Learning complementary saliency priors for foreground object segmentation in complex scenes

Object segmentation is widely recognized as one of the most challenging problems in computer vision. One major problem of existing methods is that most of them are vulnerable to the cluttered background. Moreover, human intervention is often required to specify foreground/background priors, which restricts the usage of object segmentation in real-world scenario. To address these problems, we propose a novel approach to learn complementary saliency priors for foreground object segmentation in complex scenes. Different from existing saliency-based segmentation approaches, we propose to learn two complementary saliency maps that reveal the most reliable foreground and background regions. Given such priors, foreground object segmentation is formulated as a binary pixel labelling problem that can be efficiently solved using graph cuts. As such, the confident saliency priors can be utilized to extract the most salient objects and reduce the distraction of cluttered background. Extensive experiments show that our approach outperforms 16 state-of-the-art methods remarkably on three public image benchmarks.

Avoiding the subject media, culture and the object

"This is a collection of inter-related essays on the postmillennial mediascape. Focusing on the neglected significance of the object within today's discourse networks, Avoiding the Subject extends the formal possibilities of cultural criticism by highlighting feedback loops between philosophy, technology, and politics. Students and teachers of visual culture, critical theory, cultural studies, film theory, and new media will find a wealth of ideas and insights in this fresh approach to the electronic environment."--BOOK JACKET.

The roles of static depth information and object-image relative motion in perception of heading

In a series of 6 experiments, two hypotheses were tested: that nominal heading perception is determined by the relative motion of images of objects positioned at different depths (R. F. Wang & J. E. Cutting 1999) and that static depth information contributes to this determination. By manipulating static depth information while holding retinal-image motion constant during  simulated self-movement, the authors found that static depth information played a role in determining perceived heading. Some support was also found for the involvement of R. F. Wang and J. E. Cutting’s (1999) categories of object-image relative motion in determining perceived heading. However, results suggested an unexpected functional dominance of information about heading relative to apparently near objects.

The influence of object-image velocity change on perceived heading in minimal environments

When human observers move forward and rotate their eyes, a complex pattern of light flows across the retina. This pattern is referred to as retinal flow. A model has been proposed to explain how humans perceive their direction of self-movement (or heading) from (1) static depth, (2) direction of image motion, and (3) whether image velocity undergoes acceleration or deceleration (Wang & Cutting, 1999). However, findings from past research in which sparse or minimalist stimuli were used have suggested that not all of the information to which participants are sensitive is captured within the scope of this model. In particular it has been suggested that the magnitude or size of image velocity change may be of significance beyond simply whether image velocity could be categorized as speeding up (i.e., accelerating) or slowing down (i.e., decelerating). In two experiments, the influence of this factor on heading judgments under minimal conditions was investigated. Evidence was found in support of the idea that the rate of image velocity change can influence judgments of the direction of self-movement in minimalist conditions.

Using object and trajectory analysis to facilitate indexing and retrieval of video

This paper aims to show that by using low level feature extraction, motion and object identifying and tracking methods, features can be extracted and indexed for efficient and effective retrieval for video; such as an awards ceremony video. Video scene/shot analysis and key frame extraction are used as a foundation to identify objects in video and be able to find spatial relationships within the video. The compounding of low level features such as colour, texture and abstract object identification lead into higher level real object identification and tracking and scene detection. The main focus is on using a video style that is different to the heavily used sports and news genres. Using different video styles can open the door to creating methods that could encompass all video types instead of specialized methods for each specific style of video.

Object oriented finite element analysis: a distributed approach to mesh generation

The object-oriented finite element method (OOFEM) has attracted the attention of many researchers. Compared with the traditional finite element method, OOFEM software has the advantages of maintenance and reuse. Moreover, it is easier to expand the architecture to a distributed one. In this paper, we introduce a distributed architecture of a object-oriented finite element preprocessor. A comparison between the distributed system and the centralised system shows that the former, presented in the paper, greatly improves the performance of mesh generation. Other finite element analysis modules could be expanded according to this architecture.

The design and development of an integrated system for object-oriented finite element computing

Finite Element Method (FEM) is widely used in Science and Engineering since 1960’s. The vast majority of FEM software is procedure-oriented. However, this conventional style of designing FEM software encounters problems in maintenance, reuse, and expansion of the software. Recently the object-oriented finite element method attracts the attention of lots of researchers, and now there is a growing interest in this method. In this paper, the object-oriented finite element (OOFE) is briefly introduced. Then the design and development of an integrated OOFE system is described. A comparison of the integrated OOFE system and a procedure-oriented system shows that our OOFE system has many advantages.

Object-oriented security modelling for healthcare

With the convergence of paper to electronic, the health industry is relying more on technology to maintain and update the well-being of patients. This reliance on technology requires an acute level of protection from unwanted technological disasters and/or human threats. Research shows insufficiencies with the implementation and use of security controls; as well as current analysis methods lacking the techniques to analyse technical and social aspects of security. The aim of this paper is to introduce an information security evaluation methodology for health information systems based on UML.

Health information security evaluation: continued development of an object-oriented method

With the convergence of paper to electronic, the health industry is relying more on technology to maintain and update the well-being of patients. This reliance on technology requires an acute level of protection from
unwanted technological disasters and/or human threats. Research shows insufficiencies with the implementation and use of security controls; as well as current analysis methods lacking the techniques to analyse technical and social aspects of security. The aim of this paper is to introduce an information security evaluation methodology for health information systems based on UML.

Computational simulation of gas flow and heat transfer near an immersed object in fluidized beds

To improve the understanding of the heat transfer mechanism and to find a reliable and simple heat-transfer model, the gas flow and heat transfer between fluidized beds and the surfaces of an immersed object is numerically simulated based on a double particle-layer and porous medium model. The velocity field and temperature distribution of the gas and particles are analysed during the heat transfer process. The simulation shows that the change of gas velocity with the distance from immersed surface is consistent with the variation of bed voidage, and is used to validate approximately dimensional analysing result that the gas velocity between immersed surface and particles is 4.6Umf/εmf. The effects of particle size and particle residence time on the thermal penetration depth and the heat-transfer coefficients are also discussed.

Polyhedral studies for minimum-span graph labelling with integer distance constraints

This paper studies the polytope of the minimum-span graph labelling problems with integer distance constraints (DC-MSGL). We first introduce a few classes of new valid inequalities for the DC-MSGL defined on general graphs and briefly discuss the separation problems of some of these inequalities. These are the initial steps of a branch-and-cut algorithm for solving the DC-MSGL. Following that, we present our polyhedral results on the dimension of the DC-MSGL polytope, and that some of the inequalities are facet defining, under reasonable conditions, for the polytope of the DC-MSGL on triangular graphs.

Simultaneous estimation of optical flow and object state: A modified approach to optical flow calculation

Differential optical flow methods are widely used within the computer vision community. They are classified as being either local, as in the Lucas-Kanade method, or global, as in the Horn-Schunck technique. As the physical dynamics of an object is inherently coupled into the behavior of its image in the video stream, in this paper, we use such dynamic parameter information in calculating optical flow when tracking a moving object using a video stream. Indeed, we use a modified error function in the minimization that contains physical parameter information. Further, the refined estimates of optical flow is used for better estimation of the physical parameters of the object in the simultaneous estimation of optical flow and object state(SEOS).

Stereo-vision-based moving object tracking via robust linear filtering

Vision-based tracking sensors typically provide nonlinear measurements
of the targets Cartesian position and velocity state components. In this paper we derive linear measurements using an analytical measurement conversion technique which can be used with two (or more) vision sensors. We derive
linear measurements in the target’s Cartesian position and velocity components and we derive a robust version of a linear Kalman filter. We show that our linear robust filter significantly outperforms the extended Kalman Filter. Moreover, we prove that the state estimation error is bounded.