Siemens Corporate Research, Inc.

Siemens Corporation

Siemens Medical Solutions Usa, Inc.

Siemens Aktiengesellschaft

Siemens Energy, Inc.

Siemens Power Generation, Inc.

Continental Automotive Gmbh

Siemens Schweiz Ag

Visvanathan Ramesh

Dorin Comaniciu

Nikolaos Paragios

Anurag Mittal

Imad Zoghlami

Ying Zhu

Maneesh Kumar Singh

Terrance Edward Boult

Binglong Xie

Michael Greiffenhagen

Xiang Sean Zhou

Arun Krishnan

Yakup Genc

Thorsten Köhler

Dennis H Lemieux

Yanghai Tsin

Kazunori Okada

Alok Gupta

Mikael Rousson

Benedicte Bascle

Martin Pellkofer

Claus Bahlmann

Diane S Paine

Matthias Voigt

Bhavani Duggirala

Frans Martin Coetzee

Antoine Monnet

Nikos Paragios

Bjoern Stenger

Vasudev Parameswaran

Xiang Gao

Bernhard Geiger

Jan Neumann

Stephen Price Masticola

Vinay Damodar Shet

Vinay Jonnalagadda

Xiang Zhang

Hans-Gerd Johann Brummel

Thorsten Koehler

Markus Simon

Nikolaos Paragyios

Umut Akdemir

Tony X Han

Alessio Del Bue

Toufiq Parag

Michael A Gall

Roberto Antonio Suarez

Martin Zarzycki

Che-Bin Liu

Lan Dong

Fabio Berton

First order predicate logics are provided, extended with a bilattice based uncertainty handling formalism, as a means of formally encoding pattern grammars, to parse a set of image features, and detect the presence of different patterns of interest implemented on a processor. Information from different sources and uncertainties from detections, are integrated within the bilattice framework. Automated logical rule weight learning in the computer vision domain applies a rule weight optimization method which casts the instantiated inference tree as a knowledge-based neural network, to converge upon a set of rule weights that give optimal performance within the bilattice framework. Applications are in (a) detecting the presence of humans under partial occlusions and (b) detecting large complex man made structures in satellite imagery (c) detection of spatio-temporal human and vehicular activities in video and (c) parsing of Graphical User Interfaces.

Predicate logic based image grammars for complex visual pattern recognition

A method for performing crowd segmentation includes receiving video image data (S). Background differencing is performed on the received video image data to identify a foreground silhouette shape (S). Approximate number and position of human subjects within the received video image data are determined by matching the foreground silhouette shape against a set of predetermined foreground silhouette shapes, for each of which a number and position of human subjects is known (S). The estimated number and position of the human subjects is refined to determine a final number and position of the human subjects (S).

Fast crowd segmentation using shape indexing

A method for modeling a vehicle, includes: receiving an image that includes a vehicle; and constructing a three-dimensional (3D) model of the vehicle, wherein the 3D model is constructed by: (a) taking a predetermined set of base shapes that are extracted from a subset of vehicles; (b) multiplying each of the base shapes by a parameter; (c) adding the resultant of each multiplication to form a vector that represents the vehicle's shape; (d) fitting the vector to the vehicle in the image; and (e) repeating steps (a)-(d) by modifying the parameters until a difference between a fit vector and the vehicle in the image is minimized.

Active shape model for vehicle modeling and re-identification

A system and corresponding method for image acquisition are provided, the system including a processor, an imaging adapter in signal communication with the processor for receiving image data from each of a static imaging device and a dynamic imaging device, and a homography unit in signal communication with the processor for computing a planar homography between the static and dynamic image data; and the method including receiving an image from a static imaging device, receiving an image from a dynamic imaging device, and registering the dynamic image to the static image using planar homography.

Multiple camera system for obtaining high resolution images of objects

The present invention provides a technique for automated selection of a parameterized operator sequence to achieve a pattern classification task. A collection of labeled data patterns is input and statistical descriptions of the inputted labeled data patterns are then derived. Classifier performance for each of a plurality of candidate operator/parameter sequences is determined. The optimal classifier performance among the candidate classifier performances is then identified. Performance metric information, including, for example, the selected operator sequence/parameter combination, will be outputted. The operator sequences selected can be chosen from a default set of operators, or may be a user-defined set. The operator sequences may include any morphological operators, such as, erosion, dilation, closing, opening, close-open, and open-close.

Automatic design of morphological algorithms for machine vision

A system and method for providing decision support to a physician during a medical examination is disclosed. Data is received from a sensor representing a particular medical measurement. The received data includes image data. The received data and context data is analyzed with respect to one or more sets of training models. Probability values for the particular medical measurement and other measurements to be taken are derived based on the analysis and based on identified classes. The received image data is compared with training images. Distance values are determined between the received image data and the training images, and the training images are associated with the identified classes. Absolute value feature sensitivity scores are derived for the particular medical measurement and other measurements to be taken based on the analysis. The probability values, distance values and absolute value feature sensitivity scores are outputted to the user.

System and method for performing probabilistic classification and decision support using multidimensional medical image databases

By testing for nodule segmentation errors based on the scan data, juxtapleural cases are identified. Once identified, the scan data or subsequent estimation may be altered to account for adjacent rib, tissue, vessel or other structure effecting segmentation. One alteration is to shape a filter as a function of the scan data. For example, an originally estimated ellipsoid for the nodule segmentation defines the filter. The filter is used to identify the undesired information, and masking removes the undesired information for subsequent estimation of the nodule segmentation. Another possible alteration biases the subsequent estimation away from the incorrect information, such as the rib, tissue or vessel information influencing the original estimation. For example, a negative prior or probability is assigned to data corresponding to the originally estimated segmentation for the subsequent estimation.

Refined segmentation of nodules for computer assisted diagnosis

The present invention relates to a method for visually detecting and tracking an object through a space. The method chooses modules for a restricting a search function within the space to regions with a high probability of significant change, the search function operating on images supplied by a camera. The method also derives statistical models for errors, including quantifying an indexing step performed by an indexing module, and tuning system parameters. Further the method applies a likelihood model for candidate hypothesis evaluation and object parameters estimation for locating the object.

Statistical modeling and performance characterization of a real-time dual camera surveillance system

Methods for maximum scene surface temperature estimation for blades with reflective surface properties in advanced stationary gas turbines are disclosed. The approach utilizes high speed infrared imagery provided by an online monitor system using a focal plan array (FPA) for near-infrared monitoring during engine runtime up to base load. The one waveband method for temperature estimation is assumed as starting point. A lower surface emissivity and higher surface reflectance of thermal barrier coating (TBC) in near-infrared can cause systematic estimation errors. Methods using the one wave band method, with the purpose to reduce estimation errors for maximum temperatures are also disclosed. Theoretical results, data from numerical simulations, and real data from engine test are provided. A system for performing temperature estimation methods is also disclosed.

Maximum blade surface temperature estimation for advanced stationary gas turbines in near-infrared (with reflection)

The present invention comprises using error propagation for building feature spaces with variable uncertainty and using variable-bandwidth mean shift for the analysis of such spaces, to provide peak detection and space partitioning. The invention applies these techniques to construct and analyze Hough spaces for line and geometrical shape detection, as well as to detect objects that are represented by peaks in the Hough space. This invention can be further used for background modeling by taking into account the uncertainty of the transformed image color and uncertainty of the motion flow. Furthermore, the invention can be used to segment video data in invariant spaces, by propagating the uncertainty from the original space and using the variable-bandwidth mean shift to detect peaks. The invention can be used in a variety of applications such as medical, surveillance, monitoring, automotive, augmented reality, and inspection.

Error propogation and variable-bandwidth mean shift for feature space analysis

The performance of template matching is characterized by deriving the distribution of warp parameter estimate as a function of the ideal template, the ideal warp parameters and a given perturbation or noise model. An expression for the Probability Mass Function of the parameter estimate is provided. The optimal template size for template matching is the one that provides the best matching performance which is calculated from the minimum entropy of the parameter estimate.

On optimizing template matching via performance characterization

A tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking is provided. The solution to the tracking problem is articulated into a method that encodes the spatial configuration of features along with their density and yet retains robustness to spatial deformations and feature density variations. The method of encoding of spatial configuration is provided using a set of kernels whose parameters can be optimized for a given class of objects off-line. The method enables the use of mean-shift iterations and runs in real-time. Better tracking results by the novel tracking method as compared to the original mean-shift tracker are demonstrated.

Tunable kernels for tracking

An apparatus and method for video object generation and selective encoding is provided. The apparatus includes a detection module for detecting a first object in at least one image frame of a series of image frames; a tracking module for tracking the first object in successive image frames and segmenting the first object from a background, the background being a second object; and an encoder for encoding the first and second objects to be transmitted to a receiver, wherein the first object is compressed at a high compression rate and the second object is compressed at a low compression rate. The receiver merges the first and second object to form a composite image frame. The method provides for detecting, tracking and segmenting one or more objects, such as a face, from a background to be encoded at the same or different compression rates to conserve bandwidth.

Real-time video object generation for smart cameras

A system and method are provided for prior-constrained mean shift analysis of a data array, the system including a processor, an input adapter in signal communication with the processor for receiving at least one data array, and a prior constraints unit in signal communication with the processor for performing a prior-constrained mean shift analysis on the at least one data array; and the method including receiving initialization data, selecting an initial point relative to the initialization data, Gaussian fitting with a prior-constrained mean shift responsive to the initial point to parse a structure, and setting the parsed structure as a prior constraint.

Prior-constrained mean shift analysis

A method of detecting a feature of a vehicle in an image of a vehicle includes providing a digitized image of a vehicle, providing a first filter mask over a first subdomain of the image, where the filter mask is placed to detect a feature in the image, calculating a function of a gradient of the image inside the first masked subdomain, and detecting the presence or absence of a vehicle feature within the first masked subdomain based on the value of the gradient function.

System and method for detecting features from images of vehicles

Growing community of inventors

Plainsboro, NJ, United States of America

Visvanathan Ramesh