Comparison of Target Detection Algorithms using Adaptive Background Models

Hall, Daniela; Nascimento, Jacinto C.; Ribeiro, Pedro; Andrade, E.L.; Moreno, Plínio; Pesnel, S.; List, T.; Emonet, Rémi; Fisher, Robert B.; Victor, Jonathan; Crowley, James L.

doi:10.1109/vspets.2005.1570905

Cited by 64 publications

(51 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We notice that the color appearance is very different according to the real scene illumination conditions. For each video sequence, the silhouette of the moving person is extracted by using the background subtraction technique, combined with a shadow elimination algorithm [11,12] and morphological operators (erosion and dilation). A set of key frames in which people are entirely viewed is then extracted in order to characterize the passage of an individual.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

People re-identification by spectral classification of silhouettes

Cong¹,

Khoudour²,

Achard³

et al. 2010

Signal Processing

View full text Add to dashboard Cite

The problem described in this paper consists in re-identifying moving people in different sites which are completely covered with non-overlapping cameras. Our proposed framework relies on the spectral classification of the appearance-based signatures extracted from the detected person in each sequence. We first propose a new feature called "color-position" histogram combined with several illumination invariant methods in order to characterize the silhouettes in static images. Then, we develop an algorithm based on spectral analysis and Support Vector Machines (SVM) for the re-identification of people. The performance of our system is evaluated on real data sets collected on INRETS premises. The experimental results show that our approach provides promising results for security applications.

show abstract

Section: Resultsmentioning

confidence: 99%

“…To do this, a detection of moving areas, by background subtraction, combined with a shadow elimination algorithm is first carried out [11,12]. Let us assume now that each person's silhouette is located in all the frames of a video sequence.…”

Section: Signature Generationmentioning

confidence: 99%

People re-identification by spectral classification of silhouettes

Cong¹,

Khoudour²,

Achard³

et al. 2010

Signal Processing

View full text Add to dashboard Cite

show abstract

“…In addition, there is no agreement on the metrics. With no other objective in mind than giving an order of magnitude of current published results [13], the sensitivity of detection algorithms is less than 50%, using a different metric based on the number of boxes having a sufficient overlap with the ground truth. We believe that this metric is less accurate than the one we have used.…”

Section: Resultsmentioning

confidence: 99%

Real-time control of video surveillance systems with program supervision techniques

Georis

Brémond

Thonnat

2007

Machine Vision and Applications

View full text Add to dashboard Cite

In this article, we describe a knowledge-based controlled platform using program supervision techniques. This platform eases the creation and the configuration of video surveillance systems. Several issues need to be addressed to provide a correct system configuration: (1) to choose, among a library of programs, those which are best satisfying a given user request, (2) to assign a correct value for each program parameter, (3) to evaluate performances and to guarantee a performance rate which is satisfactory regarding end-user requirements. This platform is composed of three main components: the library of programs, the knowledge base and the control component. The knowledge is either given by experts or learnt by the system. The control is generic in the sense that it is independent of any application. To validate this platform, we have built and evaluated six video surveillance systems which are featured with three properties: adaptability, reliability and real-time processing.

show abstract

“…Target detection is achieved by considering a background image periodically refreshed throughout the process (Hall et al, 2005). The time interval between two background images is set to 3 minutes but can be chosen by the operator.…”

Section: Motion Detectionmentioning

confidence: 99%

Ship Classification From Multispectral Videos

2012

View full text Add to dashboard Cite

Surveillance of a seaport can be achieved by different means: radar, sonar, cameras, radio communications and so on. Such a surveillance aims, on the one hand, to manage cargo and tanker traffic, and, on the other hand, to prevent terrorist attacks in sensitive areas. In this paper an application to video-surveillance of a seaport entrance is presented, and more particularly, the different steps enabling to classify mobile shapes. This classification is based on a parameter measuring the similarity degree between the shape under study and a set of reference shapes. The classification result describes the considered mobile in terms of shape and speed, as speed is determined by target tracking.

show abstract

Comparison of Target Detection Algorithms using Adaptive Background Models

Abstract: Abstract

Cited by 64 publications

References 11 publications

People re-identification by spectral classification of silhouettes

People re-identification by spectral classification of silhouettes

Real-time control of video surveillance systems with program supervision techniques

Ship Classification From Multispectral Videos

Contact Info

Product

Resources

About