A Review Of Iot-based Surveillance

DOI : 10.17577/ICCIDT2K23-238

Download Full-Text PDF Cite this Publication

Text Only Version

A Review Of Iot-based Surveillance

Keerthana Chandran,

M.Tech. Student, Department of Computer Science,,

Managalam College of Engineering, Kottayam, Kerala.

Abstract : This Review paper describes about the an existing wireless video surveillance system based on the Internet of Things in order to strengthen school security and establish a wireless smart campus. This study first boosts surveillance quality in a video surveillance system and presents a zero-copy buffer technique, a network protocol, and a network protocol.

A congestion suppression approach and a codec rate coordination strategy are both employed. Second, about the distributed

A tracking optimization method based on multi- camera integration is used in a wide area video surveillance system.proposed. Finally, this study develops a Bayesian monitoring event modeling strategy based on genetic information.algorithm. The results from the tests reveal that the improved video surveillance system has a rather consistent delay.Substantially reduced packet loss rate and effortless video playback. This method has the ability of properly realizing the synchronizing the tracking of several cameras over a large area.

INDEX TERMS Internet of Things, smart campus, video surveillance, optimization.

  1. . INTRODUCTION :With the acceleration of higher education institution construction, the campus area is gradually expanding, as is the total amount of mobile employees. Various erratic elements have also posed major obstacles to campus safety management. Video surveillance is an essential instrument for keeping the campus safe. However, there are still many analog and digital hybrid systems used in college and university video surveillance systems that can no longer meet the requirements of the development and construction of new digital campuses and smart campuses.

    The video surveillance system has a long history of development as an important security method, and it has been widely employed in the fields of public safety monitoring, manufacturing process monitoring, and so on. monitoring, as well as monitoring of residential communities.With the advancement of multimedia technology and the progressive development in people's quality expectations of life, video surveillance system research has received tremendous attention. On the one hand, picture development

    processing technology and communication technology level have fueled the advancement of technology Surveillance cameras are used in video surveillance systems. As a result, the technological level of One side has also reacted to video surveillance equipment. image processing technological advancements.

    Sl no.

    Review Paper


    R. Muzaffar, E. Yanmaz,

    C. Raffelsberger, C. Bettstetter, and A. Cavallaro,

    “Live multicast video streaming from drones: An experimental study,'' Auto. Robots, vol. 44, no.

    1, pp. 7591, Apr. 2020.


    J.-Y. Chang, S.-M. Hong,

    D. Son, H. Yoo, and H.-W.

    Ahn, “Development of real-time video

    surveillance system using the intelligent behavior recognition

    technique,'' J. Inst. Internet, Broadcast. Commun., vol. 19, no. 2,

    pp. 161168, Apr. 2019


    L. Ma, “Construction of intelligent building sky- eye system based on multi- camera and speech

    recognition,'' Int. J. Speech Technol., vol. 23, no. 1, pp. 2330, Dec. 2020.


    J. Yang, B. Jiang, Z. Lv, and K.-K.-R. Choo, “A task scheduling algorithm considering game theory designed for energy management in cloud computing,'' Future Gener. Comput. Syst., vol. 105, pp. 985992,

    Apr. 2020


    H. He, G. Liu, X. Zhu, L. He, and G. Tian,

    “Interacting multiple modelbased

    human pose estimation using a distributed 3D



The video surveillance system can carry out a wide range of advanced and powerful activities. The inbuilt video processing module front end examines the monitored image and employs clever algorithms to compare to user-enhanced security model. When a security danger becomes apparent, surveillance begins.The center is swiftly notified. The robust image processing the video processing module's capacity and the robustness Algorithms with intelligence can significantly increase the accuracy of alarm and limit the likelihood of false positives and false negatives negatives. The specifications for video surveillance systems The price tag of video processing modules is very costly as well. It not only has to be finish the video encoding and decoding processes, but also allows for real-time processing of intelligent video so that the system can recognize the algorithm


First, the quality of monitoring in video surveillance Optimized system and zero-copy cache strategy,Strategies to eliminate network bottlenecks and codec speeds A coordinated strategy is proposed.Buffer does not copy This strategy reduces terminal load and improves system performance.the ability to calculate.Eliminate network congestion This strategy effectively reduces the packet loss rate. THE The codec rate matching strategy balances system latency and flucency Aimed at large- scale distributed video surveillance system, a tracking optimization method based on multiple cameras proposed merger. Tracking optimization algorithm performs weighted data merging based on priority of target and its occlusion state in each camera and the size of the segmented image, assigning high priority Target the camera with the best weight for tracking and Automatic load balancing monitoring, assigning low priority The target in the camera has a large tracking load on others cameras for monitoring.

IOT : IoT refers to a loosely coupled system of multiple heterogeneous and homogeneous devices which can sense, process and network.

Figure 1 : System Architecture


    Due to the large differences in structure of different individuals After GA optimization, the detection accuracy of Individual fluctuations are within a small range. So in experiment, we integrate the results after 10 GA optimizations for reference.To reflect improvements in accuracy and durability GA brings the BN- based system in the process optimizer,Figure 13 shows the initial model based on expert knowledge (IMEK notes) and models after GA optimization (recorded to GAOB). We can see that in the worst case scenario, GAOB can still maintain a DR close to 95%.IMEK drops rapidly to about 81%. It means The model after GA optimization has higher robustness and detection accuracy, thanks to GA optimization structure and parameters of the model accordingly and correct areas of incomplete professional knowledge and meet the requirements of smart campus construction.The quality of surveillance video is mainly reflected in performance indexes such as real-time, fluency and clarity.


This article first optimizes the quality of internal monitoring video surveillance system, effectively improve quality of video surveillance and ensures real-time, efficient,and high- definition surveillance video. Monday,for large- scale distributed video surveillance system, one tracking optimization method based on multi- camera fusion proposed to achieve effective combination of goal coherence between multiple cameras. Finally, this article elaborates a Bayesian approach to modeling surveillance- based events genetic algorithm, can reduce the

redundancy of the system, Reduce optimization complexity, increase system modeling flexible and reduces the amount of data needed for optimization.Simulation experiments show the optimal model Video surveillance system can effectively implement cooperation Monitor multiple cameras in wide area surveillance scene, achieving high tracking and monitoring performance, and meet the requirements of smart campus construction.


[1].-Y. Chang, S.-M. Hong, D. Son, H. Yoo, and H.-W. Ahn, “Development

of real-time video surveillance system using the intelligent behavior recognition

technique,'' J. Inst. Internet, Broadcast. Commun., vol. 19, no. 2,

pp. 161 168, Apr. 2019.

[2] T. Tamuhla, L. Joubert, D.Willemse, and M.

J.Williams, “SufT is required

for growth of mycobacterium smegmatis under iron limiting conditions,''

Microbiology, vol. 166, no. 3, pp. 296 305, Mar.


3] V. J. McIver, L. Mattin, G. H. Evans, and A.

M. W. Yau, “The effect

of brisk walking in the fasted versus fed state on metabolic responses,

gastrointestinal function, and appetite in healthy men,'' Int. J. Obesity,

vol. 43, no. 9, pp. 1691 1700, Sep. 2019.

[] R. Sun, J. Qian, R. H. Jose, Z. Gong, R. Miao,

W. Xue, and P. Liu,

“A exible and ef cient real-time ORB-based full-HD image feature

extraction accelerator,'' IEEE Trans. Very Large Scale Integr. (VLSI) Syst.,

vol. 28, no. 2, pp. 565 575, Feb. 2020.

[] R. F. Riley, S. J. Walsh, A. J. Kirtane, R. M. Wyman, W. J. Nicholson,

L. Azzalini, J. C. Spratt, S. Kalra, C. G. Hanratty,

A. Pershad, T. DeMartini,

D. Karmpaliotis, W. L. Lombardi, and J. A.

Grantham, “Algorithmic

solutions to common problems encountered during chronic total occlusion

angioplasty: The algorithms within the algorithm,'' Catheteriza

Z. Zhang and F. Cohen, “3D pedestrian tracking and frontal face image

capture based on head point detection,''

Multimedia Tools Appl., vol. 79, nos. 1 2, pp. 737 764, Sep. 2020.

[7] W. Osamy, A. M. Khedr, A. Salim, and D. P.

Agrawal, “Sensor network

node scheduling for preserving coverage of wireless multimedia

networks,'' IETWireless Sensor Syst., vol. 9, no. 5, pp. 295 305, Oct. 2019.

[8] J. Yang, B. Jiang, Z. Lv, and K.-K.-R. Choo,

“A task scheduling algorithm

considering game theory designed for energy management in cloud computing,''

Future Gener. Comput. Syst., vol. 105, pp. 985 992, Apr. 2020.

[9] M. Quintana, S. Karaoglu, F. Alvarez, J. M. Menendez, and T. Gevers,

“Three-D wide faces (3DWF): Facial landmark detection and 3D reconstruction

over a newRGB D multi-camera dataset,''

Sensors, vol. 19, no. 5,

pp. 1103 1124. Jan. 2019.

[] L. Wang, R. Gao, J. Váncza, J. Krüger, X. V. Wang, S. Makris,

and G. Chryssolouris, “Symbiotic human-robot collaborative assembly,''

CIRP Ann., vol. 68, no. 2, pp. 701 726, Jun.


[11] H. He, G. Liu, X. Zhu, L. He, and G. Tian,

“Interacting multiple modelbased

human pose estimation using a distributed 3D camera network,''

IEEE Sensors J., vol. 19, no. 22, pp. 10584 10590, Jul. 2019.

[12] F. Zhou, “Dynamic tracking algorithm suitable for intelligent video

surveillance,'' J. Comput. Methods Sci. Eng., vol. 19, no. S1, pp. 157 164,

Aug. 2019.