Person Detection, Re-identification and Tracking Using Spatio-Color-based Model for Non-Overlapping Multi-Camera Surveillance Systems

Author(s):  
Farah Jahan
Author(s):  
Suneung Kim ◽  
Myeongseob Ko ◽  
Kyungchai Lee ◽  
Mingi Kim ◽  
Kwangtaek Kim

2012 ◽  
Vol 14 (3) ◽  
pp. 555-562 ◽  
Author(s):  
M. Saini ◽  
Xiangyu Wang ◽  
P. K. Atrey ◽  
M. Kankanhalli

2013 ◽  
Vol 1 (1) ◽  
pp. 11-19
Author(s):  
H.H. Weerasena ◽  
P. B. S. Bandara ◽  
J.R.B. Kulasekara ◽  
B. M. B. Dassanayake ◽  
U. A. A. Niroshika ◽  
...  

Today, automated camera surveillance systems play a major role in securing public and private premises to ensure security and to reduce crime by detecting behavioral changes of moving objects. The important goal of such a surveillance system is to reduce human intervention while at the same time, provide accurate detection of moving objects. Many researchers have attempted to automate different aspects of camera surveillance such as tracking humans, traffic controlling, ground surveillance, etc. However, a system that overcomes overall difficulties that arise in the task of object detection and object tracking has not been developed because of high variance in the problem domain. The proposed system tracks the path of a locked object through a network of cameras. In contrast to traditional methods where the operators have to switch the screens manually to find the target objects, the proposed technique, once locked to an object; automatically tracks it through a camera network and generates the path on a map. We propose to use stereo cameras to enhance the detection and tracking of objects in 3D space.


In last few decades, technological revolution has accelerated the deployment of large scale surveillance systems on almost all public places such as malls, hospitals, airports, railways, bus stations, roads, etc. These intelligent surveillance systems can play crucial role in governance of situations, collective security and safety, mitigating as well as prevention of adversaries. With gradual increase in multi camera surveillance systems enclosing multi angle views of same as well as different scenes has increased complexity of monitoring the systems by manual inspection. Abnormalities also known as anomalies or outliers are inevitable part of the existence and presumed to be rare in occurrence. Manual monitoring of such abnormalities is susceptible to errors and limited by human capabilities such as inattention and tiresome. Hence in the field of computer vision, automated abnormal activity recognition (AAR) from surveillance systems is emerging research area. The intent of this research is to shed a light on recent innovations and developments that have made a mark in abnormal activity recognition (AAR) involving deep learning. This paper also includes conventional categorization of anomalies based on different perspectives which can provide better understanding to young researchers. Though recent developments still poses many real time challenges in automatic abnormal activity recognition, some of them are enclosed in this paper.


2002 ◽  
Vol 35 (7) ◽  
pp. 204-208 ◽  
Author(s):  
James Black ◽  
Tim Ellis

This article describes some of the advances that have been made in intelligent image surveillance and monitoring. In general most image surveillance and monitoring applications share a common set of key requirements. A variety of solutions to these key requirements are reviewed. A number of achievements made by the IMCASM project at City University are described in greater depth, with particular focus on multi camera surveillance systems. A number of open issues, which need to be resolved for the continued advancement of this technology, are also discussed


Sign in / Sign up

Export Citation Format

Share Document