Video Monitoring Research Articles

Lyapunov-Guided Energy Scheduling and Computation Offloading for Solar-Powered WSN

To satisfy the continuously high energy consumption and high computational capacity requirements for IoT applications, such as video monitoring, we integrate solar harvesting and multi-access edge computing (MEC) technologies to develop a solar-powered MEC system. Considering the stochastic nature of solar arrivals and channel conditions, we formulate a stochastic optimization problem to maximize network energy efficiency under the constraints of energy queue stability, task queue stability, peak transmission power, and maximum CPU frequency of each sensor. To solve the long-term stochastic optimization problem, we propose a Lyapunov-based online joint computational offloading and resource scheduling optimization algorithm, transforming the long-term stochastic problem into a series of deterministic subproblems in each time slot. Simulation results show that the proposed algorithm can find the optimal solution to tradeoff long-term energy efficiency and queueing backlog without requiring a priori knowledge of the channel state and energy arrival, which is a more realistic solution for practical solar-powered MEC systems.

Chemical composition and anticonvulsant activities of herb pair of Gastrodia elata Blume-Acorus tatarinowii Schott decoction on experimentally induced seizures in mice.

Epilepsy is a serious public health problem in the world. At present, over 30% of affected patients remain refractory to currently available treatment. Medicinal plants as pharmaceuticals and healthcare treatments have been frequently used in the management of epilepsy in China for many centuries. Gastrodia elata-Acous tatarinowii (GEAT), as a classic and most commonly used herb pair in traditional Chinese medicine (TCM), has been employed to control seizures for thousands of years. However, the animal experiment data on its anticonvulsant effect is limited in the literature. Thus, this study aimed to reveal the therapeutic actions of GEAT decoction against seizures in mice. UHPLC-MS/MS was performed to analyze the chemical components of GEAT decoction. The mice were given GEAT decoction for 7days, and MES, PTZ, and 3-MP injection was given 30min after the last administration. Video monitoring was performed for comparisons. In addition, the PTZ-induced kindling models were conducted to investigate the seizure severity, anxiety and cognitive profile, inflammation, and oxidative stress parameters in mice. The results showed that GEAT decoction dose-dependently protected mice against MES, 3-MP, and PTZ-induced acute seizures. Furthermore, GEAT decoction significantly ameliorated seizure severity, decreased the accumulation of inflammatory mediators TNF-α, IL-1β, and IL-6, mitigated oxidative stress, as well as alleviated anxious-like behavior and cognitive deficits in PTZ-kindled mice. These results suggest that GEAT decoction possesses certain anticonvulsant properties, which might be clinically useful as phytotherapy alone or as an adjunct therapy for the prevention and treatment of seizures and epilepsy.

Adaptive GW Relocation and Strategic Flow Rerouting for Heterogeneous Drone Swarms

A drone swarm is a robotic architecture having multiple drones cooperate to accomplish a mission. Nowadays, heterogeneous drone swarms, in which a small number of gateway drones (GWs) act as protocol translators to enable the mixing of multiple swarms that use independent wireless protocols, have attracted much attention from many researchers. Our previous work proposed Path Optimizer — a method to minimize the number of end-to-end path-hops in a remote video monitoring system using heterogeneous drone swarms by autonomously relocating GWs to create a shortcut in the network for each communication request. However, Path Optimizer has limitations in improving communication quality when more video sessions than the number of GWs are requested simultaneously. Path Coordinator, which we propose in this paper, achieves a uniform reduction in end-to-end hops and maximizes the allowable hop satisfaction rate regardless of the number of sessions by introducing the cooperative and synchronous relocation of all GWs. Path Coordinator consists of two phases: first, physical optimization is performed by geographically relocating all GWs (relocation phase), and then logical optimization is achieved by modifying the relaying GWs of each video flow (rerouting phase). Computer simulations reveal that Path Coordinator adapts to various environments and performs as well as we expected. Furthermore, its performance is comparable to the upper limits possible with brute-force search.

Research on Transformer Equipment Identification Based on Improved Fast RCNN Algorithm

Because of the problems such as the long work cycle and manual efficiency faced by the traditional manual inspection and video monitoring inspection methods of substations, this paper proposes an electrical equipment identification algorithm that improves the Fast RCNN network to realize automatic identification and positioning of electrical equipment. We used affine transformation, background fusion, hue and saturation change, clipping and filling methods to enrich images and change the feature extraction network from VGG16 to ResNet50 with residual structure so that the feature extraction network can focus on specific anchor frames, and then used K-means clustering algorithm in the regional recommendation network to increase the convergence speed of the model, in this way, the improved anchoring height-to-width ratio is more suitable for detecting the image of power equipment. The experimental simulation shows that the average detection accuracy of the improved model is better than that of the original model, with the average accuracy mAP reaching 90.04%, and the image detection speed reaching 11 frames/second.

Development of video control system training stand

The article focuses on the process of teaching students technical aspects of video surveillance systems in the course "Technical Means of Security". The main attention is paid to the methods of developing professional competencies related to installation and configuration of equipment, mastering video surveillance software and mastering the application of facial recognition technologies. The article describes laboratory work in detail, starting from the theoretical basis laid at the beginning of the course to practical skills such as connecting cameras, configuring programs and creating databases for identifying individuals. The learning process includes preparation and analysis of theoretical material, performance of laboratory works, as well as testing and evaluation of the obtained results. The result is to provide learners with a comprehensive understanding of video surveillance systems and practical skills relevant for their future careers in security and use in everyday life. The research methodology in the article combines theoretical learning and practical laboratory work. It includes the steps of connecting video monitoring cameras, configuring software and facial recognition algorithms. Students gained experience with real equipment and programs, which contributed to deep learning of the material and development of practical skills. The scientific novelty of this article lies in the integrated approach to teaching students how to use video surveillance systems, including technical aspects of connecting the equipment, configuring software and face recognition algorithms. This approach provides not only theoretical training, but also practical mastery of skills, which is innovative in the context of security technology education programs. The findings of the article emphasize the importance of practical training in student learning. It is shown that real-life experience with equipment and programs significantly improves the quality of education and readiness of students for future professional activities. The article emphasizes that modern education in the field of security systems requires the integration of theoretical knowledge and practical skills, thus providing comprehensive training of specialists in this important and relevant field.

Evaluation method of the turbine impeller imbalance based on the headroom analysis

Impeller imbalance is an unavoidable problem in the process of the operation of wind turbines, and it often has a serious impact on the safety and stability of wind turbines, thus shortening their life cycle. Aiming at the current problems, such as high cost and instability caused by the impeller imbalance in wind turbines, this paper proposes an assessment method for impeller imbalance in wind turbines based on image processing and headroom analysis. Firstly, the deep-learning image-processing technology is used to convert the video monitoring data into numerical data, and then the comprehensive imbalance index of the three blades based on the numerical data is calculated, so as to determine if an impeller imbalance problem exists or not. The proposed method was validated with the operation data of wind turbines in field and good results were achieved.

Driver alertness monitoring system in the context of safety increasing and sustainable energy use

Road transport is an important factor in carbon dioxide emissions. These emissions can be reduced by improving propulsion sources and traffic flow (avoiding traffic jams due to accidents). This article presents a system for monitoring and warning the driver to prevent a possible accident involving material damage, injury, or loss of life. The system performs video monitoring of the driver in order to determine his state (tired or attentive). By reducing traffic incidents and traffic jams, the energy consumed will not be wasted; thus, more sustainable transport energy use can be achieved.

Research on Automatic Patrol Inspection Technology Scheme for Safe Operation of Super Long and Long Span Highway Tunnel

Firstly, this paper conducts systematic research on tunnel fire and traffic incident detection technologies, and develops a high-precision monitoring and detection implementation plan for ultra-long and large-span tunnels; Secondly, in terms of tunnel fire detection, video thermal imaging technology is used as the main detection method, combined with dual wavelength flame detectors, to achieve fire open fire monitoring and pure smoke detection, making up for the blind spots of traditional fire detection, and improving the accuracy, timeliness, and reliability of monitoring. In terms of traffic incident detection, based on traditional traffic incident detection technology and advanced technical means, the system mainly focuses on lightning visual integration detection, combined with artificial video monitoring, to comprehensively judge the status of tunnel traffic incidents, thereby reducing the false alarm rate of incident detection. Finally, based on the technical research scheme, an intelligent automatic patrol robot was developed using the mobile automatic patrol mode. Using this as a carrier, various sensor modules and emergency equipment were built to replace manual 24-hour uninterrupted full coverage patrols, achieving automatic patrol, automatic reporting, analysis, early warning, and emergency response for ultra-long tunnels, reducing the cost of manual patrols and improving the efficiency of patrols, Enhanced emergency response capabilities of operating units.

PEDESTRIAN DETECTION AND TRACKING OF THEIR MOVEMENT TRAJECTORY USING THE BACKGROUND SEGMENTATION METHOD BASED ON KNN

Problem statement. Target detection and video image tracking is one of the important topics of computer vision, as well as a problem that needs to be urgently addressed in practical applications. Interference makes it difficult to get the target position. Faced with this problem, scientists have proposed many tracking algorithms. Purpose. In real video monitoring, the system can automatically detect the foreground and draw the trajectory of the foreground. Methods. Use the KNN background segmenting algorithm in combination with OpenCV to detect the foreground and track the trajectory of the video. Novelty. It can continuously detect the foreground in the video and is also applicable to the new foreground in the video. This method is easy to call, does not require the use of a large amount of computer performance resources and can achieve real-time detection and tracking. Result. In a real test, we got good test results, we successfully identified moving pedestrians on video and drew their trajectories. Practical relevance. The algorithm can be applied to road traffic, can determine the trajectory of a vehicle to track vehicles, and can also be used to detect pedestrians to pave the way for subsequent recognition of pedestrian behavior.

Railroad Crossing Surveillance and Foreground Extraction Network: Weakly Supervised Artificial-Intelligence Approach

According to the report to Congress National Strategy to Prevent Trespassing on Railroad Property issued by the Federal Railroad Administration, trespassing is currently the number one cause of all railroad-related deaths. The number of fatalities resulting from trespassing, including both illegally entering and remaining in the railroad right-of-way, is even higher than the number of deaths caused by collisions between vehicles and trains. Accurately and effectively detecting objects at rail crossings is critical for improving railway safety. The convolutional neural network (CNN) is one of the most potent tools in image processing and video surveillance. However, the current CNNs under supervised learning rely on a substantial amount of manually labeled images, which is labor-intensive and time-consuming. This study proposes a weakly supervised learning technique for training foreground-segmentation networks and develops a tailored CNN network, RC-SAFE (railroad crossing surveillance and foreground extraction), to accurately and effectively detect and track both still and moving objects in the railroad crossing area. The weakly supervised learning significantly reduces the load for image labeling. The experimental results on the public CDnet 2014 dataset show that the weakly supervised network outperforms the supervised network and some other state-of-the-art foreground-segmentation methods. Railroad crossing monitoring videos are collected at different railroad crossings to validate the proposed RC-SAFE network. The results confirm the robustness of the proposed RC-SAFE network, and that RC-SAFE can detect any object that does not belong to the railroad crossing, which outperforms object-detection-based models, such as Mask RCNN (a region-based CNN).

Sample Reduction-Based Pairwise Linear Regression Classification for IoT Monitoring Systems

At present, the development of the Internet of Things (IoT) has become a significant symbol of the information age. As an important research branch of it, IoT-based video monitoring systems have achieved rapid developments in recent years. However, the mode of front-end data collection, back-end data storage and analysis adopted by traditional monitoring systems cannot meet the requirements of real-time security. The currently widely used edge computing-based monitoring system can effectively solve the above problems, but it has high requirements for the intelligent algorithms that will be deployed at the edge end (front-end). To meet the requirements, that is, to obtain a lightweight, fast and accurate video face-recognition method, this paper proposes a novel, set-based, video face-recognition framework, called sample reduction-based pairwise linear regression classification (SRbPLRC), which contains divide SRbPLRC (DSRbPLRC), anchor point SRbPLRC (APSRbPLRC), and attention anchor point SRbPLRC (AAPSRbPLRC) methods. Extensive experiments on some popular video face-recognition databases demonstrate that the performance of proposed algorithms is better than that of several state-of-the-art classifiers. Therefore, our proposed methods can effectively meet the real-time and security requirements of IoT monitoring systems.

A Social Distance Monitoring Method Based on Improved YOLOv4 for Surveillance Videos

Social distance monitoring is of great significance for public health in the era of COVID-19 pandemic. However, existing monitoring methods cannot effectively detect social distance in terms of efficiency, accuracy, and robustness. In this paper, we proposed a social distance monitoring method based on an improved YOLOv4 algorithm. Specifically, our method constructs and pre-processes a dataset. Afterwards, our method screens the valid samples and improves the K-means clustering algorithm based on the IoU distance. Then, our method detects the target pedestrians using a trained improved YOLOv4 algorithm and gets the pedestrian target detection frame location information. Finally, our method defines the observation depth parameters, generates the 3D feature space, and clusters the offending aggregation groups based on the L2 parametric distance to finally realize the pedestrian social distance monitoring of 2D video. Experiments show that the proposed social distance monitoring method based on improved YOLOv4 can accurately detect pedestrian target locations in video images, where the pre-processing operation and improved K-means algorithm can improve the pedestrian target detection accuracy. Our method can cluster the offending groups without going through calibration mapping transformation to realize the pedestrian social distance monitoring of 2D videos.

An Automated Hardware-Software Module Monitoring Acheta Domesticus Population at Breeding Facilities

The growing population on planet Earth and the deteriorating environment are leading humanity to a swift depletion of resources. And if it is possible to reduce the use of some, it is impossible to eliminate, or even decrease the consumption of protein. Thus, an alternative solution needs to be found. For the past several decades scholars have suggested to breeding crickets as an alternative source of protein. Numerous studies have been made, which resulted in a simple description of the process and a manual of how to establish a breeding cricket farm. However, the fluctuations in breeding conditions stemming from the lack of automation in this sphere, are a hazard to the safe growth and development of the cricket breeding stock. This paper focuses on the developed prototype of a video monitoring equipment developed using machine learning technologies aiming to help identifying hazardous conditions based on the training received in the process of the experiment and numerous tests. The prototype has shown a 70% accuracy rate, yet is capable of determining when the crickets are subjected to various stressors, namely water, nutrition, thermal and methane. Via observing the cricket population, the prototype is learning to alert the breeder as to the potential danger, thereby preserving the cricket population, and increasing the chances of a future mass production of protein from crickets.

Random matrix-based laser speckle contrast imaging enables quasi-3D blood flow imaging in laparoscopic surgery.

Laser speckle contrast imaging (LSCI) provides full-field and label-free imaging of blood flow and tissue perfusion. It has emerged in the clinical environment, including the surgical microscope and endoscope. Although traditional LSCI has been improved in resolution and SNR, there are still challenges in clinical translations. In this study, we applied a random matrix description for the statistical separation of single and multiple scattering components in LSCI using a dual-sensor laparoscopy. Both in-vitro tissue phantom and in-vivo rat experiments were performed to test the new laparoscopy in the laboratory environment. This random matrix-based LSCI (rmLSCI) provides the blood flow and tissue perfusion in superficial and deeper tissue respectively, which is particularly useful in intraoperative laparoscopic surgery. The new laparoscopy provides the rmLSCI contrast images and white light video monitoring simultaneously. Pre-clinical swine experiment was also performed to demonstrate the quasi-3D reconstruction of the rmLSCI method. The quasi-3D ability of the rmLSCI method shows more potential in other clinical diagnostics and therapies using gastroscopy, colonoscopy, surgical microscope, etc.

Multiple vehicles tracking and detection using weight high order singular value decomposition dimensionality reduction and double classifiers

Controlling and managing city traffic is one of them. In order to use image processing to prevent accidents on the road, vehicle tracking and detection are essential. By following moving objects, surveillance video monitoring and human activity recording are carried out. By taking this into account, a useful technique for image processing that detects automobiles from the image is suggested. For numerous vehicle tracking and detection systems, the ECNN-SVM (Enhanced Convolution Neural Network with Support Vector Machine) has just been introduced. However, the larger dimensional data space and inaccurate edge recognition make this system’s performance difficult. The WHOSVD (Weight High Order Singular Value Decomposition) approach, which reduces the dimension and breaks up the positive and negative training picture samples, is established to improve training speed and visual vehicle recognition. To effectively identify the edges at corners, improved canny edge detection is used for edge detection. Mean Kernel Fuzzy C Means (MKFCM) clustering algorithm-based three-dimensional bounding box estimation is used to identify the vehicle items. By merging the feature value of samples with their class labels, the Speed Factor Based Cuckoo Search Algorithm (SFCSA) is introduced for feature selection. The WHOSVD algorithm was used as the input for the enhanced convolutional neural network (ECNN), which is introduced for low-dimensional space and is used for vehicle detection and tracking. Occlusion problems are resolved and target features are further identified using a machine learning classifier. For common algorithms like CNN+SVM, Support Vector Machine (SVM), and the proposed technique, experimentation is done in regards to the metrics of accuracy, f-measure, precision, and recall for performance evaluation.

Visual attention framework for identifying semantic information from construction monitoring video

Construction safety management has been extensively investigated. Construction cameras have been widely adopted to monitor people’s performance in construction on-site. However, manually analyzing large quantities of video or image data is time-consuming and labor-intensive. Existing studies mostly focus on single element identification in videos or images, while the deeper semantic understanding of construction scenes with the whole scene is limited. Drawing on the attention mechanism, a framework is proposed to address this problem and identify semantic information such as multiple objects, relationships, and attributes from construction videos. This framework comprises the following two-step modeling approach: (1) a frame extraction model with an interframe difference mechanism is proposed to extract frames/images from construction videos and (2) an image scene understanding model that integrates a ResNet101 “encoder” and an LSTM + Attention “decoder” is put forward to identify semantic information/natural language descriptions from frames/images. Finally, the proposed framework is validated by multiple experiments with offline image datasets of construction scenes. The contributions of this research are twofold: (1) The proposed visual attention framework represents a significant and data-driven advancement in the cross-modal processing of construction video-image-natural language descriptions; (2) The automatic generation of video semantic information facilitates construction safety management such as workers’ safety state estimation and monitoring video/image retrieval and storage.

Characteristics of Multi-Stage Auxiliary Equipment Linkage in Pumped Storage Power Station Under Double Carbon Target

The auxiliary control linkage system of the pumped storage power station has become a necessary technical means for the safe operation and production of the station. However, due to the scattered linkage control function and low control level of each subsystem of the pumped storage power station, the security system cannot play a full role, affecting the safety portion and other effects. This paper studies a multistage auxiliary equipment linkage method based on a linkage body for the pumped storage power station. In the framework of the system dividing safety intervals, five linkage bodies are constructed for multi-layer hierarchical linkage, including real-time monitoring, fire fighting, five-prevention locking, online monitoring, and video monitoring. Completing the development of the linkage method of auxiliary equipment comprehensive control based on a multi-level linkage strategy and implementing multi-stage auxiliary equipment linkage in the station can reduce the loss of auxiliary equipment in pumped storage stations and improve the carbon neutrality and carbon compliance benefit of the pumped storage stations.

Detection Method of River Floating Objects based on Edge Computing

For the detection of objects floating in the river, most of the traditional intelligent video monitoring methods are used to monitor through manual viewing. During the traditional video data transmission and processing, the massive amount of data will put pressure on the background such as network and computing power. The new effective method is to crop and optimize YOLOV5s, add a specific image pre-processing module, and deploy it by edge computing, embed a SOC (System on Chip) chip in the web camera for real-time processing of video data. Simulation experiments prove that the above method can improve the accuracy and speed of the target detection network.

Vehicle Information Acquisition and Communication System Based on Multi-Satellite Fusion, CAN Bus and GPS

This paper proposes a GPS and GPRS-based multifunctional vehicle terminal design scheme, which uses an embedded platform based on S3C2440 (bit 23 microprocessor of ARM920T core) and operating system, expands GPS navigation module and GPRS module, video surveillance The module integrates the CAN bus interface to realize vehicle navigation, wireless Internet access, CAN bus communication, and video monitoring functions, and fully meets people's requirements for car safety, convenience and comfort. The GPRS navigation module selects the JP13 receiver, and completes the related hardware circuit design. The navigation system adopts navigation software design based on the eSuperMap platform, which can realize electronic map display and operation, satellite positioning information display, path analysis, navigation and other functions.

Design and Implementation of Home Video Surveillance Systems Based on IoT Location Service

Due to its simplicity, directness, and rich content, home video surveillance has gradually become the core content of the smart home security system. The rapid development of computer technology, the internet, video image processing, and transmission technology, as well as the emergence of “wireless cities,” have continuously expanded the coverage of wireless internet such as 5G and WiFi and greatly changed data processing methods and transmission speeds. Video surveillance has also gradually developed from traditional wired networking to mobile video surveillance of wireless networks. Therefore, this paper will focus on the design of the home video monitoring system based on the IoT location service. The system combines traditional network video surveillance with intelligent mobile terminals, which can meet the needs of users for video surveillance of home conditions at any location and at any time. And it compared the sensitivity, accuracy, capture time interval, and energy consumption of the two by comparing with traditional internet video surveillance.