Background Learning with Support Vectors: Efficient Foreground Detection and Tracking for Automated Visual Surveillance

2014 ◽  
pp. 293-316
Keyword(s):  
Visual Surveillance ◽  
Foreground Detection ◽  
Detection And Tracking ◽  
Support Vectors

Automated Object Detection and Tracking for Intelligent Visual Surveillance Based on Sensor Network

2011 ◽  
pp. 1263-1284
Author(s):  
Ruth Aguilar-Ponce ◽  
Ashok Kumar ◽  
J. Luis Tecpanecatl-Xihuitl ◽  
Magdy Bayoumi ◽  
Mark Radle
Keyword(s):  
Wireless Sensor Network ◽  
Object Detection ◽  
Sensor Network ◽  
Tracking System ◽  
Visual Surveillance ◽  
Wireless Sensor ◽  
Surveillance Systems ◽  
Object Detection And Tracking ◽  
Detection And Tracking ◽  
Automated Object Detection

The aim of this research was to apply an agent approach to wireless sensor network in order to construct a distributed, automated scene surveillance. Wireless sensor network using visual nodes is used as a framework for developing a scene understanding system to perform smart surveillance. Current methods of visual surveillance depend on highly train personnel to detect suspicious activity. However, the attention of most individuals degrades after 20 minutes of evaluating monitor-screens. Therefore current surveillance systems are prompt to failure. An automated object detection and tracking was developed in order to build a reliable visual surveillance system. Object detection is performed by means of a background subtraction technique known as Wronskian change detection. After discovery, a multi-agent tracking system tracks and follows the movement of each detected object. The proposed system provides a tool to improve the reliability and decrease the cost related to the personnel dedicated to inspect the monitor-screens

scholarly journals Robust Real Time Multiple Human Detection and Tracking for Automatic Visual Surveillance System

2021 ◽  
Vol 17 ◽  
pp. 93-98
Author(s):  
LAKHYADEEP KONWAR ◽  
ANJAN KUMAR TALUKDAR ◽  
KANDARPA KUMAR SARMA
Keyword(s):  
Particle Filter ◽  
Surveillance System ◽  
Graph Cut ◽  
Visual Surveillance ◽  
Human Detection ◽  
Svm Classifier ◽  
Feature Descriptor ◽  
Tracking Accuracy ◽  
Detection And Tracking ◽  
Automation Systems

Detection of human for visual surveillance system provides most important rule for advancement in the design of future automation systems. Human detection and tracking are important for future automatic visual surveillance system (AVSS). In this paper we have proposed a flexible technique for proper human detection and tracking for the design of AVSS. We used graph cut for segment human as a foreground image by eliminating background, extract some feature points by using HOG, SVM classifier for proper classification and finally we used particle filter for tracking those of detected human. Our system can easily detect and track humans in poor lightening conditions, color, size, shape, and clothing due to the use of HOG feature descriptor and particle filter. We use graph cut based segmentation technique, therefore our system can handle occlusion at about 88%. Due to the use of HOG to extract features our system can properly work in indoor as well as outdoor environments with 97.61% automatic human detection and 92% automatic human detection and tracking accuracy of multiple human

Automated Object Detection and Tracking for Intelligent Visual Surveillance Based on Sensor Network

2011 ◽  
pp. 206-228 ◽  
Author(s):  
Ruth Aguilar-Ponce ◽  
Ashok Kumar ◽  
J. Luis Tecpanecatl-Xihuitl ◽  
Magdy Bayoumi ◽  
Mark Radle
Keyword(s):  
Wireless Sensor Network ◽  
Object Detection ◽  
Sensor Network ◽  
Tracking System ◽  
Visual Surveillance ◽  
Wireless Sensor ◽  
Surveillance Systems ◽  
Object Detection And Tracking ◽  
Detection And Tracking ◽  
Automated Object Detection

The aim of this research was to apply an agent approach to wireless sensor network in order to construct a distributed, automated scene surveillance. Wireless sensor network using visual nodes is used as a framework for developing a scene understanding system to perform smart surveillance. Current methods of visual surveillance depend on highly train personnel to detect suspicious activity. However, the attention of most individuals degrades after 20 minutes of evaluating monitor-screens. Therefore current surveillance systems are prompt to failure. An automated object detection and tracking was developed in order to build a reliable visual surveillance system. Object detection is performed by means of a background subtraction technique known as Wronskian change detection. After discovery, a multi-agent tracking system tracks and follows the movement of each detected object. The proposed system provides a tool to improve the reliability and decrease the cost related to the personnel dedicated to inspect the monitor-screens

scholarly journals Traffic Foreground Detection at Complex Urban Intersections Using a Novel Background Dictionary Learning Model

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Qianxia Cao ◽  
Zhengwu Wang ◽  
Kejun Long
Keyword(s):  
Sparse Representation ◽  
Heavy Traffic ◽  
Urban Traffic ◽  
Detection Methods ◽  
Video Sequences ◽  
Foreground Detection ◽  
Qualitative And Quantitative ◽  
Detection And Tracking ◽  
Vehicle Detection And Tracking ◽  
Slow Moving

In complex urban intersection scenarios, due to heavy traffic and signal control, there are many slow-moving or temporarily stopped vehicles behind the stop lines. At these intersections, it is difficult to extract traffic parameters, such as delay and queue length, based on vehicle detection and tracking due to the dense and severe occlusion of vehicles. In this study, a novel background subtraction algorithm based on sparse representation is proposed to detect the traffic foreground at complex intersections to obtain traffic parameters. By establishing a novel background dictionary update model, the proposed method solves the problem that the background is easily contaminated by slow-moving or temporarily stopped vehicles and therefore cannot obtain the complete traffic foreground. Using the real-world urban traffic videos and the PV video sequences of i -LIDS, we first compare the proposed method with other detection methods based on sparse representation. Then, the proposed method is compared with other commonly used traffic foreground detection models in different urban intersection traffic scenarios. The experimental results show that the proposed method performs well in keeping the background model being unpolluted from slow-moving or temporarily stopped vehicles and has a good performance in both qualitative and quantitative evaluations.

Sign in / Sign up

Export Citation Format

Share Document