in traditional monitoring systems. By adopting a multi-layered approach that leverages edge, fog, and cloud computing, coupled with blockchain technology and expert collaboration, our architecture offers a comprehensive framework for efficient data processing at every stage, from initial data acquisition to real-time anomaly detection and decision-making. [ABSTRACT FROM AUTHOR]

In recent decades, technological progress and the development of Artificial Intelligence (AI) have profoundly transformed the way modern societies operate, interact and ensure security. AI has become an essential tool in the field of public order, providing innovative solutions that have enabled law enforcement to accomplish their mission with increased efficiency and precision. This text explores the possible possibilities of AI in public policy, highlighting its use in crime prevention, predictive analytics, intelligent video surveillance, assisting in investigations, protecting critical infrastructure, managing emergencies and contributing to citizen engagement. Ethical and legal challenges associated with the integration of AI are also discussed, such as privacy and protection of personal data, algorithmic discrimination, impact on civil liberties, and cybersecurity vulnerabilities. The paper highlights the need for a balanced approach to the adoption of AI in public policy, which includes the development of responsible policies and regulations, ensuring transparency and accountability of authorities, as well as collaboration between policy makers, technical experts, human rights organizations and citizens, to promote . a just and secure society.

Given the global importance and limited availability of phosphate, optimizing the use of this critical resource and minimizing its wastage are of paramount importance. In this context, this paper proposes an innovative architecture for the implementation of an intelligent video surveillance system specifically designed for open-pit phosphate mines. The proposed architecture is designed to meet the overall functional requirements of a surveillance system in the challenging environment of open-pit mining, while aligning with the guidelines of the Mine 4.0 revolution. It incorporates advanced technologies that address the critical challenges of latency, data security, and transparency commonly encountered in traditional monitoring systems. By adopting a multi-layered approach that leverages edge, fog, and cloud computing, coupled with blockchain technology and expert collaboration, our architecture offers a comprehensive framework for efficient data processing at every stage, from initial data acquisition to real-time anomaly detection and decision-making.

Person re-identification (re-ID) involves the cross-camera retrieval and matching of target pedestrian images, facilitating pedestrian association in scenarios where biometric features such as faces and fingerprints may prove ineffective. It has become a pivotal technology in intelligent video surveillance systems, playing a crucial role in domains like smart security and smart cities. Traditional re-ID algorithms typically employ either representation learning or metric learning methods. A novel approach was proposed which combined representation learning and metric learning methods based on the multi-task learning machine learning paradigm. By capitalizing on the advantages of both feature representation and distance metric, and concurrently training the model using classification loss and triplet loss, comprehensive training for both feature extraction and similarity measurement was ensured. Experimental results validate the effectiveness of the proposed approach, demonstrating superior performance in re-ID tasks and underscoring the robustness and superior generalization capability.

To assure operational safety in the airport apron area and track the process of ground service, it is necessary to analyze key targets and their activities in the airport apron surveillance videos. This research shows an activity identification algorithm for ground service objects in an airport apron area and proposes an improved YOLOv5 algorithm to increase the precision of small object detection by introducing an SPD-Conv (spath-to-depth-Conv) block in YOLOv5's backbone layer. The improved algorithm can efficiently extract the information features of small-sized objects, medium-sized objects, and moving objects in large scenes, and it achieves effective detection of activities of ground service in the apron area. The experimental results show that the detection average precision of all objects is more than 90%, and the whole class mean average precision (mAP) is 98.7%. At the same time, the original model was converted to TensorRT and OpenVINO format models, which increased the inference efficiency of the GPU and CPU by 55.3 and 137.1%, respectively.

Anomaly detection approaches have limiting aspects regarding the representativeness of the information since the video data is captured from a single perspective and may not distinguish all relevant aspects of the scene. The lack of sufficient labeled data is also a challenging aspect of building video anomaly detection approaches. Although multiple instance learning (MIL) has been explored extensively in the weakly supervised video anomaly detection (WS-VAD) literature since it is less hungry for labeled data, there are no studies that exploit multiple overlapping camera views to provide wider representativeness of vision data under MIL assumption. In this work, we show the performance of the video anomaly detection task can be improved by using multiple cameras to capture spatiotemporal information from different perspectives. We propose the approach MC-MIL (Video Anomaly Detection with Multiple Overlapped Cameras and Multiple Instance Learning) framework, which consists of a training scheme with multiple cameras under multiple instance learning for video anomaly detection. We specialize our proposed framework for the two-camera case as a proof of concept for performance evaluation. Due to the lack of datasets for this task, we relabeled the multiple-camera PETS-2009 benchmark dataset for the anomaly detection task from multiple overlapped camera views to evaluate the MC-MIL algorithm. The result shows a significant performance improvement in the AUC ROC score compared to the single-camera configuration and with the literature. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunications Science is the property of Beijing Xintong Media Co., Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To assure operational safety in the airport apron area and track the process of ground service, it is necessary to analyze key targets and their activities in the airport apron surveillance videos. This research shows an activity identification algorithm for ground service objects in an airport apron area and proposes an improved YOLOv5 algorithm to increase the precision of small object detection by introducing an SPD-Conv (spath-to-depth-Conv) block in YOLOv5's backbone layer. The improved algorithm can efficiently extract the information features of small-sized objects, medium-sized objects, and moving objects in large scenes, and it achieves effective detection of activities of ground service in the apron area. The experimental results show that the detection average precision of all objects is more than 90%, and the whole class mean average precision (mAP) is 98.7%. At the same time, the original model was converted to TensorRT and OpenVINO format models, which increased the inference efficiency of the GPU and CPU by 55.3 and 137.1%, respectively. [ABSTRACT FROM AUTHOR]

Detecting objects within real-time video frames is a formidable challenge due to visual degradation and object movement complexities. This research presents a three-step strategy to construct an advanced intelligent video surveillance system using hybrid deep learning techniques. A modified Barnacles Mating Optimization (MBMO) algorithm is introduced to segment objects from video frames, addressing redundancy and temporal intricacies. Further, a Chaotic Hummingbird Optimization (CHO) algorithm is employed for feature optimization, mitigating data dimensionality issues. The core innovation involves a Hybrid Convolutional Neural Network with Supreme Gradient Boosting (hybrid CNN-SGboost) classifier for precise object prediction and detection. Validation is conducted on benchmark datasets, including Penn-Fudan pedestrians, Daimler pedestrian segmentation, and Inria person, comparing the hybrid CNN-SGboost classifier against state-of-the-art alternatives using common evaluation parameters. Simulation outcomes affirm the superiority of the hybrid model, marking a significant advancement in accurate object detection for video surveillance applications. [ABSTRACT FROM AUTHOR]

Smart city is an area where the Internet of things is used effectively with sensors. The data used by smart city can be collected through the cameras, sensors etc. Intelligent video surveillance (IVS) systems integrate multiple networked cameras for automatic surveillance purposes. Such systems can analyze and monitor video data and perform automatic functions required by users. This study performed main path analysis (MPA) to explore the development trends of IVS research. First, relevant articles were retrieved from the Web of Science database. Next, MPA was performed to analyze development trends in relevant research, and g-index and h-index values were analyzed to identify influential journals. Cluster analysis was then performed to group similar articles, and Wordle was used to display the key words of each group in word clouds. These key words served as the basis for naming their corresponding groups. Data mining and statistical analysis yielded six major IVS research topics, namely video cameras, background modeling, closed-circuit television, multiple cameras, person reidentification, and privacy, security, and protection. These topics can boost the future innovation and development of IVS technology and contribute to smart transportation, smart city, and other applications. According to the study results, predictions were made regarding developments in IVS research to provide recommendations for future research. [ABSTRACT FROM AUTHOR]

Existing CNN-based video anomaly detection methods improve the accuracy continuously, which are faced with issues such as complex architecture, large parameters and lengthy training. Therefore, the hardware computing power requirements of them are high, which makes it difficult to adapt to edge devices with limited computing resources like UAVs. To this end, this paper proposed a lightweight abnormal event detection method for edge devices. Firstly, the method extracted gradient cuboids and optical flow cuboids from video sequence as appearance and motion feature representation; Secondly, the method designed a modified PCANet network to obtain high-level block-wise histogram features of gradient cuboids; Then, the method calculated the appearance anomaly score of each block based on histogram feature distribution, and calculated the motion anomaly score based on the accumulation of optical flow amplitudes of internal pixels; Finally, the method fused the appearance and motion anomaly scores to identify anomalous blocks, achieving appearance and motion abnormal events detection and localization simultaneously. The frame-level AUC of proposed method reached 86.7% on UCSD Ped1 dataset and 94.9% on UCSD Ped2 dataset, which were superior to other methods and the parameters are much smaller. Experimental results show that the method achieves better anomaly detection performance under low computational power requirements, making the balance between detection precision and computing resources, which is suitable for low-power edge devices. [ABSTRACT FROM AUTHOR]

Academics have become increasingly interested in creating cutting-edge technologies to enhance Intelligent Video Surveillance (IVS) performance in terms of accuracy, speed, complexity, and deployment. It has been noted that precise object detection is the only way for IVS to function well in higher level applications including event interpretation, tracking, classification, and activity recognition. Through the use of cutting-edge techniques, the current study seeks to improve the performance accuracy of object detection techniques based on Gaussian Mixture Models (GMM). It is achieved by developing crucial phases in the object detecting process. In this study, it is discussed how to model each pixel as a mixture of Gaussians and how to update the model using an online k-means approximation. The adaptive mixture model's Gaussian distributions are then analyzed to identify which ones are more likely to be the product of a background process. Each pixel is categorized according to whether the background model is thought to include the Gaussian distribution that best depicts it.

Human activity recognition (HAR) has become a highly researched area with numerous practical applications in public safety. Deep learning has revolutionized HAR by introducing novel approaches to tackle its challenges. Abnormal activity recognition enables prompt intervention and enhances public safety. Presently visionbased activity recognition techniques mainly use recurrent neural network (RNN) architectures like LSTM to handle sequential data dependency. However, this approach struggles to capture the spatial information between consecutive frames in video data, limiting their ability to learn spatiotemporal patterns. To address this issue, we introduce a layer called ResAttenConvLSTM2D, a variant of the ConvLSTM layer, and propose a novel architecture for solving the abnormal activity recognition problem. In the residual attention model, attention is applied to the residual connections, enabling the network to concentrate on portions of the input by calculating the attention score at each time iteration during model training. In addition, the proposed approach addresses the challenge of limited resources in handling video data by employing robust key frame extraction methods using an unsupervised K-Means algorithm. The proposed architecture is tested for benchmark datasets, i.e., AIRT Lab, hockey fight, and abnormal human activity with a classification accuracy of 90%, 96%, and 99% respectively, showing comparable accuracy or complexity compared to the state-of-the-art (SOTA) approaches. [ABSTRACT FROM AUTHOR]

Smart city is an area where the Internet of things is used effectively with sensors. The data used by smart city can be collected through the cameras, sensors etc. Intelligent video surveillance (IVS) systems integrate multiple networked cameras for automatic surveillance purposes. Such systems can analyze and monitor video data and perform automatic functions required by users. This study performed main path analysis (MPA) to explore the development trends of IVS research. First, relevant articles were retrieved from the Web of Science database. Next, MPA was performed to analyze development trends in relevant research, and g-index and h-index values were analyzed to identify influential journals. Cluster analysis was then performed to group similar articles, and Wordle was used to display the key words of each group in word clouds. These key words served as the basis for naming their corresponding groups. Data mining and statistical analysis yielded six major IVS research topics, namely video cameras, background modeling, closed-circuit television, multiple cameras, person reidentification, and privacy, security, and protection. These topics can boost the future innovation and development of IVS technology and contribute to smart transportation, smart city, and other applications. According to the study results, predictions were made regarding developments in IVS research to provide recommendations for future research.

Person re-identification is a challenging yet meaningful task to match two pedestrian images captured from non-overlapping cameras for public security. Attention schemes have been widely applied to deep learning based person re-identification because they help deep networks dynamically focus on salient regions on person images containing large scale variations and unconstrained auto-detection errors. However, previous attention approaches typically are of a single receptive field, which are difficult to capture rich structural affinities from different scales, harming salient region inferring effect. In this paper, we propose a multi-receptive field attention (MRFA) for person re-identification. MRFA captures multi-scale structural affinities among spatial positions in feature maps via weighted summing over correlations among positions represented with convolutional features of different receptive fields. The multi-scale structural affinities are further applied to infer the importance of different spatial locations. The MRFA is embedded into popular deep architectures (e.g., ResNet and Res2Net) to enhance the feature learning effect for person re-identification. The main contribution of this paper is to extend single receptive field attention to multi-receptive field attention to improve person re-identification effectively. Experiments on three public datasets, i.e., Market-1501, DukeMTMC-reID, and MSMT17, demonstrate that our method is superior to state-of-the-art person re-identification approaches, e.g., on the largest MSMT17 dataset, our method's rank-1 identification rate is 83.9%. [ABSTRACT FROM AUTHOR]

As one of the important applications of intelligent video surveillance, violent behaviour detection (VioBD) plays a crucial role in public security and safety. As a particular type of behaviour recognition, VioBD aims to identify whether the behaviours that occurred in the scene is aggressive, such as fighting and assault. To comprehensively analyse the current state and predict the future trend of VioBD research, we survey the existing approaches of VioBD in this work. First, we briefly introduce the basic principle and the challenges of VioBD; Then, we category the existing approaches according to their framework, including the traditional framework, end-to-end deep learning framework, and hybrid deep learning framework. Finally, we introduce the public datasets for evaluating the performance of VioBD approaches and compare their performances on these datasets. Besides, we also summarise the open problems in VioBD and predict its future trends. [ABSTRACT FROM AUTHOR]

Video Anomaly Detection (VAD) under a weakly supervised setting involves operating with limited video-level annotations. The practical significance of this work plays a crucial role in applications related to surveillance and security. A commonly adopted strategy within existing Weakly Supervised VAD (WS-VAD) methods involves utilizing various modalities as inputs such as audio and video. This integration is motivated by the ability of these modalities to provide abundant discriminative capabilities in addressing the complexities of diverse real-world scenarios. However, the integration of multimodal data poses challenges like misalignment of temporal features and the need for efficient fusion strategies. In response to these challenges, a transformer-based deep architecture based on Multiview and Multimodality WS-VAD named M 2 VAD is proposed. The proposed M 2 VAD utilizes different views of input with varying durations or resolutions for efficient processing. The Space–Time transformer (ST Transformer) is employed for extracting visual features, while the SpectFormer is utilized for extracting the audio features. To interact and synchronize features from various modalities, a novel Cross-Modality Synchronization (CMS) module is proposed to ensure the coherent representation for strong detection of anomalies. To enhance the overall robustness of the proposed M 2 VAD , the anomaly detection module with optimization techniques is proposed to generate anomaly scores. Experimental studies conducted on benchmark datasets demonstrate the superior performance of the M 2 VAD , underscoring its resilience and generalization across various views and modalities. Code is available at https://github.com/Shalmiyapaulraj78/Multiview-Multimodality-VAD.git. [Display omitted] • Multiview multimodality VAD system is proposed that utilizes different views with varying durations. • ST-Transformer block is proposed in each view of video inputs to capture the visual modality features. • Audio transformer named SpectFormer is employed for audio modality inputs feature extraction. • Cross-Modality Synchronization module with an effective fusion strategy is proposed to synchronize multimodality features. • Performance of the proposed M2VAD has obtained significantly better results over the benchmark datasets. [ABSTRACT FROM AUTHOR]

The number of video cameras in public places increases due to different reasons such as detecting dangers (e.g., thefts, robberies, terrorist attacks) and security breaches in crowds. The application of video surveillance systems is sometimes evaluated ambivalently; therefore, the presented study focuses on factors influencing the acceptance of a privacy-friendly, smart video surveillance system. Overall, 216 persons aged between 18 and 81 years participated in an online survey. In terms of the perceived usefulness, there are significant interactions of public spaces × gender and public spaces × time of day. In addition, the assessment of different privacy levels of a video surveillance system differ significantly in terms of perceived risk. Interestingly, men rate the risk concerning their own privacy significantly higher than women do. Participants rate the presented system as fairly useful and slightly risky for their own privacy. The findings of the presented exploratory study provide insight into how people perceive smart video surveillance. These findings have the potential to support the conditions of the use of smart video surveillance systems and to address the possibly affected individuals. [ABSTRACT FROM AUTHOR]

Airport apron carries a lot of preparations for flight operation, and the advancement of its various tasks is of great significance to the flight operation. In order to build a more intelligent and easy-to-deploy airport apron operation analysis guarantee system, it is necessary to study a low-cost, fast, and real-time object detection scheme. In this article, a real-time object detection solution based on edge cloud system for airport apron operation surveillance video is proposed, which includes lightweight detection model Edge-YOLO, edge video detection acceleration strategy, and a cloud-based detection results verification mechanism. Edge-YOLO reduces the amounts of parameters and computational complexity by using model lightweight technology, which can achieve better detection speed performance on edge-end embedded devices with weak computing power, and adds an attention mechanism to compensate for accuracy loss. Edge video detection acceleration strategy achieves further detection acceleration for Edge-YOLO by utilizing the motion information of objects in the video to achieve real-time detection. Cloud-based detection results verification mechanism verifies and corrects the detection results generated by the edge through a multi-level intervention mechanism to improve the accuracy of the detection results. Through this solution, we can achieve reliable and real-time monitoring of airport apron video on edge devices with the support of a small amount of cloud computing power. [ABSTRACT FROM AUTHOR]

This study describes a method for detecting incomplete cast iron tapping in blast furnace production using computer vision. Incomplete cast iron tapping is a violation of the technological process and can slow down or stop the work of a metallurgical plant, which will lead to economic losses, therefore, the task of detecting incomplete cast iron tapping and notifying the operator of it is relevant. A method for detecting incomplete tapping was developed, based on the use of a neural network detector that detects a jet of cast iron in the tapping hole immediately before the tapping is completed. A dataset was assembled for training a neural network and software was developed to implement the method. An additional method for detecting incomplete tapping was developed, which is based on counting the number of sparks that appear during the subsequent cast iron tapping with the help of computer vision. The software implementing this method was developed, the threshold value of sparks was determined, upon reaching which a notification of the problem is generated. The universal video warning notification system «Empty display» was developed. The developed systems were implemented and tested at public joint-stock company (PJSC) Severstal in the agglomeration and blast-furnace coke production site. Warning notifications were correctly generated in 98% of cases. [ABSTRACT FROM AUTHOR]

This article discusses the Mobile Edge Computing (MEC) architecture. A broad overview of ready-made platforms for IoT systems is presented. Examples of real use of ready-made systems in various fields are considered. The problem of delays in data processing is identified. Nowadays reduction in delays require large computing resources. A solution is proposed based on the modification of the MEC architecture using fog computing environments and cloud computing. An approach for transferring computations to the cloud and fog has been developed. The proposed approach was tested and the results were obtained in relation to the processing of a large amount of data (video information). Specific examples are given.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The continuous developments of urban and industrial environments have increased the demand for intelligent video surveillance. Deep learning has achieved remarkable performance for anomaly detection in surveillance videos. Previous approaches achieve anomaly detection with a single-pretext task (image reconstruction or prediction) and detect anomalies by larger reconstruction error or poor prediction. However, they cannot fully exploit the discriminative semantics and temporal context information. Moreover, tackling anomaly detection with a single pretext task is suboptimal due to the nonalignment between the pretext task and anomaly detection. In this article, we propose a temporal-aware contrastive network (TAC-Net) to address the abovementioned problems of anomaly detection for intelligence video surveillance. TAC-Net is an unsupervised method that utilizes deep contrastive self-supervised learning to capture the high-level semantic features and tackles anomaly detection with multiple self-supervised tasks. During inference phase, the multiple task losses and contrastive similarity are utilized to calculate the anomaly score. Experimental results show that our method is superior to state-of-the-art approaches on three benchmarks, which demonstrates the validity and advancement of TAC-Net. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Locating a missing child or elderly person in a large gathering through face recognition in videos is still challenging because of various dynamic factors. In this paper, we present an intelligent mechanism for tracking missing persons in an unconstrained large gathering scenario of Al-Nabawi Mosque, Madinah, KSA. The proposed mechanism in this paper is unique in two aspects. First, there are various proposals existing in the literature that deal with face detection and recognition in high-quality images of a large crowd but none of them tested tracking of a missing person in low resolution images of a large gathering scenario. Secondly, our proposed mechanism is unique in the sense that it employs four phases: (a) report missing person online through web and mobile app based on spatio-temporal features; (b) geo fence set estimation for reducing search space; (c) face detection using the fusion of Viola Jones cascades LBP, CART, and HAAR to optimize the results of the localization of face regions; and (d) face recognition to find a missing person based on the profile image of reported missing person. The overall results of our proposed intelligent tracking mechanism suggest good performance when tested on a challenging dataset of 2208 low resolution images of large crowd gathering. [ABSTRACT FROM AUTHOR]

Intelligent video surveillance is an important computer vision application in natural environments. Since detected objects under surveillance are usually low-resolution and noisy, their accurate recognition represents a huge challenge. Knowledge distillation is an effective method to deal with it, but existing related work usually focuses on reducing the channel count of a student network, not feature map size. As a result, they cannot transfer “privilege information” hidden in feature maps of a wide and deep teacher network into a thin and shallow student one, leading to the latter’s poor performance. To address this issue, we propose a Feature Map Distillation (FMD) framework under which the feature map size of teacher and student networks is different. FMD consists of two main components: Feature Decoder Distillation (FDD) and Feature Map Consistency-enforcement (FMC). FDD reconstructs the shallow texture features of a thin student network to approximate the corresponding samples in a teacher network, which allows the high-resolution ones to directly guide the learning of the shallow features of the student network. FMC makes the size and direction of each deep feature map consistent between student and teacher networks, which constrains each pair of feature maps to produce the same feature distribution. FDD and FMC allow a thin student network to learn rich “privilege information” in feature maps of a wide teacher network. The overall performance of FMD is verified in multiple recognition tasks by comparing it with state-of-the-art knowledge distillation methods on low-resolution and noisy objects. [ABSTRACT FROM AUTHOR]

In order to solve the problems of limited monitoring range,unreasonable allocation of monitoring resources,and untimely detection of moving targets in intelligent video surveillance systems under special application scenarios,the use of radar to detect electromagnetic waves has astrong penetration ability,large search range,and being not subject to special weather and optical conditions.Combined with the flexibility and maneuverability of unmanned aerial vehicles and automatic navigation vehicles,this paper proposes a radar-directed integrated linkage video surveillance model,and on this basis,studies a unified coordinate positioning system based on geodetic coordinates and intelligent assignment and positioning algorithm of moving target based on fuzzy neural network optimized by particle swarm optimization.The algorithm can automatically solve the control parameters of each camera in three dimensions of horizontal,vertical and zoom according to the radar detection signal,and combines the linkage control system to achieve real-time positioning and tracking of moving targets.Through field tests at a cultural relics protection site,the accuracy of the target positioning accuracy of the geodetic positioning system reaches 99.6%,and the accuracy rate of the intelligent assignment algorithm for moving targets based on the fuzzy neural network reaches 95%,which can achieve precise positioning and intelligent allocation of monitoring resources,and has high practical application value.

The increase in the deployment of surveillance camera in outdoor and indoor settings have resulted in a growing demand for intelligent systems that can accurately detect and recognize human actions as well as other entities of interest within the captured video data. Although, human action recognition is a well-established topic in computer vision, abnormal behaviour detection has recently received increased research attention. Several abnormal behaviour detection systems have been proposed over the years to ensure human safety. However, only a few comprehensive and systematic reviews report on the current state and future direction of video anomaly detection(VAD) research. This present effort aims to contribute a systematic and detailed review of current research and advances in the detection of anomalous actions and entities in videos. The review focuses on studies published between 2003 and 2023. During the literature selection process, 530 scholarly articles were identified and evaluated to showcase prevalent research trends, techniques, datasets, and frameworks within the realm of VAD This review aims to offer a comprehensive understanding of key areas of focus among researchers, provide resources for commonly used public datasets for evaluation and experimentation, and examine advancements and integration of network design to accommodate the needs for handling multimedia information. To sum up, this study highlights various potential opportunities and obstacles about the VAD domain.VAD has gained significant interest in recent years due to its potential applications in various domains such as security, surveillance, traffic monitoring, medical imaging among others. Areas of further research include, Anomaly detection in real-time, multi-camera anomaly detection, privacy preserving in VAD to mention a few. The study revealed some key trends and challenges in VAD that can guide future research direction. [ABSTRACT FROM AUTHOR]

Video anomaly detection automatically recognizes abnormal events in surveillance videos. Existing works have made advances in recognizing whether a video contains abnormal events; however, they cannot temporally localize the abnormal events within videos. This paper presents a novel anomaly attention-based framework for accurately temporally localize the abnormal events. Benefiting from the proposed framework, we can achieve frame-level VAD using video-level labels, which significantly reduces the burden of data annotation. Our method is an end-to-end deep neural network-based approach, which contains three modules: anomaly attention module (AAM), discriminative anomaly attention module (DAAM) and generative anomaly attention module (GAAM). Specifically, AAM is trained to generate the anomaly attention, which is used to measure the abnormal degree of each frame. Whereas, DAAM and GAAM are used to alternately augmenting AAM from two different aspects. On the one hand, DAAM enhancing AAM by optimizing the video-level video classification. On the other hand, GAAM adopts a conditional variational autoencoder to model the likelihood of each frame given the attention for refining AAM. As a result, AAM can generate higher anomaly scores for abnormal frames while lower anomaly scores for normal frames. Experimental results show that our proposed approach outperforms state-of-the-art methods, which validates the superiority of our AAVAD. [ABSTRACT FROM AUTHOR]

Intelligent video surveillance systems are rapidly being introduced to public places. The adoption of computer vision and machine learning techniques enables various applications for collected video features; one of the major is safety monitoring. The efficacy of violent event detection is measured by the efficiency and accuracy of violent event detection. In this paper, we present a novel architecture for violence detection from video surveillance cameras. Our proposed model is a spatial feature extracting a U-Net-like network that uses MobileNet V2 as an encoder followed by LSTM for temporal feature extraction and classification. The proposed model is computationally light and still achieves good results—experiments showed that an average accuracy is 0.82 ± 2% and average precision is 0.81 ± 3% using a complex real-world security camera footage dataset based on RWF-2000. [ABSTRACT FROM AUTHOR]

Intelligent video surveillance is important to ensure production safety in coal mines, while cloud-edge cooperation is an effective means to improve the performance of intelligent video monitoring. However, in edge layers, incorrect resource allocation of computing and network resources will result in the waste of resources and low real-time performance. In this paper, a DDPG-Based (Deep deterministic policy gradient-based) edge resource allocation method for cloud-edge cooperation framework is proposed. Firstly, the cloud-edge cooperation framework is designed for different tasks. Secondly, the joint minimizing problem of latency and bandwidth usage caused by edge computing is modeled. To quickly solve the joint optimization problem, we convert it to MDP (Markov Decision Process). In addition, ESPN (Edge status perception network) is proposed, which enhances the ability of feature perception and action output of DDPG. Finally, DDPG-ESPN is proposed to solve the joint optimization problem. Simulation results show that compared with other methods, DDPG-ESPN improves the real-time performance and bandwidth usage by up to 18.88% and 42.81% respectively.

Modeling abnormal behavior detection in the intelligent video monitoring system for recognition or detection of special event has attracted significant research interest in recent years. In order to achieve more effective recognition of abnormal behavior detection of the intelligent video surveillance system, this paper proposes a working human abnormal operation recognition approach based on deep multi-instance sorting model. Firstly, the uncut long video is sparse to obtain normal and abnormal behavior video segments, and the RGB and optical flow features in the segment are extracted by the deep convolution network. Video feature vectors are obtained by the consensus function and feature extractor. Then, multi-instance sorting learning is used to assign abnormality scores between 0 and 1 to feature vectors. When the abnormal values of abnormal packets are higher than those of normal packets, the abnormality score is returned and the high abnormality score is determined as an abnormal behavior. The experiments on the open THUMOS14 data set and our own XAGCWD data set using CUDA GPU accelerated computing to demonstrate that our approach improves the recognition accuracy about 10.8% and high accuracy of abnormal detection. The main purpose of this research is to apply the model proposed in this paper to the intelligent workshop behavior monitoring system to effectively realize the safety management of workshop personnel. [ABSTRACT FROM AUTHOR]

The construction industry is extremely high risk, and safety checklist analysis is a widely used approach for safety assessment. To overcome its limitations, this article proposes an improved safety checklist analysis approach using intelligent video surveillance to replace on-site inspection. Then, a case study on metro tunnel construction is adopted to illustrate the process. First, the checklist is prepared. Second, the inspection items are correlated with construction areas, and intelligent cameras are positioned to cover the major areas of the construction site to guarantee that all the items can be checked. Thus, problems with inspection items are automatically identified and recorded. Third, the inspection items are marked by a remote scoring mechanism for safety assessment. Finally, the efficiency of the improved approach is tested by a comparative analysis among three groups. The application results indicate the feasibility of the improved approach for evaluating the safety management performance at construction sites. [ABSTRACT FROM AUTHOR]

The recent intelligent surveillance systems provide various services that have not existed before, such as proactive predictive surveillance, through the AI-based video analysis technology. However, there are common security and privacy challenges caused by malicious attacker and untrusted 3rd party in the CCTV cloud system. To solve this problem, we exploit the blockchain technology to insure integrity and security of cloud-based intelligent surveillance system. In this paper, we propose a new method for cloud-based CCTV blockchain system. Our contribution is to propose a new Merkle-Tree method for the efficient transmission of video data. The suggested method in this paper is efficient because it reduces the bandwidth required for transmission. It also has the advantage of enabling deduplication to reduce storage costs. Also, the proposed method can synchronize CCTV video data safely without exposing the privacy of the object in the course of synchronization. [ABSTRACT FROM AUTHOR]

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The number of video cameras in public places increases due to different reasons such as detecting dangers (e.g., thefts, robberies, terrorist attacks) and security breaches in crowds. The application of video surveillance systems is sometimes evaluated ambivalently; therefore, the presented study focuses on factors influencing the acceptance of a privacy-friendly, smart video surveillance system. Overall, 216 persons aged between 18 and 81 years participated in an online survey. In terms of the perceived usefulness, there are significant interactions of public spaces × gender and public spaces × time of day. In addition, the assessment of different privacy levels of a video surveillance system differ significantly in terms of perceived risk. Interestingly, men rate the risk concerning their own privacy significantly higher than women do. Participants rate the presented system as fairly useful and slightly risky for their own privacy. The findings of the presented exploratory study provide insight into how people perceive smart video surveillance. These findings have the potential to support the conditions of the use of smart video surveillance systems and to address the possibly affected individuals.

Airport apron carries a lot of preparations for flight operation, and the advancement of its various tasks is of great significance to the flight operation. In order to build a more intelligent and easy-to-deploy airport apron operation analysis guarantee system, it is necessary to study a low-cost, fast, and real-time object detection scheme. In this article, a real-time object detection solution based on edge cloud system for airport apron operation surveillance video is proposed, which includes lightweight detection model Edge-YOLO, edge video detection acceleration strategy, and a cloud-based detection results verification mechanism. Edge-YOLO reduces the amounts of parameters and computational complexity by using model lightweight technology, which can achieve better detection speed performance on edge-end embedded devices with weak computing power, and adds an attention mechanism to compensate for accuracy loss. Edge video detection acceleration strategy achieves further detection acceleration for Edge-YOLO by utilizing the motion information of objects in the video to achieve real-time detection. Cloud-based detection results verification mechanism verifies and corrects the detection results generated by the edge through a multi-level intervention mechanism to improve the accuracy of the detection results. Through this solution, we can achieve reliable and real-time monitoring of airport apron video on edge devices with the support of a small amount of cloud computing power.

Background subtraction, being the most cited algorithm for foreground detection, encounters the major problem of proper threshold value at run time. For effective value of the threshold at run time in background subtraction algorithm, the primary component of the foreground detection process, motion is used, in the proposed algorithm. For the said purpose, the smooth histogram peaks and valley of the motion were analyzed, which reflects the high and slow motion areas of the moving object(s) in the given frame and generates the threshold value at run time by exploiting the values of peaks and valley. This proposed algorithm was tested using four recommended video sequences, including indoor and outdoor shoots, and were compared with five high ranked algorithms. Based on the values of standard performance measures, the proposed algorithm achieved an average of more than 12.30% higher accuracy results. [ABSTRACT FROM AUTHOR]

Copyright of Experimental Technology & Management is the property of Experimental Technology & Management Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)