Performance Evaluation Criterion for Characterizing Video-Surveillance Systems
| Autor: | Elena Stringa, Gianni Vernazza, Franco Oberti |
|---|---|
| Rok vydání: | 2001 |
| Předmět: |
Signal processing
Guard (information security) Receiver operating characteristic Computer science Real-time computing Cognitive neuroscience of visual object recognition Object detection Set (abstract data type) Signal Processing Evaluation methods Performance requirement Computer Vision and Pattern Recognition Electrical and Electronic Engineering Simulation |
| Zdroj: | Real-Time Imaging. 7:457-471 |
| ISSN: | 1077-2014 |
| Popis: | In the last decade, video surveillance systems have been developed to guard remote environments in order to detect and prevent dangerous situations. In general, such systems are very complex and their performances rely strongly on the values taken on by the parameters regulating the behavior of surveillance algorithms. This makes it difficult to compare performances to select the most suitable system for the problem considered. Moreover, parameters are set during the installation phase, but a good selection requires time and experience. In this paper, we present an evaluation method for characterizing video-surveillance systems in order to provide an easy way of system installation. The proposed procedure is based on the definition of Receiver Operating Characteristic (ROC) curves traced for different parameter sets and for different system working conditions. Examples are given that concern an indoor video-based surveillance system for detecting, recognizing and tracking moving objects; the system has been characterized and evaluated for different scenarios. Results prove the validation of the proposed evaluation procedure though a comparison of the performances obtained in a laboratory with the ones achieved in real working environments, after system installation following the guidelines provided by the proposed methodology. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect