General Electric Company

Nbcuniversal Media, LLC

Jilin Tu

Peter Henry Tu

Frederick Wilson Wheeler

Xiaoming Liu

Huan Tan

Li Zhang

Yan Tong

Tao Gao

Jens Rittscher

Arpit Jain

Musodiq O Bello

Gyeong Woo Cheon

Ahmad Yekta

Ser Nam Lim

Li Guan

Yi Xu

Thomas Baby Sebastian

Romano Patrick

Dirk Ryan Padfield

Ghulam Ali Baloch

Dirk Padfield

Jimmie Autrey Beacham

Guangliang Zhao

Tao Jia

Weina Ge

Ana Isabel Del Amo

Bikash Chandra Mahato

Zhiguang Wang

Alexander S-Ban Chen

Craig Ronald Hoffmann

Ying Li

An analogy generating system includes one or more image databases that include a first set of images depicting a first symbolic class and a second set of images depicting a second symbolic class and an autoencoder that receive images from the first set of images and the second set of images; determines a first characteristic shared between the first symbolic class and the second symbolic class using a first node from multiple nodes on a neural network; determine a second characteristic shared between the first symbolic class and the second symbolic class using a second node from multiple nodes on the neural network; and exchange the first characteristic and the second characteristic between the first node and the second node to establish an analogy between the first symbolic class and the second symbolic class.

Analogy engine for grounding and situational awareness

A method and system, the method including receive image data representations of a set of images of a physical asset; receive a data model of at least one asset, the data model of each of the at least one assets including a semantic description of the respective modeled asset and at least one operation associated with the respective modeled asset; determine a match between the received image data and the data model of one of the at least one assets based on a correspondence therebetween; generate, for the data model determined to be a match with the received image data, an operation plan based on the at least one operation included in matched data model; execute, in response to the generation of the operation plan, the generated operation plan by the physical asset.

Systems and methods of 3D scene segmentation and matching for robotic operations

A method and system, the method including receiving semantic descriptions of features of an asset extracted from a first set of images; receiving a model of the asset, the model constructed based on a second set of a plurality images of the asset; receiving, based on an optical flow-based motion estimation, an indication of a motion for the features in the first set of images; determining a set of candidate regions of interest for the asset; determining a region of interest in the first set of images; iteratively determining a matching of features in the set of candidate regions of interest and the determined region of interest in the first set of images to generate a record of matches in features between two images in the first set of images; and displaying a visualization of the matches in features between two images in the first set of images.

Systems and methods of feature correspondence analysis

An asset inspection system includes a robot and a server. The robot collects inspection data corresponding to an asset. The server, includes a user interface, a processor, and a memory. The memory includes instructions that, when executed by the processor, cause the processor to receive the inspection data from the robot, display the inspection data via the user-interface, receive feedback on the inspection data via the user interface, generate a human-assisted inspection based on the received feedback, analyze the inspection data via a trained model, generate an automated inspection based on the analysis by the trained model, combine the automated inspection and the human-assisted inspection to generate an inspection report, and transmit the inspection report for review.

Systems and method for human-assisted robotic industrial inspection

An authentication system includes a processor, a non-transitory computer readable medium, and one or more programs stored on the computer readable medium, where the processor, under control of the programs implements at least one neural network trained to produce first feature vectors from facial features extracted from a population of first facial images and, after training, configured to produce a second feature vector from facial features extracted from a second facial image, a discriminative classifier trained to identify closely matching ones of the first feature vectors and configured to identify whether at least one first feature vector and the second feature vector meet a correlation threshold. The authentication system may also include an access interface configured to allow access if the correlation threshold is met.

Automatic authentification for MES system using facial recognition

Provided are techniques for assessing individual or crowd level behavior based on image data analysis. For example, in one embodiment, the techniques may include generating signatures representative of an observed behavior based on video data and performing pairwise matching by determining whether the first signature matches a second signature indicative of a query behavior.

Crowd analytics via one shot learning

A security monitoring technique includes receiving data related to one or more individuals from one or more cameras in an environment. Based on the input data from the cameras, agent-based simulators are executed that each operate to generate a model of behavior of a respective individual, wherein an output of each model is symbolic sequences representative of internal experiences of the respective individual during simulation. Based on the symbolic sequences, a subsequent behavior for each of the respective individuals is predicted when the symbolic sequences match a query symbolic sequence for a query behavior.

Techniques for assessing group level cognitive states

A method and system for detecting a damaged machine component during operation of the machine are provided. The damaged machine component detection system includes one or more processors, one or more memory devices communicatively coupled to the one or more processors, an image capture device configured to generate a stream of temporally-spaced images of a scene including a machine component of interest, the images generated in real-time, and a grouping model configured to compare features of a current image of the stream of images to features of previously captured images sorted into a plurality of groups of images having similar features, generate an alert if predetermined features of the current image deviate from corresponding features of the grouped images by a predetermined amount, and update the groups with the current image if the predetermined features of the current image are similar to corresponding features of the grouped images by a predetermined amount. The system also includes an output device configured to output at least one of the alert and the current image.

Method and system for detecting a damaged component of a machine

A method implemented using a processor based device is disclosed. The method includes receiving a video stream comprising a plurality of image frames having at least one moving object, determining a difference between at least two image frames among the plurality of image frames and generating a difference image comprising a plurality of image blobs corresponding to the at least one moving object. The method further includes generating a plurality of bounding boxes, each bounding box surrounding at least one corresponding image blob among the plurality of image blobs, and determining a subset of bounding boxes among the plurality of bounding boxes, associated with the corresponding moving object, using a fuzzy technique based on a perceptual characterization of the subset of bounding boxes. The method also includes merging the subset of bounding boxes to generate a merged bounding box enclosing the subset of bounding boxes to detect the moving object.

System and method for detection and tracking of moving objects

A system and method for estimating a set of landmarks for a large image ensemble employs only a small number of manually labeled images from the ensemble and avoids labor-intensive and error-prone object detection, tracking and alignment learning task limitations associated with manual image labeling techniques. A semi-supervised least squares congealing approach is employed to minimize an objective function defined on both labeled and unlabeled images. A shape model is learned on-line to constrain the landmark configuration. A partitioning strategy allows coarse-to-fine landmark estimation.

System and method for automatic landmark labeling with minimal supervision

A method for image alignment is disclosed. In one embodiment, the method includes acquiring a facial image of a person and using a discriminative face alignment model to fit a generic facial mesh to the facial image to facilitate locating of facial features. The discriminative face alignment model may include a generative shape model component and a discriminative appearance model component. Further, the discriminative appearance model component may have been trained to estimate a score function that minimizes the angle between a gradient direction and a vector pointing toward a ground-truth shape parameter. Additional methods, systems, and articles of manufacture are also disclosed.

Optimal gradient pursuit for image alignment

Systems and methods for extracting information about an organism of interest, such as an atlas of the organism of interest; a storage device for at least temporarily storing an image of the organism of interest; and an operating device that automatically creates a map of the image of the organism of interest and automatically compares the map of the image to the atlas of the organism.

Systems and methods for automated extraction of high-content information from whole organisms

The present invention is directed to method and system for image processing of test wells on a microplates wherein the microplates' test well wall boundaries are identified through the use of a candidate edge image wherein the candidate edge image represents locations of one or more segments of the wall boundaries.

Methods and systems for identifying well wall boundaries of microplates

A technique for optimizing object recognition is disclosed. The technique includes receiving at least one image of an object and at least one reference image. The technique further includes identifying at least one performance metric corresponding to an object recognition task. The identified performance metric is optimized to generate the corresponding optimized performance metric by determining an optimal subspace based on a determined objective function corresponding to the object recognition task and a difference between the received image and the corresponding reference image. Subsequently, the technique includes comparing the received image with the reference image based on the optimized performance metric for performing the object recognition task.

Growing community of inventors

Schenectady, NY, United States of America

Jilin Tu