Real-time outdoor video surveillance with robust foreground extraction and object tracking via multi-state transition management

Lei, Bangjun; Xu, Li-Qun

doi:10.1016/j.patrec.2006.02.017

Cited by 49 publications

(21 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 2 it is shown that our system is comparative in performance. Furthermore it runs in real time, as does the system found in (Lei and Xu 2006) while the frame rate of system found in (Lee et al 2007) is lower.…”

Section: Resultsmentioning

confidence: 99%

“…In the case of POT we consider occlusion level lower than 25%. Table 1 We also compared our system with those found in (Lei and Xu 2006) and (Lee et al 2007). In Table 2 it is shown that our system is comparative in performance.…”

Section: Resultsmentioning

confidence: 99%

“…An effective algorithm has to be able to handle changes in object's appearances, partial and=or complete occlusions, etc. (Li et al 2008;Francois 2004;Lei and Xu 2006). Systems designed for moving cameras can be categorized in pan=tilt camera systems and freely moving camera systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Hybrid Static/Active Video Surveillance System

Iosifidis

Mouroutsos

Γαστεράτος

2011

International Journal of Optomechatronics

View full text Add to dashboard Cite

In this article, we present an effective real-time video surveillance system for real-life outdoor surveillance scenarios. The system integrates two different camera's behaviors: a static and a moving one. Static camera subsystem operates multiple object tracking and classification. Abnormal behaviors are detected using information about objects' routes. In case of a probable collision scenario, the operation of the moving camera subsystem initiates and a PID controller gives instructions at a pan/tilt mechanism in order to rotate the camera and record the activity. The approaches employed address properly the challenges that might arise in a typical outdoor scene, such as local and global lighting changes, variations in objects' appearance and occlusions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Static/Active Video Surveillance System

Iosifidis

Mouroutsos

Γαστεράτος

2011

International Journal of Optomechatronics

View full text Add to dashboard Cite

show abstract

“…This background pixel model is able to cope with the multimodal nature of many practical situations and leads to good results when repetitive background motions, such as tree leaves or branches, are encountered. Since its introduction, the model has gained vastly in popularity among the computer vision community [4], [7], [11], [42]- [44], and it is still raising a lot of interest as authors continue to revisit the method and propose enhanced algorithms [45]- [50]. In [51], a particle swarm optimization method is proposed to automatically determine the parameters of the GMM algorithm.…”

Section: Review Of Background Subtraction Algorithmsmentioning

confidence: 99%

ViBe: A Universal Background Subtraction Algorithm for Video Sequences

Barnich

Droogenbroeck²

2011

IEEE Trans. on Image Process.

1,716

1,109

View full text Add to dashboard Cite

Abstract-This paper presents a technique for motion detection that incorporates several innovative mechanisms. For example, our proposed technique stores, for each pixel, a set of values taken in the past at the same location or in the neighborhood. It then compares this set to the current pixel value in order to determine whether that pixel belongs to the background, and adapts the model by choosing randomly which values to substitute from the background model. This approach differs from those based on the classical belief that the oldest values should be replaced first. Finally, when the pixel is found to be part of the background, its value is propagated into the background model of a neighboring pixel.We describe our method in full details (including pseudocode and the parameter values used) and compare it to other background subtraction techniques. Efficiency figures show that our method outperforms recent and proven state-of-the-art methods in terms of both computation speed and detection rate. We also analyze the performance of a downscaled version of our algorithm to the absolute minimum of one comparison and one byte of memory per pixel. It appears that even such a simplified version of our algorithm performs better than mainstream techniques. An implementation of ViBe is available at http://www.motiondetection.org.

show abstract

“…Mean shift Lu et al, 2008) is used to track an illegal vehicle and Kalman filtering (Lei et al, 2006;Yao et al, 2008) is used to predict the location of the vehicle.…”

Section: Illegal Vehicle Trackingmentioning

confidence: 99%

An illegal lane change monitoring system

Gao¹,

Liu²,

Zhang³

et al. 2009

Journal of the Chinese Institute of Engineers

View full text Add to dashboard Cite

In order to solve problems such as traffic jams and poor traffic management, a kind of illegal lane changing monitoring system based on traffic video is presented. The hardware system is composed of industrial computers and cameras fixed above the road. The software part consists of video processing, background extraction and updating, lane line extraction, vehicle recognition, moving shadow analysis, illegal lane change detection, vehicle tracking and prediction. First, the video collected is transformed into a series of images. Then a background is obtained by using averaging, and the lane lines are extracted by an improved Hough transform. In order to obtain complete and accurate outlines of the moving vehicles, a method of obtaining a vehicle profile combined with background subtraction and edge detection is proposed.A simple method for illegal lane change discrimination is also put forward. A meanshift algorithm combined with a Kalman filter is used to track and predict the locations of vehicles. Experimental results show that this system satisfies the need for real-time accuracy, and it can be used for intelligent traffic supervison.

show abstract

Real-time outdoor video surveillance with robust foreground extraction and object tracking via multi-state transition management

Cited by 49 publications

References 16 publications

A Hybrid Static/Active Video Surveillance System

A Hybrid Static/Active Video Surveillance System

ViBe: A Universal Background Subtraction Algorithm for Video Sequences

An illegal lane change monitoring system

Contact Info

Product

Resources

About