Cost-Effective Security Support in Real-Time Video Surveillance

Puvvadi, Udaya; Benedetto, Kevin Di; Patil, Aditya; Kang, Kyoung-Don; Park, Young-Joon

doi:10.1109/tii.2015.2491259

Cited by 29 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…V IDEO Surveillance (VS) technology has become a fundamental tool for the public and private sector security, such as traffic monitoring, indoor monitoring, and crime and violence detection [1][2][3]. Edge Artificial Intelligence (EAI) is a promising technology that combines Artificial Intelligence (AI), Internet of Things (IoT), and Edge Computing (EC) technologies [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing

Chen

Deng

et al. 2024

IEEE Trans. Ind. Inf.

181

View full text Add to dashboard Cite

In this paper, we propose a Distributed Intelligent Video Surveillance (DIVS) system using Deep Learning (DL) algorithms and deploy it in an edge computing environment. We establish a multi-layer edge computing architecture and a distributed DL training model for the DIVS system. The DIVS system can migrate computing workloads from the network center to network edges to reduce huge network communication overhead and provide low-latency and accurate video analysis solutions. We implement the proposed DIVS system and address the problems of parallel training, model synchronization, and workload balancing. Task-level parallel and model-level parallel training methods are proposed to further accelerate the video analysis process. In addition, we propose a model parameter updating method to achieve model synchronization of the global DL model in a distributed EC environment. Moreover, a dynamic data migration approach is proposed to address the imbalance of workload and computational power of edge nodes. Experimental results showed that the EC architecture can provide elastic and scalable computing power, and the proposed DIVS system can efficiently handle video surveillance and analysis tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing

Chen

Deng

et al. 2024

IEEE Trans. Ind. Inf.

181

View full text Add to dashboard Cite

show abstract

“…In user authentication, verification of persons' identity is performed to provide a customized experience or grant permission to access a specific set of resources or data in a particular system (semi-controlled environment, e.g., inspection lane, chokepoint entry, home or office access control), whereas in security surveillance the detection of individuals of interest is performed for enhanced security and situational awareness in major events (un-controlled environment, e.g., airport or casino) [1]. Though in both applications, many different physiological and behavioral biometrics may be used, the facial biometric has become more popular for its non-intrusive nature, cost effectiveness, and easiness of collecting with the available devices, like cameras.…”

Section: Introductionmentioning

confidence: 99%

“…Though in both applications, many different physiological and behavioral biometrics may be used, the facial biometric has become more popular for its non-intrusive nature, cost effectiveness, and easiness of collecting with the available devices, like cameras. However, after three decades of intense research, the state-of-the-art face recognition approaches can achieve high recognition rate under only controlled settings (verification), whereas the semi-and un-controlled environments still remain challenging [1].…”

Section: Introductionmentioning

confidence: 99%

“…In still-to-video face recognition, most of the reported techniques rely heavily on the size and representativeness of the training data in the WL gallery, and most of them suffer serious performance drop or even fail to work if only one/few training samples per target person is available for generating the face models. 1 The most challenging is the Single Sample Face Recognition (SSFR) problem, where a single training face image for a target individual is given for face modeling, and the person is to be identified later in time, in many different and unpredictable poses, lighting, etc. [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Approach to Improving Single Sample Face Recognition Using High Confident Tracking Trajectories

Dewan

Qiao

Lin

et al. 2016

Advances in Artificial Intelligence

View full text Add to dashboard Cite

Abstract. In this paper, single sample face recognition (SSFR) problem is addressed by introducing an adaptive biometric system within a modular architecture where one detector per target individual is proposed. For each detector, a face model is generated with the gallery face image and updated overtime. Sequential Karhunen-Loeve technique is applied to update the face model using representative face captures which are selected from the operational data by using reliable tracking trajectories. This process helps to induce intra-class variation of face appearance and improve representativeness of the face models. The effectiveness of the proposed method is detailed in security surveillance and user authentication using Chokepoint and FIA datasets in SSFR setting.

show abstract

“…Currently, video surveillance systems are becoming more cost-effective, light-weight and convenient with better frame resolution. Also, the safety of captured visual data is getting better protection when transferred on-line [98]. We can access to surveillance cameras from smartphones to check real-time video stream remotely or look up for the previous event of interest from the stored database.…”

Section: Albert Einstein 1879 -1955mentioning

confidence: 99%

Exploring the frontier of smart video surveillance: novel domains and fine-grain event understanding

Zhang¹

View full text Add to dashboard Cite

Video surveillance plays an important role in our times. It is a great help in reducing the crime rate, and it can also help monitoring the status of facilities or animals. The contribution video surveillance is significant especially regarding the public and home safety.However, the performance of video surveillance system is limited by human factors such as fatigue, time efficiency, and human resources. It would be beneficial for all if fully automatic video surveillance systems are employed to do the job. With this aim, many commercial products and research prototypes have been developed for the automation of video surveillance. Although progress has been made, the performance and ability of the emerging automatic surveillance systems are still not satisfying regarding two major unsolved problems: 1) The ability to work in multiple domains; 2)The ability to understand and describe the events like the human.On the one hand, special domains such as the thermal camera or hidden camera in the wild forest are seldom considered today. We can develop great potential usage for these novel domains. For example, we can catch the thief even if the light is turned off at night with a thermal face recognition surveillance system. We can also study surveillance system with wildlife without worrying about privacy issues with the human. And surveillance in wildlife domain is a great help to zoologists and biologists. In a short word, the ability to work under different circumstances is an important sign of an advanced surveillance system and it can have numerous benefits.On the other hand, existing surveillance systems lack the event understanding and description ability. For example, current commercialised smart surveillance systems can only detect motion changes or human faces. They are far away from the ideal system that can understand the meaning of the motion in the perspective of events. Even the research prototypes which have the abilities of event recognition and anomaly detection are not able to deal with unseen events or understand relationships between roles in an event. For instance, when the detector of the smart surveillance system detected keywords "person", "baby" and "feed", we do not want the system to report "a person feeding a baby" when the actual screen is a scene where the baby is trying to share the food.This thesis aims to explore the frontier of smart video surveillance systems by investigating the above-mentioned two problems. In this thesis, several methods are proposed to study video surveillance in various domains such as crowded scene domain, and more importantly, in novel domains that are barely investigated such as thermal imaging and wildlife domain. Also, novel methods of event analysis and video description are proposed to enhance the efficiency of human-machine interaction.All the methods are connected in the scope of smart video surveillance framework. With the novel directions, three new datasets are built in this thesis as well. Enhancing the smart video surveillance system wit...

show abstract

Cost-Effective Security Support in Real-Time Video Surveillance

Cited by 29 publications

References 10 publications

Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing

Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing

An Approach to Improving Single Sample Face Recognition Using High Confident Tracking Trajectories

Exploring the frontier of smart video surveillance: novel domains and fine-grain event understanding

Contact Info

Product

Resources

About