Sony Corporation

Sony Electronics Inc

Skybox Imaging, Inc.

Google Inc.

Urban Sky Theory Inc.

Mark Allen Robertson

Ming-Chang Liu

Yoshihiro Murakami

Yutaka Yoneda

Toru Kurata

M Dirk Robinson

Julian M Mann

Daniel Berkenstock

Oliver Guinan

Hadar Isaac

Thomas Joseph Melendez

Ken James Kryda

Ximin Zhang

Jared Leidich

Maxmillion J W McLaughlin

A method for creating a composite image includes receiving a group of images indexed according to a time-consecutive capture sequence. Each image is evaluated for inclusion in the composite image, and the evaluation of each image entails determining whether a spatial footprint of the image is entirely internal to a polygon formed based on a union of spatial footprints corresponding to images positioned on a same side of the image within the time-consecutive capture sequence. If the spatial footprint of the image is not entirely internal to the polygon, an identifier for the image is added to a composite image array. Otherwise, the identifier for the image is excluded from the composite image array. After all images have been evaluated, the composite image is created by stitching together images with respective identifiers included in the composite image array.

Composite image creation for aerial image capture system

Systems and methods are provided for generating high-dynamic range images. In particular, a signal-to-noise (SNR) ratio objective associated with an imaging platform configured to capture one or more images of a region of interest using an image sensor having a first portion and a second portion can be determined. The SNR objective can specify a desired SNR response as a function of a brightness of the region of interest. A first integration time and a second integration time can then be determined based at least in part on the SNR objective. Data indicative of a plurality of image frames can then be obtained. Each image frame is captured by exposing the first portion of the image sensor for the first integration time and exposing the second portion of the image sensor for the second integration time.

Generating high-dynamic range images using multiple filters

Systems and methods are provided for generating high-dynamic range images. In particular, a signal-to-noise (SNR) ratio objective associated with an imaging platform configured to capture one or more images of a region of interest can be determined. The SNR objective can specify a desired signal-to-noise ratio behavior as a function of a brightness of the region of interest. An exposure profile associated with the imaging platform can then be determined based at least in part on the SNR objective. Data indicative of a plurality of image frames, each depicting at least a portion of the region of interest, can then be obtained. The plurality of image frames being captured by the imaging platform in accordance with the exposure profile.

Generating high-dynamic range images using varying exposures

A method of improving accuracy and reliability of motion estimation is described herein. In one aspect, a 2D neighborhood of phase correlation peak is approximated with an outer-product of two 1D vectors to eliminate the sub-pixel error. In another aspect, estimation of reliability is improved. In yet another aspect, two-pass phase correlation is implemented to eliminate sub-pel motion bias.

Method to improve accuracy and reliability of motion estimated with phase correlation

A method for navigating images in microscopic imaging, the method comprising reducing dimensionality of an original sequence of images of a specimen for navigation using an all-focus image and providing a user interface to a user for navigating the original sequence of images and the all-focus image.

Method and apparatus for navigating stacked microscopy images

Described are systems, methods, computer programs, and user interfaces for image location, acquisition, analysis, and data correlation that uses human-in-the-loop processing, Human Intelligence Tasks (HIT), and/or or automated image processing. Results obtained using image analysis are correlated to non-spatial information useful for commerce and trade. For example, images of regions of interest of the earth are used to count items (e.g., cars in a store parking lot to predict store revenues), detect events (e.g., unloading of a container ship, or evaluating the completion of a construction project), or quantify items (e.g., the water level in a reservoir, the area of a farming plot).

Adaptive image acquisition and processing with image analysis feedback

A method and apparatus for simulating depth of field (DOF) in microscopic imaging, the method comprising computing a blur quantity for each pixel of an all-focus image, performing point spread function operations on one or more regions of the all-focus image, computing intermediate and normalized integral images on the regions and determining an output pixel for the each pixel based on the intermediate and normalized integral images.

Method and apparatus for simulating depth of field (DOF) in microscopy

A method for improving depth for field (DOF) in microscopic imaging, the method comprising combining a sequence of images captured from different focal distances to form an all-focus image, comprising computing a focus measure at every pixel, finding the largest peaks at each position in the focus measure as multiple candidate values and blending the multiple candidates values according to the focus measure to determine the all-focus image.

Method and apparatus for improving depth of field (DOF) in microscopy

A method and system to improve the performance of phase correlation motion estimation for low-bit-precision implementation are described herein. Phase correlation uses the Fast Fourier Transform (FFT) with operations with infinite-precision constants. Since physical implementations use finite-precision arithmetic, there is some loss in precision relative to the ideal infinite-precision case. In low-complexity implementations, it is desirable to use as few bits as possible, and if the precision is too low, the performance of traditional phase correlation suffers. A pre-processing technique is applied to the data prior to taking the FFT, which minimizes the negative effects of finite precision in the FFT and allows high quality results from phase correlation. The pre-processing step is a content-dependent contrast adjustment that maps the range of the input images' pixel values to the range of input values for the FFT. There is no post-processing required after the FFT to compensate for the pre-processing step.

Method to increase the accuracy of phase correlation motion estimation in low-bit-precision circumstances

Using human intelligence tasks for precise image analysis

Phase correlation is an established method for computing motion which relies on the ability to find peaks in a computed phase correlation surface. Two methods to improve the ability to detect peaks in the phase correlation surface are described herein. The first method applies a theoretically-derived and spatially-varying gain to the phase correlation surface. The gain compensates for peaks whose amplitudes have been decreased due to windowing effects; such effects are unavoidable in phase correlation. The second method uses concepts from matched filters to improve detection of peaks whose amplitudes are diminished due to a spreading of the peak energy into surrounding positions in the phase correlation surface. Peak detection filters allow such low-amplitude peaks to be properly detected. It is possible to use only the first method, or only the second method or both methods combined.

Method to improve detection of motion with phase correlation

A method and apparatus for compressing Z-stack microscopy images comprising compressing an all-focus image and depth map representation of an original Z-stack of images, computing a prediction residual as a difference between a simulated Z-stack, generated from the all-focus image and the depth-map, and the original Z-stack and concatenating the prediction residual to the compressed all-focus image and the depth map to produce a final compressed file.

Method and apparatus for compressing Z-stack microscopy images

A stain separation system of digital pathology images that performs transforming a digital image from a first color domain to an optical domain to form an optical domain image (ODI), identifying a plane containing two or more basis vector which contain the pixels of the ODI, determining a plurality of orthogonal vector within the identified plane, forming a histogram of the digital image represented by the orthogonal vectors and determining one or more final stain vectors by searching for candidate vectors in the plane that minimize a cost function of the histogram.

Method and apparatus for stain separation in digital pathology images

A method to estimate segmented motion uses phase correlation to identify local motion candidates and a region-growing algorithm to group small picture units into few distinct regions, each of which has its own motion according to optimal matching and grouping criteria. Phase correlation and region growing are combined which allows sharing of information. Using phase correlation to identify a small number of motion candidates allows the space of possible motions to be narrowed. The region growing uses efficient management of lists of matching criteria to avoid repetitively evaluating matching criteria.

Growing community of inventors

Cupertino, CA, United States of America

Mark Allen Robertson