From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Many current neurophysiological, psychophysical, and psychological approaches to vision rest on the idea that when we see, the brain produces an internal representation of the world. The activation of this internal representation is assumed to give rise to the experience of seeing. The problem with this kind of approach is that it leaves unexplained how the existence of such a detailed internal representation might produce visual consciousness. An alternative proposal is made here. We propose that seeing is a way of acting. It is a particular way of exploring the environment. Activity in internal representations does not generate the experience of seeing. The outside world serves as its own, external, representation. The experience of seeing occurs when the organism masters what we call the governing laws of sensorimotor contingency. The advantage of this approach is that it provides a natural and principled way of accounting for visual consciousness, and for the differences in the perceived quality of sensory experience in the different sensory modalities. Several lines of empirical evidence are brought forward in support of the theory, in particular: evidence from experiments in sensorimotor adaptation, visual \"filling in,\" visual stability despite eye movements, change blindness, sensory substitution, and color perception.

A sensorimotor account of vision and visual consciousness-Authors' Response-Acting out our sensory experience

We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow estimate and computing an update to the flow. Instead of the standard minimization of an objective function at each pyramid level, we train one deep network per level to compute the flow update. Unlike the recent FlowNet approach, the networks do not need to deal with large motions, these are dealt with by the pyramid. This has several advantages. First, our Spatial Pyramid Network (SPyNet) is much simpler and 96% smaller than FlowNet in terms of model parameters. This makes it more efficient and appropriate for embedded applications. Second, since the flow at each pyramid level is small (

https://openaccess.thecvf.com/content_cvpr_2017/papers/Ranjan_Optical_Flow_Estimation_CVPR_2017_paper.pdf

Optical Flow Estimation Using a Spatial Pyramid Network

i n c y h h i t i a R Last month, Alzheimer’s & Dementia: The Journal of the lzheimer’s Association received acceptance for inclusion n MEDLINE, the bibliographic database of the U.S. Naional Library of Medicine (NLM). Three years since the aunch, this achievement marks an important recognition of he Journal’s scientific merit and contribution to the field of lzheimer’s disease research. The editors, our publishing artners from Elsevier, and our sponsoring colleagues from he Alzheimer’s Association are extremely thankful to the uthors, reviewers, Editorial Board members, and readers or their many valuable contributions. As the official journal of the Alzheimer’s Association, lzheimer’s & Dementia will now be circulated to the active embers of the Association’s new International Society to dvance Alzheimer Research and Treatment (ISTAART) imonthly, as well as other subscribers and libraries. The ournal will continue to cover critical scientific, medical, ocial, and policy issues that investigators and clinicians ace every day, on matters concerning healthy brain aging to ll forms of dementia. Unlike other journals in the field, lzheimer’s & Dementia bridges new thinking across dierse areas of investigation. This interdisciplinary journal rovides the impetus for new scientific initiatives and offers

Alzheimer's & Dementia: the Journal of the Alzheimer's Association.

Event cameras are bio-inspired sensors that differ from conventional frame cameras: Instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes, and output a stream of events that encode the time, location and sign of the brightness changes. Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of is), very high dynamic range (140dB vs. 60dB), low power consumption, and high pixel bandwidth (on the order of kHz) resulting in reduced motion blur. Hence, event cameras have a large potential for robotics and computer vision in challenging scenarios for traditional cameras, such as low-latency, high speed, and high dynamic range. However, novel methods are required to process the unconventional output of these sensors in order to unlock their potential. This paper provides a comprehensive overview of the emerging field of event-based vision, with a focus on the applications and the algorithms developed to unlock the outstanding properties of event cameras. We present event cameras from their working principle, the actual sensors that are available and the tasks that they have been used for, from low-level vision (feature detection and tracking, optic flow, etc.) to high-level vision (reconstruction, segmentation, recognition). We also discuss the techniques developed to process events, including learning-based techniques, as well as specialized processors for these novel sensors, such as spiking neural networks. Additionally, we highlight the challenges that remain to be tackled and the opportunities that lie ahead in the search for a more efficient, bio-inspired way for machines to perceive and interact with the world.

Event-based Vision: A Survey

The recent release of the Oculus Rift, originally developed for entertainment applications, has reignited the interest of researchers and clinicians toward the use of head-mounted-displays in basic behavioral research and physical and psychological rehabilitation. However, careful evaluation of the Oculus Rift is necessary to determine whether it can be effectively used in these novel applications. In this article we address two issues concerning the perceptual quality of the Oculus Rift. (a) Is the Oculus able to generate an acceptable degree of immersivity? In particular, is it possible to elicit the sensation of presence via the virtual stimuli rendered by the device? (b) Does the Virtual Reality experienced through the Oculus Rift induce physical discomfort? To answer these questions, we employed four virtual scenarios in three separate experiments and evaluated performance with objective and subjective outcomes. In Experiment 1 we monitored observers’ heart rate and asked them to rate their Virtual R...

The Perceptual Quality of the Oculus Rift for Immersive Virtual Reality

Calibrated depth and color cameras for accurate 3D interaction in a stereoscopic augmented reality environment

We have developed a low-cost, practical gaze-contingent display in which natural images are presented to the observer with dioptric blur and stereoscopic disparity that are dependent on the three-dimensional structure of natural scenes. Our system simulates a distribution of retinal blur and depth similar to that experienced in real-world viewing conditions by emmetropic observers. We implemented the system using light-field photographs taken with a plenoptic camera which supports digital refocusing anywhere in the images. We coupled this capability with an eye-tracking system and stereoscopic rendering. With this display, we examine how the time course of binocular fusion depends on depth cues from blur and stereoscopic disparity in naturalistic images. Our results show that disparity and peripheral blur interact to modify eye-movement behavior and facilitate binocular fusion, and the greatest benefit was gained by observers who struggled most to achieve fusion. Even though plenoptic images do not replicate an individual's aberrations, the results demonstrate that a naturalistic distribution of depth-dependent blur may improve 3-D virtual reality, and that interruptions of this pattern (e.g., with intraocular lenses) which flatten the distribution of retinal blur may adversely affect binocular fusion.

Simulated disparity and peripheral blur interact during binocular fusion

http://www.eyeshots.it/papers/eyeshots_res_pub/GibaldiA10.pdf

A cortical model for binocular vergence control without explicit calculation of disparity

Motion estimation has been studied extensively in neuroscience in the last two decades. Even though there has been some early interaction between the biological and computer vision communities at a modelling level, comparatively little work has been done on the examination or extension of the biological models in terms of their engineering efficacy on modern optical flow estimation datasets. An essential contribution of this paper is to show how a neural model can be enriched to deal with real sequences. We start from a classical V1-MT feedforward architecture. We model V1 cells by motion energy (based on spatio-temporal filtering), and MT pattern cells (by pooling V1 cell responses). The efficacy of this architecture and its inherent limitations in the case of real videos are not known. To answer this question, we propose a velocity space sampling of MT neurons (using a decoding scheme to obtain the local velocity from their activity) coupled with a multi-scale approach. After this, we explore the performance of our model on the Middlebury dataset. To the best of our knowledge, this is the only neural model in this dataset. The results are promising and suggest several possible improvements, in particular to better deal with discontinuities. Overall, this work provides a baseline for future developments of bio-inspired scalable computer vision algorithms and the code is publicly available to encourage research in this direction. Graphical abstractDisplay Omitted HighlightsWe show how a V1-MT neural model can be adapted to handle real sequences.For the first time, a neural model is benchmarked on a Middlebury dataset.We share our code to encourage research in bio-inspired scalable vision algorithms.

/pdf/what-can-we-expect-from-a-v1-mt-feedforward-architecture-for-29mw6pgjdj.pdf

Manuela Chessa

Papers

The Perceptual Quality of the Oculus Rift for Immersive Virtual Reality

Calibrated depth and color cameras for accurate 3D interaction in a stereoscopic augmented reality environment

Simulated disparity and peripheral blur interact during binocular fusion

A cortical model for binocular vergence control without explicit calculation of disparity

What can we expect from a V1-MT feedforward architecture for optical flow estimation?