Humans perceive the three-dimensional structure of the world with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a computer interpret an image at the same level as a two-year old remains elusive. Why is computer vision such a challenging problem and what is the current state of the art? Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging, and for fun, consumer-level tasks such as image editing and stitching, which students can apply to their own personal photos and videos. More than just a source of recipes, this exceptionally authoritative and comprehensive textbook/reference also takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting them to produce descriptions of a scene. These problems are also analyzed using statistical models and solved using rigorous engineering techniques Topics and features: structured to support active curricula and project-oriented courses, with tips in the Introduction for using the book in a variety of customized courses; presents exercises at the end of each chapter with a heavy emphasis on testing algorithms and containing numerous suggestions for small mid-term projects; provides additional material and more detailed mathematical topics in the Appendices, which cover linear algebra, numerical techniques, and Bayesian estimation theory; suggests additional reading at the end of each chapter, including the latest research in each sub-field, in addition to a full Bibliography at the end of the book; supplies supplementary course material for students at the associated website, http://szeliski.org/Book/. Suitable for an upper-level undergraduate or graduate-level course in computer science or engineering, this textbook focuses on basic techniques that work under real-world conditions and encourages students to push their creative boundaries. Its design and exposition also make it eminently suitable as a unique reference to the fundamental techniques and current research literature in computer vision.

/pdf/computer-vision-algorithms-and-applications-25dn6wu83j.pdf

Computer Vision: Algorithms and Applications

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

We present a new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail. It is based on a two-scale decomposition of the image into a base layer,...

/pdf/fast-bilateral-filtering-for-the-display-of-high-dynamic-43a1vkjsrr.pdf

Fast bilateral filtering for the display of high-dynamic-range images

We present a new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail. It is based on a two-scale decomposition of the image into a base layer, encoding large-scale variations, and a detail layer. Only the base layer has its contrast reduced, thereby preserving detail. The base layer is obtained using an edge-preserving filter called the bilateral filter. This is a non-linear filter, where the weight of each pixel is computed using a Gaussian in the spatial domain multiplied by an influence function in the intensity domain that decreases the weight of pixels with large intensity differences. We express bilateral filtering in the framework of robust statistics and show how it relates to anisotropic diffusion. We then accelerate bilateral filtering by using a piecewise-linear approximation in the intensity domain and appropriate subsampling. This results in a speed-up of two orders of magnitude. The method is fast and requires no parameter setting.

/pdf/fast-bilateral-filtering-for-the-display-of-high-dynamic-fprymiweg7.pdf

We present a new method for rendering high dynamic range images on conventional displays. Our method is conceptually simple, computationally efficient, robust, and easy to use. We manipulate the gradient field of the luminance image by attenuating the magnitudes of large gradients. A new, low dynamic range image is then obtained by solving a Poisson equation on the modified gradient field. Our results demonstrate that the method is capable of drastic dynamic range compression, while preserving fine details and avoiding common artifacts, such as halos, gradient reversals, or loss of local contrast. The method is also able to significantly enhance ordinary images by bringing out detail in dark regions.

/pdf/gradient-domain-high-dynamic-range-compression-50i9o7k3p7.pdf

Gradient domain high dynamic range compression

There is provided an image pickup apparatus including: a control unit generating exposure time control data in which an exposure time of an image sensor is set in pixel region units; and an image sensor inputting the exposure time control data and carrying out image acquisition based on exposure time control in the pixel region units. The control unit successively and sequentially generates the exposure time control data in region units based on luminance information in the pixel region units that form part of a preceding picked-up image and outputs the exposure time control data to the image sensor. The image sensor inputs the exposure time control data in the region units from the control unit and successively and sequentially uses the inputted exposure time control data to carry out the image acquisition based on the exposure time control in the pixel region units.

Image pickup apparatus, image pickup apparatus control method, and program

A color filter array includes a plurality of filters, each having one of a plurality of types of spectral sensitivity and being disposed at the location of a corresponding one of a plurality of pixels. The filters of a predetermined type selected from among the plurality of types are arranged at the locations of the pixels in a checkered pattern, and the filters of some or all of the other types are randomly arranged at the pixel locations at which the filters of the predetermined type are not present.

Color filter array, imaging device, and image processing unit

PROBLEM TO BE SOLVED: To provide an image processor and an image processing method to be suitably used at the time of executing de-mosaic processing(color interpolation processing or simultaneous processing) to interpolate a plurality of colors into overall pixels, and to obtain a color image signal from a mosaic image signal obtained by using a color solid-state imaging element. SOLUTION: Four color array shown in the figure is configured by alternatively arranging R and B at the opposite angles with an alternative cycle by every pixel in the direction of upward slant to the right and in an alternative cycle by every two pixel in the direction of downward slant to the right. A rough interpolation processing part calculates a plurality of sets of the strength of a first color Cr which is the same as the color at the pixel position under consideration and the strength of a second color Ce based on a mosaic image extracted from such filter array. A statistic calculating part calculates statistic concerning the color distribution shape of the strength of Cr and the strength of Ce. A recursion arithmetic operation processing part calculates the Ce estimate of the pixel position under consideration based on the strength of the color Cr at the pixel position under consideration and the statistic of the color distribution shape. Thus, it is possible to obtain an output image with much higher picture quality by solving such two phenomena as color moire and false color generated due to the engineering of a chrominance signal. This invention may be applied to a digital still camera. COPYRIGHT: (C)2005,JPO&NCIPI

Image processor and image processing method

Methods and systems for coded rolling shutter are provided. In accordance with some embodiments, methods and system are provided that control the readout timing and exposure length for each row of a pixel array in an image sensor, thereby flexibly sampling the three-dimensional space-time value of a scene and capturing sub-images that effectively encode motion and dynamic range information within a single captured image.

Methods and systems for coded rolling shutter

PROBLEM TO BE SOLVED: To reduce the capacity of a memory to be used and an operation quantity, to easily form into hardware, and to emphasize the contrast of an image subjected to proper gradation compression. SOLUTION: In a step S21, the luminance of a wide DR image L is subjected to logarithmic conversion. In a step S22, a logarithmic tone curve correction image logL c is generated. In step S23, a logarithmic reduction image logL cl is generated, and luminance logL cl (p) of a pixel of a logarithmic smoothed image is further calculated by interpolation operation. In step S24, a gain value g(p) is calculated for each pixel position. In a step S25, luminance logL u (p) of a pixel of a logarithmic gradation compressed image logL u (p) is calculated. In a step S26, the luminance logL u (p) is subjected to logarithmic inverse conversion. This apparatus is applicable to an image pickup device such as a digital video camera, and a reproducing device such as a display and a printer. COPYRIGHT: (C)2004,JPO&NCIPI

Tomoo Mitsunaga

Papers

Image pickup apparatus, image pickup apparatus control method, and program

Color filter array, imaging device, and image processing unit

Image processor and image processing method

Methods and systems for coded rolling shutter

Image processing apparatus and method therefor, recording medium, and program