Non-parametric statistical background modeling for efficient foreground region detection

Most methods for foreground region detection in videos are challenged by the presence of quasi-stationary backgrounds—flickering monitors, waving tree branches, moving water surfaces or rain. Additional difficulties are caused by camera shake or by the presence of moving objects in every image. The contribution of this paper is to propose a scene-independent and non-parametric modeling technique which covers most of the above scenarios. First, an adaptive statistical method, called adaptive kernel density estimation (AKDE), is proposed as a base-line system that addresses the scene dependence issue. After investigating its performance we introduce a novel general statistical technique, called recursive modeling (RM). The RM overcomes the weaknesses of the AKDE in modeling slow changes in the background. The performance of the RM is evaluated asymptotically and compared with the base-line system (AKDE). A wide range of quantitative and qualitative experiments is performed to compare the proposed RM with the base-line system and existing algorithms. Finally, a comparison of various background modeling systems is presented as well as a discussion on the suitability of each technique for different scenarios.     

An ordering algorithm for pattern presentation in fuzzy ARTMAP thattends to improve generalization performance

We introduce a procedure, based on the max-min clustering method, that identifies a fixed order of training pattern presentation for fuzzy adaptive resonance theory mapping (ARTMAP). This procedure is referred to as the ordering algorithm, and the combination of this procedure with fuzzy ARTMAP is referred to as ordered fuzzy ARTMAP. Experimental results demonstrate that ordered fuzzy ARTMAP exhibits a generalization performance that is better than the average generalization performance of fuzzy ARTMAP, and in certain cases as good as, or better than the best fuzzy ARTMAP generalization performance. We also calculate the number of operations required by the ordering algorithm and compare it to the number of operations required by the training phase of fuzzy ARTMAP. We show that, under mild assumptions, the number of operations required by the ordering algorithm is a fraction of the number of operations required by fuzzy ARTMAP.     

Genetic object recognition using combinations of views

Investigates the application of genetic algorithms (GAs) for recognizing real 2D or 3D objects from 2D intensity images, assuming that the viewpoint is arbitrary. Our approach is model-based (i.e. we assume a pre-defined set of models), while our recognition strategy relies on the theory of algebraic functions of views. According to this theory, the variety of 2D views depicting an object can be expressed as a combination of a small number of 2D views of the object. This implies a simple and powerful strategy for object recognition: novel 2D views of an object (2D or 3D) can be recognized by simply matching them to combinations of known 2D views of the object. In other words, objects in a scene are recognized by "predicting" their appearance through the combination of known views of the objects. This is an important idea, which is also supported by psychophysical findings indicating that the human visual system works in a similar way. The main difficulty in implementing this idea is determining the parameters of the combination of views. This problem can be solved either in the space of feature matches among the views ("image space") or the space of parameters ("transformation space"). In general, both of these spaces are very large, making the search very time-consuming. In this paper, we propose using GAs to search these spaces efficiently. To improve the efficiency of genetic searching in the transformation space, we use singular value decomposition and interval arithmetic to restrict the genetic search to the most feasible regions of the transformation space. The effectiveness of the GA approaches is shown on a set of increasingly complex real scenes where exact and near-exact matches are found reliably and quickly     

Integrating perceptual level of detail with head-pose estimation and its uncertainty

Immersive virtual environments with life-like interaction capabilities can provide a high fidelity view of the virtual world and seamless interaction methods to the user. High demanding requirements, however, raise many challenges in the development of sensing technologies and display systems. The focus of this study is on improving the performance of human–computer interaction by rendering optimizations guided by head pose estimates and their uncertainties. This work is part of a larger study currently being under investigation at NASA Ames, called “Virtual GloveboX” (VGX). VGX is a virtual simulator that aims to provide advanced training and simulation capabilities for astronauts to perform precise biological experiments in a glovebox aboard the International Space Station (ISS). Our objective is to enhance the virtual experience by incorporating information about the user’s viewing direction into the rendering process. In our system, viewing direction is approximated by estimating head orientation using markers placed on a pair of polarized eye-glasses. Using eye-glasses does not pose any constraints in our operational environment since they are an integral part of a stereo display used in VGX. During rendering, perceptual level of detail methods are coupled with head-pose estimation to improve the visual experience. A key contribution of our work is incorporating head pose estimation uncertainties into the level of detail computations to account for head pose estimation errors. Subject tests designed to quantify user satisfaction under different modes of operation indicate that incorporating uncertainty information during rendering improves the visual experience of the user.     

On-road vehicle detection: a review

Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments, and possible collision with other vehicles has attracted a lot of attention lately. In these systems, robust and reliable vehicle detection is a critical step. This paper presents a review of recent vision-based on-road vehicle detection systems. Our focus is on systems where the camera is mounted on the vehicle rather than being fixed such as in traffic/driveway monitoring systems. First, we discuss the problem of on-road vehicle detection using optical sensors followed by a brief review of intelligent vehicle research worldwide. Then, we discuss active and passive sensors to set the stage for vision-based vehicle detection. Methods aiming to quickly hypothesize the location of vehicles in an image as well as to verify the hypothesized locations are reviewed next. Integrating detection with tracking is also reviewed to illustrate the benefits of exploiting temporal continuity for vehicle detection. Finally, we present a critical overview of the methods discussed, we assess their potential for future deployment, and we present directions for future research.     

Review of computer vision education

Computer vision is becoming a mainstream subject of study in computer science and engineering. With the rapid explosion of multimedia and the extensive use of video and image-based communications over the World Wide Web, there is a strong demand for educating students to become knowledgeable in computer imaging and vision. The purpose of this paper is to review the status of computer vision education today.     

Iterative tensor voting for perceptual grouping of ill-defined curvilinear structures

In this paper, a novel approach is proposed for perceptual grouping and localization of ill-defined curvilinear structures. Our approach builds upon the tensor voting and the iterative voting frameworks. Its efficacy lies on iterative refinements of curvilinear structures by gradually shifting from an exploratory to an exploitative mode. Such a mode shifting is achieved by reducing the aperture of the tensor voting fields, which is shown to improve curve grouping and inference by enhancing the concentration of the votes over promising, salient structures. The proposed technique is validated on delineating adherens junctions that are imaged through fluorescence microscopy. However, the method is also applicable for screening other organisms based on characteristics of their cell wall structures. Adherens junctions maintain tissue structural integrity and cell-cell interactions. Visually, they exhibit fibrous patterns that may be diffused, heterogeneous in fluorescence intensity, or punctate and frequently perceptual. Besides the application to real data, the proposed method is compared to prior methods on synthetic and annotated real data, showing high precision rates.     

Passive detection of image forgery using DCT and local binary pattern

With the development of easy-to-use and sophisticated image editing software, the alteration of the contents of digital images has become very easy to do and hard to detect. A digital image is a very rich source of information and can capture any event perfectly, but because of this reason, its authenticity is questionable. In this paper, a novel passive image forgery detection method is proposed based on local binary pattern (LBP) and discrete cosine transform (DCT) to detect copy–move and splicing forgeries. First, from the chrominance component of the input image, discriminative localized features are extracted by applying 2D DCT in LBP space. Then, support vector machine is used for detection. Experiments carried out on three image forgery benchmark datasets demonstrate the superiority of the method over recent methods in terms of detection accuracy.