scholarly journals Storage Optimization using Adaptive Thresholding Motion Detection

2021 ◽  
Vol 11 (2) ◽  
pp. 6869-6872
Author(s):  
M. Atif ◽  
Z. H. Khand ◽  
S. Khan ◽  
F. Akhtar ◽  
A. Rajput

Data storage is always an issue, especially for video data from CCTV cameras that require huge amounts of storage. Moreover, monitoring past events is a laborious task. This paper proposes a motion detection method that requires fewer calculations and reduces the required data storage up to 70%, as it stores only the informative frames, enabling the security personnel to retrieve the required information more quickly. The proposed method utilized a histogram-based adaptive threshold for motion detection, and therefore it can work in variable luminance conditions. The proposed method can be applied to streamed frames of any CCTV camera to efficiently store and retrieve informative frames.

Author(s):  
John Carlo M. Butil ◽  
Ma Lei Frances Magsisi ◽  
John Hart Pua ◽  
Prince Kevin Se ◽  
Ria Sagum

2020 ◽  
pp. 1-10
Author(s):  
Bryce J. Dietrich

Abstract Although previous scholars have used image data to answer important political science questions, less attention has been paid to video-based measures. In this study, I use motion detection to understand the extent to which members of Congress (MCs) literally cross the aisle, but motion detection can be used to study a wide range of political phenomena, like protests, political speeches, campaign events, or oral arguments. I find not only are Democrats and Republicans less willing to literally cross the aisle, but this behavior is also predictive of future party voting, even when previous party voting is included as a control. However, this is one of the many ways motion detection can be used by social scientists. In this way, the present study is not the end, but the beginning of an important new line of research in which video data is more actively used in social science research.


2015 ◽  
Vol 764-765 ◽  
pp. 740-746
Author(s):  
Hang Yuan ◽  
Chen Lu ◽  
Ze Tao Xiong ◽  
Hong Mei Liu

Fault detection for aileron actuators mainly involves the enhancement of reliability and fault tolerant capability. Considering the complexity of the working conditions of aileron actuators, a fault detection method for an aileron actuator under variable conditions is proposed in this study. A bi-step neural network is utilized for fault detection. The first neural network, which is employed as the observer, is established to monitor the aileron actuator and generate the residual error. The other neural network generates the corresponding adaptive threshold synchronously. Faults are detected by comparing the residual error and the threshold. In considering of the variable conditions, aerodynamic loads are introduced to the bi-step neural network. The training order spectrums are designed. Finally, the effectiveness of the proposed scheme is demonstrated by a simulation model with different faults.


Author(s):  
Jiaping Yu ◽  
Haiwen Chen ◽  
Kui Wu ◽  
Tongqing Zhou ◽  
Zhiping Cai ◽  
...  
Keyword(s):  

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Ruoshui Liu ◽  
Jianghui Liu ◽  
Jingjie Zhang ◽  
Moli Zhang

Cloud computing is a new way of data storage, where users tend to upload video data to cloud servers without redundantly local copies. However, it keeps the data out of users' hands which would conventionally control and manage the data. Therefore, it becomes the key issue on how to ensure the integrity and reliability of the video data stored in the cloud for the provision of video streaming services to end users. This paper details the verification methods for the integrity of video data encrypted using the fully homomorphic crytosystems in the context of cloud computing. Specifically, we apply dynamic operation to video data stored in the cloud with the method of block tags, so that the integrity of the data can be successfully verified. The whole process is based on the analysis of present Remote Data Integrity Checking (RDIC) methods.


2011 ◽  
Vol 480-481 ◽  
pp. 1329-1334
Author(s):  
Wei Zheng ◽  
Zhan Zhong Cui

An effective non-contact electrostatic detection method is used for human body motion detection. Theoretical analysis and pratical experiments are carried out to prove that this method is effective in the field of human body monitoring, in which a model for human body induced potential by stepping has been proposed. Furthermore, experiment results also prove that it’s feasible to measure the average velocity and route of human body motion by multiple electrodes array. What’s more the real-time velocity and direction of human body motion can be determined by orthogonal electrostatic detector array, and the real-time velocity and direction of human body motion can be obtained within the range of 2 meters.


Sign in / Sign up

Export Citation Format

Share Document