Scheduled System Maintenance on May 29th, 2015:
IEEE Xplore will be upgraded between 11:00 AM and 10:00 PM EDT. During this time there may be intermittent impact on performance. We apologize for any inconvenience.
By Topic

Selective Visual Attention:Computational Models and Applications

Cover Image Copyright Year: 2013
Author(s): Zhang, L.; Lin, W.
Publisher: Wiley-IEEE Press
Content Type : Books & eBooks
Topics: Computing & Processing (Hardware/Software)
  • Print

Abstract

Visual attention is a relatively new area of study combining a number of disciplines: artificial neural networks, artificial intelligence,  vision science and psychology. The aim is to build computational models similar to human vision in order to solve tough problems for many potential applications including object recognition, unmanned vehicle navigation, and image and video coding and processing. In this book, the authors provide an up to date and highly applied introduction to the topic of visual attention, aiding researchers in creating powerful computer vision systems. Areas covered include the significance of vision research, psychology and computer vision, existing computational visual attention models, and the authors' contributions on visual attention models, and applications in various image and video processing tasks.This book is geared for graduates students and researchers in neural networks, image processing, machine learning, computer vision, and other areas of biologically inspired model building and applications. The book can also be used by practicing engineers looking for techniques involving the application of image coding, video processing, machine vision and brain-like robots to real-world systems. Other students and researchers with interdisciplinary interests will also find this book appealing.
Provides a key knowledge boost to developers of image processing applications
Is unique in emphasizing the practical utility of attention mechanisms
Includes a number of real-world examples that readers can implement in their own work:
robot navigation and object selection
image and video quality assessment
image and video coding
Provides codes for users to apply in practical attentional models and mechanisms

  •   Click to expandTable of Contents

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Front Matter

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.fmatter
      Page(s): i - xiii
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      The prelims comprise:
      Half-Title Page
      Title Page
      Copyright Page
      Table of Contents
      Preface View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Introduction to Visual Attention

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch1
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      This chapter introduces basic phenomena, concepts, experiments and technological development for selective visual attention. It also provides relevant references to facilitate model development. The basic phenomena and concepts are given in the first section. Section 1.2 introduces the types of selective visual attention, such as pre-attention and attention, bottom-up attention and top-down attention, attention in parallel and serial processing, and overt and covert attention. Then two phenomena related visual attention models - change blindness and inhibition of return - are discussed in Section 1.3. There is also an overview of different phases of research and development in the related areas, followed by a discussion on the scope of the various chapters in this book. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Background of Visual Attention - Theory and Experiments

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch2
      Page(s): 25 - 71
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      This chapter is a continuation and an extension of the previous chapter. After the brief introduction of selective visual attention in the previous chapter, we present more details on the related knowledge, theory and experiments for visual attention. Section 2.1 describes the relevant basic properties and structures of the human visual system (HVS). In Sections 2.2 and 2.3, the widely used feature integration theory (FIT), as well as its extension (i.e. the guided search (GS) theory), is to be discussed, with the experimental confirmation available. FIT deals with bottom-up attention, while GS enables a combination of bottom-up and top-down attention. Section 2.4 further discusses the time binding theory for multi-feature integration at the neuronal level. Section 2.5 gives insight into some important issues in visual attention modelling, such as competition, normalization and frequency whitening. The final section covers statistical signal processing, which can be used for modelling visual attention alone or jointly with other principles in biology. The content in this chapter is the source of inspiration for many computational models of the human visual attention. It will help the reader not only to understand the existing computational attention models to be presented throughout this book, but also to build new systems because some crucial aspects of visual attention have not been incorporated in computational and engineering models yet, due to the difficulties in modelling, as well as application scenarios not being explored. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Computational Models in the Spatial Domain

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch3
      Page(s): 73 - 118
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      This chapter describes the computational visual attention models in the spatial domain, based on the bottom-up mechanism. Although there have been a large number of bottom-up computational models in the spatial domain since 1998, this chapter only discusses a few typical computational models: baseline saliency (BS) model, models based on neural networks and models based on statistical signal processing theory, such as information theory (the AIM model), decision-theory (the DISC model) natural statistical (the SUN model) and Bayesian theory (the surprise detection model). Section 3.1 introduces the major parts of the BS system, while Section 3.2 addresses the issues related to visual attention for video. These two sections aim to give the reader the most important ideas for modelling bottom-up visual attention in the spatial domain. Section 3.3 presents more details and variations of the BS model, to give the reader more insight and choices within the topic. Section 3.4 introduces an alternative solution, a graph-based approach, for determining visual attention, and we also demonstrate and discuss its difference with the BS model. Section 3.5 gives a new filter basis bank learning from natural images to extract features of the input image, which is based on information maximum, called the AIM model. Another model, referred to as DISC, which processes the centre-surround inhibition based on optimal decision theory, is introduced in Section 3.6. Then Section 3.7 presents a paradigm shift in visual attention modelling by introducing a new methodology based on comprehensive statistics from a large number of natural images, rather than the current test image (as used in the models in Sections 3.1 to 3.6). Section 3.8 presents a surprise detection model to test the saliency location, based on Bayesian theory. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Fast Bottom-Up Computational Models in the Spectral Domain

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch4
      Page(s): 119 - 165
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      This chapter continues the introduction to bottom-up visual attention models. Following the description of models in the spatial (pixel) domain in the previous chapter, the focus is now put on models in the spectral domain. Since frequency domain models can detect the salient object quicker to enable them to meet real-time requirements in engineering, they are the choice for many real-world applications In this chapter, first the properties of the frequency spectrum for image analysis are given in Section 4.1, and then the major bottom-up computational models based on phase spectrum in frequency domain are presented in Sections 4.2-4.6: the SR, PFT, PQFT, PCT and FDN models, respectively. In Section 4.6, FDN and PFDN models have biological plausibility because they simulate each step from the (spatial domain) BS model, but in the frequency domain. In Section 4.7, the AQFT model based on amplitude spectrum of image patches is introduced and Section 4.8 gives a computational model from the JPEG bit-stream. Finally, the advantages and limitations of frequency computational models are discussed in Section 4.9. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Computational Models for Top-down Visual Attention

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch5
      Page(s): 167 - 205
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      This chapter mainly discusses the computational models by combining bottom-up and top-down processing. In the combined models, the bottom-up part in almost all models uses all or part of the core of the BS model, and the top-down part often adopts other methods in computer vision, such as neural networks. Seven types of top-down computation are presented in this chapter. The most comprehensive is the population based model in which feature representation is in cell population form, and it is biologically plausible. Many modules are considered in the model such as bottom-up feature extraction, top-down knowledge leaning and storage, feature update by top-down influence, object recognition, inhibition of return (IoR), eye movement map, and so on. This model is first introduced in Section 5.1, then Section 5.2 covers the hierarchical object search model which simulates the human search method from coarse to finer resolution according to top-down intention. The decision tree as top-down knowledge learning, storage and retrieval is introduced in the Sections 5.3 and 5.4. Sections 5.5 and 5.6 illustrate the two models of the simple VOCUS and the model with fuzzy ART. Finally, we introduce the top-down SUN model with Bayesian framework in Section 5.7. The seven typical top-down computation methods combining the bottom-up model give different methods of knowledge representation, storage, learning and influence on visual attention. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Validation and Evaluation for Visual Attention Models

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch6
      Page(s): 207 - 220
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      This chapter assesses the performance of the saliency detection models described in the previous chapters. As with many other cases in engineering, a developed visual attention model needs to be critically benchmarked against other models, and then fully tested before being used in particular applications and situations. A number of qualitative and quantitative evaluation methods, as well as related ground-truth databases, are introduced in this chapter. Common benchmarks include simple man-made visual patterns, human-labelled images and eye tracking data, which are first given in Sections 6.1-6.3. The quantifying estimation of performance of the computational models is listed in Sections 6.4-6.6. The most commonly used criteria are PPV, TPR, F-measure, ROC and AUC, as introduced in Section 6.4. The statistical criteria for both static and dynamic scene - NNS and KL distance - are presented in Section 6.5. Then Section 6.6 shows the criterion of Spearman's rank-order correlation with visual conspicuity. Each type of ground-truth, the associated evaluation methods and their advantages and disadvantages are discussed whenever needed and possible. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Applications in Computer Vision, Image Retrieval and Robotics

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch7
      Page(s): 221 - 269
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      In this chapter, we begin to switch our focus from the visual attention modelling of Chapters 3-6 to the applications of these models. In Chapter 7, we first introduce the conventional engineering methods for object detection and recognition in Section 7.1. Then attention modelling combined with object detection and recognition for natural scenes is presented in Section 7.2. Since satellite images are different from natural images, in Section 7.3 we introduce the attention assisted object detection and recognition for satellite images. Section 7.4 presents image retrieval via visual attention. Another application of visual attention is presented finally for robots. This chapter does not try to introduce all aspects and works related to computer vision, image retrieval and robotics based on visual attention, but only demonstrates some typical methods of combining visual attention with conventional engineering methods. Readers can infer other aspects from these introduced applications. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Application of Attention Models in Image Processing

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch8
      Page(s): 271 - 303
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      This chapter introduces applications of visual attention models in image processing related areas: just noticeable difference (JND) modelling, visual quality assessment, image and video coding, visual signal retargeting and compressive sensing. Section 8.1 illustrates the combination of visual attention and the JND model towards a complete visibility threshold model which can be used in a wide spectrum of uses. The application of attention models in quality assessment (QA) of images and video is presented in Section 8.2, and a typical QA index, SSIM, is weighted by visual attention in different ways. The use of attention models to explore visual redundancy for better image coding is introduced in Section 8.3. The applications for image retargeting and compressive sensing are presented in Sections 8.4 and 8.5, respectively. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Summary, Further Discussions and Conclusions

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.ch9
      Page(s): 305 - 323
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      At the beginning of this chapter, visual attention is briefly introduced from both biological and engineering perspectives. As the emphasis of this book, saliency map computational models lying in the intersection area for biology, psychology and engineering are highlighted again. Section 9.1 summarizes the content of the whole book, and presents the connection between chapters and sections. In Section 9.2, several critical issues of visual attention modelling are discussed, while some final conclusions are given in Section 9.3. View full abstract»

    • Full text access may be available. Click article title to sign in or learn about subscription options.

      Index

      Zhang, L. ; Lin, W.
      Selective Visual Attention:Computational Models and Applications

      DOI: 10.1002/9780470828144.index
      Page(s): 325 - 332
      Copyright Year: 2013

      Wiley-IEEE Press eBook Chapters

      No abstract. View full abstract»