Background subtraction is the first step of many video surveillance applications. What is considered background varies by application, and may include regular, systematic, or complex motions. This paper explores the use of several different local spatio-temporal models of a background, defined at each pixel in the image. We present experiments with real image data and conclude that appropriate local representations are sufficient to make background models of complicated real world motions. Empirical studies illustrate, for example, that an optical flow-based model is able to detect emergency vehicles whose motion is different from those typically observed in traffic scenes. We conclude that "different models are appropriate for different scenes", but give criteria by which one can choose which model will be best.

In content-based image retrieval (CBIR) performance characterization is easily being neglected. A major difficulty lies in the fact that ground truth and the definition of benchmarks are extremely user and application dependent. This paper proposes a two-stage CBIR framework which allows to predict the behavior of the retrieval system as well as to optimize its performance. In particular, it is possible to maximize precision, recall, or jointly precision and recall. The framework is based on the detection of high-level concepts in images. These concepts correspond to vocabulary users can query the database with. Performance optimization is carried out on the basis of the user query, the performance of the concept detectors, and an estimated distribution of the concepts in the database. The optimization is transparent to the user and leads to a set of internal parameters that optimize the succeeding retrieval.

Video surveillance in outdoor areas is hampered by consistent background motion which defeats systems that use motion to identify intruders. While algorithms exist for masking out regions with motion, a better approach is to develop a statistical model of the typical dynamic video appearance. This allows the detection of potential intruders even in front of trees and grass waving in the wind, waves across a lake, or cars moving past. In this paper we present a general framework for the identification of anomalies in video, and a comparison of statistical models that characterize the local video dynamics at each pixel neighborhood. A real-time implementation of these algorithm runs on an 800 MHz laptop, and we present qualitative results in many application domains.

The classification of image regions of interest in an image is an important area of research. Generally most investigations concentrate on the optimisation of the constituent parts of the system without regard to the overall performance. This work takes a system centred approach. Using a novel multi-class receiver operating characteristic, which also allows for the inherent uncertainty present, it is shown that the influence of different region based segmentation algorithms on the performance of classification algorithms can be determined. The results generated, using this approach, for an airborne infrared application highlight the non-linear relationship between the constituent algorithms and show quantitatively that the system performance can be strongly class and segmenter/classifier dependent.

Background subtraction is the first step of many video surveillance applications. What is considered background varies by application, and may include regular, systematic, or complex motions. This paper explores the use of several different local spatio-temporal models of a background, defined at each pixel in the image. We present experiments with real image data and conclude that appropriate local representations are sufficient to make background models of complicated real world motions. Empirical studies illustrate, for example, that an optical flow-based model is able to detect emergency vehicles whose motion is different from those typically observed in traffic scenes. We conclude that "different models are appropriate for different scenes", but give criteria by which one can choose which model will be best.

Abstract This paper deals with the topic of performance evaluation of symbol recognition & spotting systems. We propose here a new approach to the generation of synthetic graphics documents containing non-isolated symbols in a real context. This approach is based on the definition of a set of constraints that permit us to place the symbols on a predefined background according to the properties of a particular domain (architecture, electronics, engineering, etc.). In this way, we can obtain a large amount of images resembling real documents by simply defining the set of constraints and providing a few predefined backgrounds. As documents are synthetically generated, the groundtruth (the location and the label of every symbol) becomes automatically available. We have applied this approach to the generation of a large database of architectural drawings and electronic diagrams, which shows the flexibility of the system. the results of a given method with the groundtruth in order to give a measure of the performance. Fig. 1 Performance evaluation 1

This document presents a design methodology the aim of which is to provide a framework for constructing machine vision systems. Central to this approach is the use of empirical design techniques and in particular quantitative statistics. The methodology described herein underpins the development of the TINA [26] open source image analysis environment which in turn provides practical instantiations of the ideas presented. The appendices form the larger part of this document, providing mathematical explanations of the techniques which are regarded as of importance. A summary of these appendices is given below; Appendix A B C D E F G H I J K L