scholarly journals A study on implementation of real-time intelligent video surveillance system based on embedded module

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Jin Su Kim ◽  
Min-Gu Kim ◽  
Sung Bum Pan
Keyword(s):  
Real Time ◽  
Video Surveillance ◽  
Surveillance System ◽  
Fire Detection ◽  
Fall Detection ◽  
Video Surveillance System ◽  
Surveillance Systems ◽  
Intelligent Video Surveillance ◽  
Intruder Detection ◽  
Intelligent Video Surveillance System

AbstractConventional surveillance systems for preventing accidents and incidents do not identify 95% thereof after 22 min when one person monitors a plurality of closed circuit televisions (CCTV). To address this issue, while computer-based intelligent video surveillance systems have been studied to notify users of abnormal situations when they happen, it is not commonly used in real environment because of weakness of personal information leaks and high power consumption. To address this issue, intelligent video surveillance systems based on small devices have been studied. This paper suggests implement an intelligent video surveillance system based on embedded modules for intruder detection based on information learning, fire detection based on color and motion information, and loitering and fall detection based on human body motion. Moreover, an algorithm and an embedded module optimization method are applied for real-time processing. The implemented algorithm showed performance of 88.51% for intruder detection, 92.63% for fire detection, 80% for loitering detection and 93.54% for fall detection. The result of comparison before and after optimization about the algorithm processing time showed 50.53% of decrease, implying potential real-time driving of the intelligent image monitoring system based on embedded modules.

Application of Non-Parametric Kernel Density Background Modeling Method in Intelligent Video Surveillance System

2015 ◽  
Vol 799-800 ◽  
pp. 1117-1120
Author(s):  
Ying Zhang ◽  
Meng Xin Li ◽  
Jing Hou
Keyword(s):  
Real Time ◽  
Video Surveillance ◽  
Surveillance System ◽  
Kernel Density ◽  
Low Noise ◽  
Video Surveillance System ◽  
Intelligent Video Surveillance ◽  
Time Performance ◽  
Intelligent Video Surveillance System ◽  
Non Parametric

Aiming to get better real time performance and effect of detection in dynamic scene of intelligent video surveillance system, non-parametric kernel density estimation (KDE) is used to model the background. And to solve the foreground detection is not precise enough, background subtraction method is fused to detect the foreground. And some modified work is done to suppress shadow and noise. Experiments show that the method proposed can get better real time performance and low noise detect result in intelligent video surveillance system.

Intelligent Video Surveillance System Based on Sound Source Localization Technology

2014 ◽  
Vol 511-512 ◽  
pp. 530-535 ◽  
Author(s):  
Ya Zhang ◽  
Cang Rong Zhao ◽  
Lai Gong Guo
Keyword(s):  
Video Surveillance ◽  
Source Localization ◽  
Sound Source ◽  
Surveillance System ◽  
Microphone Array ◽  
Sound Source Localization ◽  
Video Surveillance System ◽  
Surveillance Systems ◽  
Intelligent Video Surveillance ◽  
Intelligent Video Surveillance System

Since most of the current video surveillance systems are static or dynamic track based on video detection, the paper puts forward the scheme of sound source localization and camera dynamic acquisition in the intelligent video surveillance system. The microphone array is used to locate the sound source, then the camera is steered to monitor sound source position and alarm is executed by image analysis. The experimental results show that the system can achieve effective positioning of the sound source and alarm at abnormal condition under a low-niose environment.

scholarly journals A deep learning approach to building an intelligent video surveillance system

2020 ◽  
Author(s):  
Jie Xu
Keyword(s):  
Face Recognition ◽  
Object Detection ◽  
Video Surveillance ◽  
Surveillance System ◽  
Video Surveillance System ◽  
Surveillance Systems ◽  
Single Shot ◽  
Convolutional Networks ◽  
Starting Point ◽  
Intelligent Video Surveillance System

Abstract Recent advances in the field of object detection and face recognition have made it possible to develop practical video surveillance systems with embedded object detection and face recognition functionalities that are accurate and fast enough for commercial uses. In this paper, we compare some of the latest approaches to object detection and face recognition and provide reasons why they may or may not be amongst the best to be used in video surveillance applications in terms of both accuracy and speed. It is discovered that Faster R-CNN with Inception ResNet V2 is able to achieve some of the best accuracies while maintaining real-time rates. Single Shot Detector (SSD) with MobileNet, on the other hand, is incredibly fast and still accurate enough for most applications. As for face recognition, FaceNet with Multi-task Cascaded Convolutional Networks (MTCNN) achieves higher accuracy than advances such as DeepFace and DeepID2+ while being faster. An end-to-end video surveillance system is also proposed which could be used as a starting point for more complex systems. Various experiments have also been attempted on trained models with observations explained in detail. We finish by discussing video object detection and video salient object detection approaches which could potentially be used as future improvements to the proposed system.

Sign in / Sign up

Export Citation Format

Share Document