Browsing by Author "Fan, Chung-Shuo"

Now showing 1 - 7 of 7

A Survey of Intelligent Video Surveillance Systems: History, Applications and Future
(2015-01-01)
Fan, Chung-Shuo
;
Liang, Jia-Ming
;
Lin, Yi-Ting
;
Wu, Kun-Ru
;
Li, Kuan-Yi
With advances in wireless network infrastructure providing powerful support for surveillance video communications, it is practical to meet the needs of intelligent surveillance systems in a wide range of applications. This survey offers a comprehensive overview of state-of-the-art technologies for intelligent video surveillance systems so as to provide researchers in this field with a summary of the progress achieved to date. The evolution of surveillance systems is outlined as well. In addition, the representative technologies for environment modeling, object classification, object tracking, behavioral analysis, and database implementation are summarized. Finally, we list several detailed discussions on possible future research directions.
A Web-based Camera Dispatch System for Video Surveillance with Dynamic Requirements
(2015-01-01)
Li, Kuan-Yi
;
Liang, Jia-Ming
;
Fan, Chung-Shuo
;
Tseng, Yu-Chee
;
Lin, Yi-Ting
Video surveillance systems are commonly used to monitor environments, such as factories, shopping malls, offices, and schools, for safety and security. However, traditional closed-circuit television cameras can only capture static scenes. When unexpected events happen, such as fire accidents or stranger intrusion, the recorded video data cannot provide immediate and precise information. In this work, we design a camera dispatch system for video surveillance with pan-tilt-zoom (PTZ) cameras, which can monitor event-areas/targets real-timely and flexibly. Users can dynamically define the monitoring requirements, such as pixel-per-foot and viewing-angle of the event-areas/targets. Then, a dispatch algorithm will decide the most necessary cameras and corresponding settings to monitor the event-areas/targets immediately. The control panel is implemented as a web-based service. The demo shows that users can easily monitor potential event-areas/targets anywhere, anytime through a web browser.
A Web-based, Real-time Video Surveillance System by Leveraging PTZ Cameras
(2015)
Li, Kuan-Yi
;
Liang, Jia-Ming
;
Fan, Chung-Shuo
;
Wu, Kun-Ru
;
Lin, Yi-Ting
Video surveillance systems are commonly used for environmental monitoring. Nevertheless, existing systems such as [1, 2] can only monitor scenes statically. When an accident or a fire event happens, we cannot get the critical pictures and check those situations immediately. Therefore, we propose to leverage pan-tilt-zoom (PTZ) cameras and develop a real-time surveillance system, where the PTZ cameras can rotate in a horizontal plane by panning and in a vertical plane by tilting, and adjust the focal length by zooming, so we can control these cameras dynamically for the emergent area. Especially for the accessibility, we implement this system as a web service to help users easily define the emergent area and preview the video of cameras remotely. Specifically, our system is composed of multiple PTZ cameras and a web server, as shown in Fig. 1. The PTZ cameras are with fixed positions and can be controlled to pan, tilt, and zoom remotely by the web server. The web server maintains a website to provide the real-time surveillance service, consisting of two procedures: area setting and video displaying. The area setting is for users to define the monitored area, including the range and location of the monitored area. Then, all the cameras will be dispatched and face to the center of the monitored area. Finally, the video displaying procedure will show the monitoring results, including the video streams and the rotation parameters of the dispatched cameras. Fig. 2 shows the control panel of the implemented prototype, where there are two PTZ cameras deployed in the monitoring environment. On this panel, the left part is for video displaying and the right part is for the monitored area setting. More specifically, for the right part, the upper side is the floor plan of the monitoring environment which users can define the location of the emergent area by clicking on. On the lower left side, users can further specify the details of the area, such as its length and width. After setting, the monitored area will be marked as the red-dotted rectangle on the floor plan. Finally, the monitoring results, such as the coverage ratio of the monitored area and the rotation parameters of the cameras, will be shown on the lower central side. Note that the system also allows users to control the cameras manually on the lower right side.
An energy-efficient two phases cluster head selection in corona-based wireless sensor networks
(2015-01-01)
Fan, Chung-Shuo
;
資訊工程學系
;
Department of Computer Science
Owing to unbalanced traffic pattern of wireless sensor networks (WSNs), larger load is imposed to cluster heads (CHs) around the sink. Under this situation, CHs closer to the BS drain their energy earlier than those farther away from the sink. This paper first formulates cluster density of each corona according to the energy consumption of each CH. Then, this paper defines the range of CH candidates in phase 1 and 2 to choose the suitable CH so that sensor nodes forward data towards the BS and reduce the energy consumption. This paper further adopts cluster maintenance, which implement the cross-level data transmissions when specific conditions happen. Simulation results show that the proposed TPS (Two Phases cluster head Selection in WSNs) effectively prolongs the network lifetime and reduces the energy consumption over low energy adaptive clustering hierarchy (LEACH) and multi-hop routing with LEACH (MR-LEACH).
Efficient Cluster Radius and Transmission Ranges in Corona-based Wireless Sensor Networks
(2014-04-29)
Lai, Wei Kuang
;
Fan, Chung-Shuo
;
Shieh, Chin-Shiuh
;
資訊工程學系
;
Department of Computer Science
In wireless sensor networks (WSNs), hierarchical clustering is an efficient approach for lower energy consumption and extended network lifetime. In cluster-based multi-hop communications, a cluster head (CH) closer to the sink is loaded heavier than those CHs farther away from the sink. In order to balance the energy consumption among CHs, we development a novel cluster-based routing protocol for corona-structured wireless sensor networks. Based on the relaying traffic of each CH conveys, adequate radius for each corona can be determined through nearly balanced energy depletion analysis, which leads to balanced energy consumption among CHs. Simulation results demonstrate that our clustering approach effectively improves the network lifetime, residual energy and reduces the number of CH rotations in comparison with the MLCRA protocols.
HIGH: A Hexagon-based Intelligent Grouping Approach in Wireless Sensor Networks
(2016)
Fan, Chung-Shuo
;
資訊工程學系
;
Department of Computer Science
In a random deployment or uniform deployment strategy, sensor nodes are scattered randomly or uniformly in the sensing field, respectively. Hence, the coverage ratio cannot be guaranteed. The coverage ratio of uniform deployment, in general, is larger than that of the random deployment strategy. However, a random deployment or uniform deployment strategy may cause unbalanced traffic pattern in wireless sensor networks (WSNs). Therefore, cluster heads (CHs) around the sink have larger loads than those farther away from the sink. That is, CHs close to the sink exhaust their energy earlier. In order to overcome the above problem, we propose a Hexagon-based Intelligent Grouping approacH in WSNs (called HIGH). The coverage, energy consumption and data routing issues are well investigated and taken into consideration in the proposed HIGH scheme. The simulation results validate our theoretical analysis and show that the proposed HIGH scheme achieves a satisfactory coverage ratio, balances the energy consumption among sensor nodes, and extends network lifetime significantly.
Rich: Region-based Intelligent Cluster-Head Selection and Node Deployment Strategy in Concentric-based WSNs
(2013)
Fan, Chung-Shuo
;
資訊工程學系
;
Department of Computer Science
In a random deployment, sensor nodes are scattered randomly in the sensing field. Hence, the coverage can not be guaranteed. In contrast, the coverage of uniformly deployment is in general larger than the random deployment. However, uniformly deployment strategy may cause unbalanced traffic pattern in wireless sensor networks (WSNs). In this situation, larger load may be imposed to CHs (cluster heads) around the sink. Therefore, CHs close to the sink use up their energy earlier than those farther away from the sink. To overcome this problem, we propose a novel node deployment strategy in the concentric model, namely, Region-based Intelligent Cluster-Head selection and node deployment strategy (called Rich). The coverage, energy consumption and data routing issues are well investigated and taken into consideration in the proposed Rich scheme. The simulation results show that the proposed Rich alleviates the unbalanced traffic pattern significantly, prolongs network lifetime and achieves satisfactory coverage ratio.