Search

Automatic traffic accident detection has attracted the attention of the machine vision community for the rapid development of autonomous intelligent transportation systems (ITS). However, previous studies in this domain have been constrained by small-scale datasets with limited scope, impeding their effectiveness and applicability. Specifically, highway traffic accidents, often resulting in severe consequences due to higher speeds, require a more comprehensive approach to detection. The use of video surveillance provides a unique perspective, capturing the entire accident sequence. Unfortunately, existing traffic accident datasets are either not sourced from surveillance cameras, not publicly available, or not tailored for highway scenarios. An open-sourced traffic accident dataset with various scenes from surveillance cameras is in great need and of practical importance. To fulfill the above urgent need, we endeavor to collect abundant video data of real traffic accidents and propose a large-scale traffic accidents dataset, named TAD. Various experiments on image classification, video classification, and object detection tasks, using public mainstream vision algorithms or frameworks are conducted in this work to demonstrate the performance of different methods. The proposed dataset together with the experimental results are presented as a new benchmark to improve computer vision research, especially in ITS. The dataset is publicly available at https://github.com/UnicomAI/UnicomBenchmark/tree/main/TADBench.

China has rapidly evolved into a surveillance society. While much attention has been paid to describing the leviathan represented by the presence of surveillance cameras in China, empirical evidence on the mechanisms of the creep of surveillance remains limited. Using data collected through fieldwork and in-depth interviews, this study explores the spread of surveillance cameras and the resistance encountered in a middle school in northern China. We find that surveillance cameras were first introduced for security purposes, but their application was quickly expanded to discipline students and avoid responsibilities in school management. We further explore the resistance to the creep made possible by the existence of exempted spaces, the difficulty of self-surveillance, and what might be called the boomerang effect. Through the case study of a middle school, this research sheds light on the formation of the Chinese surveillance society from a bottom-up approach and contributes to the global literature on surveillance creep. [ABSTRACT FROM AUTHOR]

In the era of digitalization of urban spaces, video surveillance systems play a key role in ensuring public safety. However, vulnerabilities in the software and hardware of these systems can lead to serious privacy and security breaches. The importance of this topic is due to the growing number of cyber attacks and data leaks, the targets of which are often urban infrastructure. Purpose. The main aim of this article is to analyze the vulnerabilities of video surveillance systems in the context of urban infrastructure, as well as to identify potential risks to data security and personal privacy. The article seeks to identify weaknesses in technologies and offer recommendations for eliminating them. Methodology. The analysis used methods for analyzing data on violations in video surveillance systems over the past five years and a review of modern technologies: Study of modern encryption methods and practices of regular software updates aimed at minimizing risks. Results. The study showed that most video surveillance systems are vulnerable to medium-level attacks. The most common vulnerabilities are related to insufficient data encryption and outdated software. As a result of the analysis, proposals were developed to strengthen data protection, including regular software updates and the use of multi-level authentication and encryption systems. Practical implications. The findings and recommendations for strengthening surveillance systems can be applied across various sectors of urban infrastructure, including public transportation, municipal institutions, and commercial facilities. The implementation of these recommendations is particularly critical for locations with high foot traffic and elevated security requirements, such as schools, hospitals, and shopping centers. Effective adoption of the proposed encryption technologies and enhanced security measures will help prevent not only data breaches but also potential acts of terrorism or other security threats to citizens.

In the rapidly evolving realm of transportation technology, the dynamic relationship between pedestrians and technological innovations has attained unprecedented importance. The complex social-technological intersection surrounding pedestrian road crossings has emerged as an attention for traffic safety. What distinguishes the contemporary urban environment is the rapid assimilation of intelligent transportation systems (ITS) into the transportation infrastructure, including technological elements such as autonomous vehicles, advanced surveillance systems, and smart infrastructure. To investigate how pedestrians perceive risks, trust technology, and make decisions in this era of technological progress, we designed a video-based questionnaire utilizing the stated preference (SP) methodology. We collected SP data from 589 Chinese pedestrians and employed an integrated choice and latent variable (ICLV) model to quantify the influence of risk perception and trust in autonomous vehicle (trust in AV), treated as latent variables, on their crossing decisions. Our findings indicate that the presence of autonomous vehicles significantly affects pedestrian crossing decisions. Specifically, an increase in the approaching vehicle speed and a decrease in the approaching vehicle distance increase the pedestrians' tendency to choose not to cross the road, and the latent variables of risk perception and trust in AV strongly predict this phenomenon. The results of the scenario analysis show that, compared with overall pedestrians, middle-aged pedestrians and high-risk perception-level pedestrians are more conservative in their crossing decisions, but high levels of trust in AV improve pedestrians' willingness to cross the street. Additionally, the pedestrian-related findings of this study at the social-technological intersection provide better understanding of the decision process and contribute to the planning and development of urban intelligent transportation systems. • Relationship between ITS facilities, pedestrian risk perception, trust in AV, and crossing decisions are investigated. • A video-based SP questionnaire was design. • The ICLV model was used to predict pedestrians' propensity to cross the street. • The presence of autonomous vehicles can have a significant impact on pedestrian crossing decision. • Pedestrians who are middle-aged, and have high levels of risk perception are more conservative in their crossing decisions. [ABSTRACT FROM AUTHOR]

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.

In this study, we proposed a method for estimating windsea parameters from the images captured by the surveillance camera installed in coastal areas for practical use. Camera images were acquired in the observation room of the Tokyo Bay Marine Traffic Center at Cape Kannon in Tokyo Bay, Japan for approximately 4 months. Video images of the sea surface were analyzed using in-situ wave observations and wave model data. The brightness spectrum in the frequency domain and the brightness period were defined and introduced from the time series of brightness values in the obtained video images. The novelty of this study lies in the method proposed for estimating the wave parameters using the brightness period. Although this is a simple method, we confirmed that the wave parameters for windsea, such as the significant wave height and significant wave period, can be estimated with high accuracy using the brightness period. Furthermore, we confirmed that the brightness spectrum obtained from camera images and the slope spectrum of wind waves exhibited extremely similar shapes. [ABSTRACT FROM AUTHOR]

Smart video surveillance helps to build more robust smart city environment. The varied angle cameras act as smart sensors and collect visual data from smart city environment and transmit it for further visual analysis. The transmitted visual data is required to be in high quality for efficient analysis which is a challenging task while transmitting videos on low capacity bandwidth communication channels. In latest smart surveillance cameras, high quality of video transmission is maintained through various video encoding techniques such as high efficiency video coding. However, these video coding techniques still provide limited capabilities and the demand of high-quality based encoding for salient regions such as pedestrians, vehicles, cyclist/motorcyclist and road in video surveillance systems is still not met. This work is a contribution towards building an efficient salient region-based surveillance framework for smart cities. The proposed framework integrates a deep learning-based video surveillance technique that extracts salient regions from a video frame without information loss, and then encodes it in reduced size. We have applied this approach in diverse case studies environments of smart city to test the applicability of the framework. The successful result in terms of bitrate 56.92%, peak signal to noise ratio 5.35 bd and SR based segmentation accuracy of 92% and 96% for two different benchmark datasets is the outcome of proposed work. Consequently, the generation of less computational region-based video data makes it adaptable to improve surveillance solution in Smart Cities. [ABSTRACT FROM AUTHOR]

The advent of smart technology in urban environments has often been hailed as the solution to a plethora of contemporary urban challenges, ranging from environmental conservation to waste management and transportation. However, the critical aspect of security, encompassing crime detection and prevention, is frequently overlooked. Moreover, there is a dearth of research exploring the potential disruption of conventional face detection and recognition systems by new smart city surveillance security cameras, particularly those which autonomously update their databases. This paper addresses this gap by proposing the enhancement of security in smart cities through the development of an adaptive Age-Invariant Face Recognition (AIFR) model. A non-intrusive AIFR model was constructed using a convolutional neural network and transfer learning techniques, and was then integrated into surveillance cameras. These cameras, designed to capture the faces of city residents at regular intervals, consequently updated their databases autonomously. Upon testing, the developed model demonstrated its potential to substantially improve security by effectively detecting and identifying the residents and visitors of smart cities, and updating their database profiles. Remarkably, the model retained its effectiveness even with significant age intra-class variation, with the capability to alert relevant authorities about potential criminals or missing individuals. This research underscores the potential of adaptive face recognition systems in bolstering security measures within smart urban environments. [ABSTRACT FROM AUTHOR]

Stationary surveillance cameras deployed around lakes can provide continuous real-time observations of key water areas for harmful algal bloom (HAB). They can be used to supplement remote sensing-based monitoring in situations that satellites cannot handle. While some cameras were initially installed for other purposes, and the poses are not fixed during operation, hence, detecting HABs remains a challenging task due to the diverse surface features present in image frames. A novel three-step machine learning approach was proposed in this paper to address this problem. The acquired images are initially classified using the first model, and images with certain HABs undergo further examination. A second model is employed to generate a water mask, thereby eliminating interferences from non-water features. Finally, the third model is applied to detect and identify HABs specifically within water areas. The experiments showed that the three steps implemented in sequence can effectively extract distinct HABs from RGB images captured under various shooting poses. The overall pixel-level accuracy, intersection over union, and F1 score reached 0.83, 0.76, and 0.76, respectively, on 1969 images from August to September 2020. The novelty of our approach is attributed to that the combination of the three steps can significantly abate the adverse influence of an external environment; thus, the final detection can be performed with satisfactory accuracy. In practice, the approach was applied in Lake Chaohu and consistently reports the real-time status of HABs along the bank. It exhibits substantial potential for the application in eutrophic lakes to avoid HAB-induced secondary disasters.

In the United States, many schools hire police to patrol the grounds and more call upon police to arrest students for violation of school policies. Many of these will be incarcerated within the subsequent five years. The widespread adoption of surveillance cameras, zero tolerance, and police presence in schools has resulted in more students being criminalised. This reflective essay examines the ideology supporting this school-to-prison pipeline. What conception of justice has been responsible for mass incarceration? Why are surveillance cameras, police, and zero tolerance taken to be effective? Why has rehabilitation given way to retribution? Why does the public accept the criminalisation of youth in schools?. [ABSTRACT FROM AUTHOR]

In this article, we examine the installation of surveillance cameras in the Bedouin town of Hura in the Negev desert in Israel, analysing the complex interactions between the state and the local inhabitants, for whom the cameras were an opportunity to exercise agency. Considering the long history of Jewish colonialism in the Negev, one could have assumed that the new surveillance technology was imposed on the Bedouins against their will. However, in‐depth interviews with Hura inhabitants demonstrated that the municipality and tribal authorities were active players in deciding on the installation and location of the surveillance cameras. In light of the conflictual relations of the Bedouin population to Israeli state authorities, we argue that while the cameras placed the Bedouins of Hura under a new layer of surveillance, their installation could also be understood as a reaction to the ongoing neglect of Bedouin lives and possessions by the state. [ABSTRACT FROM AUTHOR]

With recent advances in both AI and IoT capabilities, it is possible than ever to implement surveillance systems that can automatically identify people who might represent a potential security threat to the public in real-time. Imagine a surveillance camera system that can detect various on-body weapons, masked faces, suspicious objects and traffic. This system could transform surveillance cameras from passive sentries into active observers which would help in preventing a possible mass shooting in a school, stadium or mall. In this paper, we present a prototype implementation of such systems, Hawk-Eye, an AI-powered threat detector for smart surveillance cameras. Hawk-Eye can be deployed on centralized servers hosted in the cloud, as well as locally on the surveillance cameras at the network edge. Deploying AI-enabled surveillance applications at the edge enables the initial analysis of the captured images to take place on-site, which reduces the communication overheads and enables swift security actions. At the cloud side, we built a Mask R-CNN model that can detect suspicious objects in an image captured by a camera at the edge. The model can generate a high-quality segmentation mask for each object instance in the image, along with the confidence percentage and classification time. The camera side used a Raspberry Pi 3 device, Intel Neural Compute Stick 2 (NCS 2), and Logitech C920 webcam. At the camera side, we built a CNN model that can consume a stream of images directly from an on-site webcam, classify them, and displays the results to the user via a GUI-friendly interface. A motion detection module is developed to capture images automatically from the video when a new motion is detected. Finally, we evaluated our system using various performance metrics such as classification time and accuracy. Our experimental results showed an average overall prediction accuracy of 94% on our dataset.

Surveillance cameras have been increasingly used in many public and private spaces in recent years to increase the security of those areas. Although many companies still recruit someone to monitor the cameras, the person recruited is more likely to miss some abnormal events in the camera feeds due to human error. Therefore, monitoring surveillance cameras could be a waste of time and energy. On the other hand, many researchers worked on surveillance data and proposed several methods to detect abnormal events automatically. As a result, if any anomalous happens in front of the surveillance cameras, it can be detected immediately. Therefore, we introduced a model for detecting abnormal events in the surveillance camera feed. In this work, we designed a model by implementing a well-known convolutional neural network (ResNet50) for extracting essential features of each frame of our input stream followed by a particular schema of recurrent neural networks (ConvLSTM) for detecting abnormal events in our time-series dataset. Furthermore, in contrast with previous works, which mainly focused on hand-crafted datasets, our dataset took real-time surveillance camera feeds with different subjects and environments. In addition, we classify normal and abnormal events and show the method's ability to find the right category for each anomaly. Therefore, we categorized our data into three main and essential categories: the first groups mainly need firefighting service, while the second and third categories are about thefts and violent behaviour. We implemented the proposed method on the UCF-Crime dataset and achieved 81.71% in AUC, higher than other models like C3D on the same dataset. Our future work focuses on adding an attention layer to the existing model to detect more abnormal events. [ABSTRACT FROM AUTHOR]

Electronic performance monitoring is expanding rapidly in public and private sector environments amidst evidence that when privacy concerns are raised by employees in arbitration and judicial proceedings, there is limited empirical foundation for what constitutes a reasonable expectation of privacy among everyday citizens. This study replicates and expands on Rainie and Duggan's U.S. study of the acceptability of facial recognition-enabled camera surveillance in the workplace with three separate Canadian survey sample populations. We find that private sector workers tolerate cameras in the workplace more than public sector workers and that the younger age cohort, for both private and public sector workers, is more likely to tolerate cameras in the workplace than the older cohort. Further, through analysis of qualitative comments among those ambivalent about camera surveillance at work, we find that concerns over transparency, safety and authoritarianism were the most frequent themes. These results point to the considerations employers must face for surveillance practices to be viewed as reasonable by employees in both public and private sectors. [ABSTRACT FROM AUTHOR]

A substantial increase in the number of surveillance camera systems has not delivered the promised deterrent effects or investigative case evidence and their usefulness has been underwhelming. A potential solution to practical camera monitor needs is computer vision (CV)-enhanced camera networks that can provide automated real-time video analysis, quick processing of monitor query-based searches, and accurate summaries of archived video files. The development and testing of four CV algorithms in computer vision laboratories is presented and implications from their possible adoption by security agencies on society are discussed. [ABSTRACT FROM AUTHOR]

• We propose a CNN-LSTM model for estimating rainfall intensity from video imagery. • By implementing a Bayesian approach, the estimation uncertainty is quantified. • The proposed approach can aid in flood control within urban areas. Accurate, high-resolution spatiotemporal estimates of rainfall intensity (RI) are essential for effective prevention and control of urban flooding. Traditional methods are often costly and provide inadequate coverage. Meanwhile, the associated uncertainty of RI estimates is often overlooked, potentially leading to poor decisions in management of urban floods. Here we examine the potential of video imagery recorded by surveillance cameras in urban areas, for providing real-time estimates of RI. Specifically, we propose the use of Bayesian deep learning (DL) to estimate RI and its related uncertainty in a real-time manner. Our DL approach combines the strengths of convolutional neural network (CNN) and long short-term memory (LSTM) to construct a suitable model for this task, and uses variational inference to quantify the uncertainty of the CNN-LSTM model. The proposed approach is tested using video imagery captured under various light-intensity conditions, including daytime, nighttime, early morning, and early evening, and evaluated via experiments using both random samples and independent rainfall events. Further, we show that the temporal processing provided by the LSTM network is important to achieve good performance of RI estimation. The results indicate the strong potential for leveraging urban camera networks to obtain high-precision spatiotemporal RI estimates at low cost, which can be extremely valuable for implementing effective flood control measures and planning emergency responses in the urban areas. [ABSTRACT FROM AUTHOR]

Video Surveillance (VS) systems are commonly deployed for real-time abnormal event detection and autonomous video analytics. Video captured by surveillance cameras in real-time often contains identifiable personal information, which must be privacy protected, sometimes along with the locations of the surveillance and other sensitive information. Within the Surveillance System, these videos are processed and stored on a variety of devices. The processing and storage heterogeneity of those devices, together with their network requirements, make real-time surveillance systems complex and challenging. This paper proposes a surveillance system, named as Multi-Level Video Security (MuLViS) for privacy-protected cameras. Firstly, a Smart Surveillance Security Ontology (SSSO) is integrated within the MuLViS, with the aim of autonomously selecting the privacy level matching the operating device's hardware specifications and network capabilities. Overall, along with its device-specific security, the system leads to relatively fast indexing and retrieval of surveillance video. Secondly, information within the videos are protected at the times of capturing, streaming, and storage by means of differing encryption levels. An extensive evaluation of the system, through visual inspection and statistical analysis of experimental video results, such as by the Encryption Space Ratio (ESR), has demonstrated the aptness of the security level assignments. The system is suitable for surveillance footage protection, which can be made General Data Protection Regulation (GDPR) compliant, ensuring that lawful data access respects individuals' privacy rights.

From the U.S. to Colombia to China, millions of public surveillance cameras are at the core of crime prevention strategies. Yet, we know little about the effects of surveillance cameras on criminal behavior, especially in developing economies. We study an installation program in Medellín and find that the quasi‐random allocation of cameras led to a decrease in crimes and arrests. With no increase in the monitoring capacity and no chance to use camera footage in prosecution, these results suggest offenders were deterred rather than incapacitated. We test for spillovers and find no evidence of crime displacement or diffusion of benefits to surrounding locations. [ABSTRACT FROM AUTHOR]

The spread of surveillance cameras has necessitated the monitoring of large quantities of surveillance video feeds. A manual monitoring system is near impossible due to the large man‐hour requirements. Recently, automatic abnormal activity detection has been an area of interest among researchers. A spatio‐temporal feature, histogram of optical flow orientation and magnitude (HOFM), has produced impressive ability in detecting abnormal activities. The authors propose a novel non‐uniform spatio‐temporal region resembling parallelepipeds, from which they extract the HOFM features. Autoencoders can be configured to detect abnormal patterns. The authors have used these abilities of the autoencoders to detect abnormalities in the HOFM features extracted from their novel spatio‐temporal regions of the video feeds. The autoencoders are trained on the HOFM features of the videos containing no abnormalities. The autoencoders are then fed with the HOFM features of the videos to be tested for abnormal activities, and these are detected based on the abilities of the autoencoders to reconstruct these features. The proposed method is tested on the standard abnormality detection datasets: UCSD Ped1, UCSD Ped2, Subway Entrance, Subway Exit, and UMN.

This article presents a system for detecting pedestrian movement patterns in urban environments, by applying computational intelligence methods for image processing and pattern detection. The proposed system is capable of processing multiple images and video sources in real-time. Furthermore, it has a flexible design, as it is based on a pipes and filters architecture that makes it easy to evaluate different computational intelligence techniques to address the subproblems involved in each stage of the process. Two main stages are implemented in the proposed system: the first stage is in charge of extracting relevant features of the processed images, by applying image processing and object tracking, and the second stage is responsible for the patterns detection. The experimental analysis of the proposed system was performed over more than 1450 problem instances, using PETS09-S2L1 videos, and the results were compared with part of the Multiple Object Tracking Challenge benchmark results. Experiments covered the two main stages of the system. Results indicate that the proposed system is competitive yet simpler than other similar software methods. Overall, this article provides the theoretical frame and a proof of concept needed for the implementation of a real-time system that takes as input a group of image sequences, extracts relevant features, and detects a set of predefined patterns. The proposed implementation is a reliable proof of the viability of building pedestrian movement pattern detection systems. [ABSTRACT FROM AUTHOR]

We present a method for synopsizing multiple videos captured by a set of surveillance cameras with some overlapped field-of-views. Currently, object-based approaches that directly shift objects along the time axis are already able to compute compact synopsis results for multiple surveillance videos. The challenge is how to present the multiple synopsis results in a more compact and understandable way. Previous approaches show them side by side on the screen, which however is difficult for user to comprehend. In this paper, we solve the problem by joint object-shifting and camera view-switching. Firstly, we synchronize the input videos, and group the same object in different videos together. Then we shift the groups of objects along the time axis to obtain multiple synopsis videos. Instead of showing them simultaneously, we just show one of them at each time, and allow to switch among the views of different synopsis videos. In this view switching way, we obtain just a single synopsis results consisting of content from all the input videos, which is much easier for user to follow and understand. To obtain the best synopsis result, we construct a simultaneous object-shifting and view-switching optimization framework instead of solving them separately. We also present an alternative optimization strategy composed of graph cuts and dynamic programming to solve the unified optimization. Experiments demonstrate that our single synopsis video generated from multiple input videos is compact, complete, and easy to understand. [ABSTRACT FROM AUTHOR]

Surveillance cameras have been increasingly used in many public and private spaces in recent years to increase the security of those areas. Although many companies still recruit someone to monitor the cameras, the person recruited is more likely to miss some abnormal events in the camera feeds due to human error. Therefore, monitoring surveillance cameras could be a waste of time and energy. On the other hand, many researchers worked on surveillance data and proposed several methods to detect abnormal events automatically. As a result, if any anomalous happens in front of the surveillance cameras, it can be detected immediately. Therefore, we introduced a model for detecting abnormal events in the surveillance camera feed. In this work, we designed a model by implementing a well-known convolutional neural network (ResNet50) for extracting essential features of each frame of our input stream followed by a particular schema of recurrent neural networks (ConvLSTM) for detecting abnormal events in our time-series dataset. Furthermore, in contrast with previous works, which mainly focused on hand-crafted datasets, our dataset took real-time surveillance camera feeds with different subjects and environments. In addition, we classify normal and abnormal events and show the method’s ability to find the right category for each anomaly. Therefore, we categorized our data into three main and essential categories: the first groups mainly need firefighting service, while the second and third categories are about thefts and violent behaviour. We implemented the proposed method on the UCF-Crime dataset and achieved 81.71% in AUC, higher than other models like C3D on the same dataset. Our future work focuses on adding an attention layer to the existing model to detect more abnormal events.

This paper presents parallel film recording of sunlight reflection from the same matter, in visual (V) and near infrared (Z) spectrum. We have designed a ZRGB-Motion GoPro video camera for parallel high quality motion recording in dual spectrum. Recorded are two parallel video twins, presenting different information in the grey area. The usage of extended reality in the infrared spectrum could be used in artistic as well as identification purposes. The scenography and costume designs give the technical solution in the making of a parallel motion image. The importance of parallel reproduction of motion images lies in the differences that create a new expanded space in communication design.

Indoor positioning techniques have become very important in recent years. Due to the wide deployment of surveillance cameras, it has become feasible to use the videos for indoor positioning. The success of using this approach can also reduce the load of security persons of watching the monitors all the time. In this study, the authors propose a vision‐based indoor positioning system. The proposed method uses a frame processing technique and applies the Gaussian mixture learning for video background model. The foreground object can be extracted by using the background subtraction. Based on the foreground object, the objects can be tracked and used in the direct linear transform, and generate a bird's‐eye map with camera information. A real‐time demonstration has been also provided. It shows the tracing of the moving objects and the bird's‐eye view. [ABSTRACT FROM AUTHOR]

Surveillance cameras have become a popular response to crime and disorder in urban parks. The literature regarding park surveillance cameras however is sparse and few have examined the impact of park surveillance cameras. This research study examined a five camera police department network in a southern US municipal park. The study measured pre- and post-camera effects on reported crime, calls for service, and park visitor perceptions. Analysis determined that although the surveillance cameras had minimal impact on crime or disorder they were related to park visitor perceptions of the park. A camera surveilled park was seen more positively following police camera installation even though perceptions of the effectiveness of surveillance cameras decreased. [ABSTRACT FROM AUTHOR]

Counting the number of work cycles per unit of time of earthmoving excavators is essential in order to calculate their productivity in earthmoving projects. The existing methods based on computer vision (CV) find it difficult to recognize the work cycles of earthmoving excavators effectively in long video sequences. Even the most advanced sequential pattern-based approach finds recognition difficult because it has to discern many atomic actions with a similar visual appearance. In this paper, we combine atomic actions with a similar visual appearance to build a stretching–bending sequential pattern (SBSP) containing only “Stretching” and “Bending” atomic actions. These two atomic actions are recognized using a deep learning-based single-shot detector (SSD). The intersection over union (IOU) is used to associate atomic actions to recognize the work cycle. In addition, we consider the impact of reality factors (such as driver misoperation) on work cycle recognition, which has been neglected in existing studies. We propose to use the time required to transform “Stretching” to “Bending” in the work cycle to filter out abnormal work cycles caused by driver misoperation. A case study is used to evaluate the proposed method. The results show that SBSP can effectively recognize the work cycles of earthmoving excavators in real time in long video sequences and has the ability to calculate the productivity of earthmoving excavators accurately.

This article presents a system for detecting pedestrian movement patterns in urban environments, by applying computational intelligence methods for image processing and pattern detection. The proposed system is capable of processing multiple images and video sources in real-time. Furthermore, it has a flexible design, as it is based on a pipes and filters architecture that makes it easy to evaluate different computational intelligence techniques to address the subproblems involved in each stage of the process. Two main stages are implemented in the proposed system: the first stage is in charge of extracting relevant features of the processed images, by applying image processing and object tracking, and the second stage is responsible for the patterns detection. The experimental analysis of the proposed system was performed over more than 1450 problem instances, using PETS09-S2L1 videos, and the results were compared with part of the Multiple Object Tracking Challenge benchmark results. Experiments covered the two main stages of the system. Results indicate that the proposed system is competitive yet simpler than other similar software methods. Overall, this article provides the theoretical frame and a proof of concept needed for the implementation of a real-time system that takes as input a group of image sequences, extracts relevant features, and detects a set of predefined patterns. The proposed implementation is a reliable proof of the viability of building pedestrian movement pattern detection systems.

Copyright of Revista Internacional y Comparada de Relaciones Laborales y Derecho del Empleo is the property of ADAPT University Press 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.)

Increasing residents' safety perception is essential for their health and wellbeing, and is of great importance when it comes to neighborhood planning and policy design. Despite the rich body of literature that explores the correlates of perceived neighborhood safety (PNS), the research on the effects of camera-based surveillance technologies on PNS is limited. Most existing studies merely examine the differences in individual perceptions and acceptance of surveillance technologies, but overlook important neighborhood context. Therefore, this study explores how surveillance cameras, as a typical example of camera-based surveillance technologies, can influence PNS and how this influence varies according to neighborhood features or is moderated by other security strategies (i.e., gating). The results show that perceived amounts of surveillance cameras is the most important factor determining PNS and its effect relies on neighborhood characteristics. Increasing the number of surveillance cameras and making them visible to residents may be efficient strategies for improving PNS, however, tailored policies should be formulated by accounting for neighborhood peculiarity. • Perceived amounts of surveillance cameras is the most important factor determining PNS; • The impact of perceived amounts of surveillance cameras on PNS relies on neighborhood characteristics; • Increasing the number of surveillance cameras and making them visible to residents can improve PNS. [ABSTRACT FROM AUTHOR]

The worldwide utilization of surveillance cameras in smart cities has enabled researchers to analyze a gigantic volume of data to ensure automatic monitoring. An enhanced security system in smart cities, schools, hospitals, and other surveillance domains is mandatory for the detection of violent or abnormal activities to avoid any casualties which could cause social, economic, and ecological damages. Automatic detection of violence for quick actions is very significant and can efficiently assist the concerned departments. In this paper, we propose a triple-staged end-to-end deep learning violence detection framework. First, persons are detected in the surveillance video stream using a light-weight convolutional neural network (CNN) model to reduce and overcome the voluminous processing of useless frames. Second, a sequence of 16 frames with detected persons is passed to 3D CNN, where the spatiotemporal features of these sequences are extracted and fed to the Softmax classifier. Furthermore, we optimized the 3D CNN model using an open visual inference and neural networks optimization toolkit developed by Intel, which converts the trained model into intermediate representation and adjusts it for optimal execution at the end platform for the final prediction of violent activity. After detection of a violent activity, an alert is transmitted to the nearest police station or security department to take prompt preventive actions. We found that our proposed method outperforms the existing state-of-the-art methods for different benchmark datasets.

Research on the effectiveness of surveillance cameras in reducing crime suffers from potential threats to causal validity. This paper reviews seven studies that address some of these problems using the rigorous research designs of randomized and natural experiments. Included studies that reported changes in total crime found crime reductions ranging from 24 to 28% in public streets and urban subway stations, but no desirable effects in parking facilities or suburban subway stations. Moreover, surveillance cameras may help reduce unruly behaviour in football stadiums and theft in supermarkets/mass merchant stores. These findings indicate that video surveillance can reduce crime in several settings. [ABSTRACT FROM AUTHOR]

Copyright of URVIO - Revista Latinoamericana de Seguridad Ciudadana is the property of FLACSO - Ecuador (Facultad Latinoamericana de Ciencias Sociales) 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.)

An ear recognition system represents a powerful tool in forensic applications. Even in case the facial characteristic of a suspect is partly or fully covered an image of the outer ear may suffice to reveal a subject's identity. In forensic scenarios imagery may stem from surveillance cameras of environments where image compression is common practice to overcome limitations of storage or transmission capacities. Yet, the impact of severe image compression on ear recognition has remained undocumented. In this work the authors analyse the influence of different state‐of‐the‐art image compression standards on ear detection and ear recognition algorithms. Evaluations conducted on an uncompressed ear database are considered with respect to different stages in the processing chain of an ear recognition system where compression may be applied, representing the most relevant forensic scenarios. Experimental results are discussed in detail highlighting the potential and limitations of automated ear recognition in presence of image compression. [ABSTRACT FROM AUTHOR]

We consider multi-agent scenarios where each agent controls a surveillance camera in the plane, with fixed position and angle of vision, but rotating freely. The agents can thus observe the surroundings and each other. They can also reason about each other's observation abilities and knowledge derived from these observations. We introduce suitable logical languages for reasoning about such scenarios which involve atomic formulae stating what agents can see, multi-agent epistemic operators for individual, distributed and common knowledge, as well as dynamic operators reflecting the ability of cameras to turn around in order to reach positions satisfying formulae in the language. We also consider effects of public announcements. We introduce several different but equivalent versions of the semantics for these languages, discuss their expressiveness and provide translations in PDL style. Using these translations we develop algorithms and obtain complexity results for model checking and satisfiability testing for the basic logic BBL that we introduce here and for some of its extensions. Notably, we show that even for the extension with common knowledge, model checking and satisfiability testing remain in PSPACE. We also discuss the sensitivity of the set of validities to the admissible angles of vision of the agents' cameras. Finally, we discuss some further extensions: adding obstacles, positioning the cameras in 3D or enabling them to change positions. Our work has potential applications to automated reasoning, formal specification and verification of observational abilities and knowledge of multi-robot systems. [ABSTRACT FROM AUTHOR]

Urban mobility is an important part of many studies related to the planning of large urban areas. This paper describes an approach for the evaluation of urban mobility as geosocial dynamics on the territory with high population density on the basis of surveillance cameras. We examine various methods of image and video processing for the evaluation of people flow. As a result, we propose a fast processing and low-cost method for general purpose cameras for the estimation of the number of moving people at a particular point in the city. A case study for some locations in St.Petersburg is considered. [ABSTRACT FROM AUTHOR]

The article offers information on the regulation made under aviation legislation for the recreational use of drones in Sweden, and mentions a Swedish Supreme Administrative Court which ruled that drones equipped with cameras are subject to permission under the Swedish Camera Monitoring Act.

Nowadays, surveillance cameras are widely installed in public places for security and law enforcement, but the video quality may be low because of the limited transmission bandwidth and storage capacity. In this study, the authors proposed a gait recognition method for extremely low‐quality videos, which have a frame‐rate at one frame per second (1 fps) and resolution of 32 × 22 pixels. Different from popular temporal reconstruction‐based methods, the proposed method uses the average gait image (AGI) over the whole sequence as the appearance‐based feature description. Based on the AGI description, the authors employed a large number of weak classifiers to reduce the generalisation errors. The performance can be further improved by incorporating the model‐based information into the classifier ensemble. The authors found that the performance improvement is directly proportional to the average disagreement level of weak classifiers (i.e. diversity), which can be increased by using the model‐based information. The authors evaluated the proposed method on both indoor and outdoor databases (i.e. the low‐quality versions of OU‐ISIR‐D and USF databases), and the results suggest that our method is more general and effective than other state‐of‐the‐art algorithms. [ABSTRACT FROM AUTHOR]