Patents by Inventor Pramod Sankar Kompalli
Pramod Sankar Kompalli has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11037002Abstract: Calibration and distance prediction for driving assistance is provided. A camera of a vehicle is calibrated to obtain a distance data set. The distance data set includes a distance of each row of pixels of a first image captured by the camera. The distance data set may be further utilized in real-time to predict a distance of an object from the vehicle. Based on the predicted distance, a warning message for an impending collision may be generated and communicated to a driver of the vehicle, thereby facilitating driving assistance to the driver in the real-time.Type: GrantFiled: June 26, 2019Date of Patent: June 15, 2021Assignee: ANI TECHNOLOGIES PRIVATE LIMITEDInventors: Pramod Sankar Kompalli, Sathya Narayanan Nagarajan, Apurv Nigam, Srikanth Vidapanakal
-
Patent number: 10872532Abstract: Lane prediction for driving assistance is provided. A camera of a vehicle is calibrated to obtain column values for each row of pixels of an image based on a plurality of lines captured in the image. The plurality of lines may be either parallel or perpendicular to a calibration lane captured in the image. The column values of each row of pixels may be utilized to predict a driving lane for the vehicle. When an on-road object is detected in the predicted driving lane, a warning message for an impending collision may be generated and communicated to a driver of the vehicle, thereby facilitating driving assistance to the driver in real-time.Type: GrantFiled: June 6, 2019Date of Patent: December 22, 2020Assignee: ANI TECHNOLOGIES PRIVATE LIMITEDInventors: Pramod Sankar Kompalli, Sathya Narayanan Nagarajan, Apurv Nigam, Srikanth Vidapanakal
-
Publication number: 20200273342Abstract: Lane prediction for driving assistance is provided. A camera of a vehicle is calibrated to obtain column values for each row of pixels of an image based on a plurality of lines captured in the image. The plurality of lines may be either parallel or perpendicular to a calibration lane captured in the image. The column values of each row of pixels may be utilized to predict a driving lane for the vehicle. When an on-road object is detected in the predicted driving lane, a warning message for an impending collision may be generated and communicated to a driver of the vehicle, thereby facilitating driving assistance to the driver in real-time.Type: ApplicationFiled: June 6, 2019Publication date: August 27, 2020Applicant: ANI TECHNOLOGIES PRIVATE LIMITEDInventors: Pramod Sankar Kompalli, Sathya Narayanan Nagarajan, Apurv Nigam, Srikanth Vidapanakal
-
Publication number: 20200258256Abstract: Calibration and distance prediction for driving assistance is provided. A camera of a vehicle is calibrated to obtain a distance data set. The distance data set includes a distance of each row of pixels of a first image captured by the camera. The distance data set may be further utilized in real-time to predict a distance of an object from the vehicle. Based on the predicted distance, a warning message for an impending collision may be generated and communicated to a driver of the vehicle, thereby facilitating driving assistance to the driver in the real-time.Type: ApplicationFiled: June 6, 2019Publication date: August 13, 2020Applicant: ANI TECHNOLOGIES PRIVATE LIMITEDInventors: Pramod Sankar Kompalli, Sathya Narayanan Nagarajan, Apurv Nigam, Srikanth Vidapanakal
-
Publication number: 20200257907Abstract: Calibration and distance prediction for driving assistance is provided. A camera of a vehicle is calibrated to obtain a distance data set. The distance data set includes a distance of each row of pixels of a first image captured by the camera. The distance data set may be further utilized in real-time to predict a distance of an object from the vehicle. Based on the predicted distance, a warning message for an impending collision may be generated and communicated to a driver of the vehicle, thereby facilitating driving assistance to the driver in the real-time.Type: ApplicationFiled: June 26, 2019Publication date: August 13, 2020Applicant: ANI TECHNOLOGIES PRIVATE LIMITEDInventors: Pramod Sankar Kompalli, Sathya Narayanan Nagarajan, Apurv Nigam, Srikanth Vidapanakal
-
Patent number: 10607330Abstract: A system estimates quality of a digital image by accessing a corpus of digital images of one or more subjects, such as a facet of a property. The system will receive, for at least a subset of the corpus, an indicator that one or more patches of each image in the subset is out of focus. The system will train a classifier by obtaining a feature representation of each pixel in each image, along with a focus value that represents an extent to which each pixel in the image is in focus or out of focus. The system will use the classifier to analyze pixels of a new digital image and assess whether each analyzed pixel in the new digital image is in focus or out of focus. The system may use the image to assess whether an incident occurred, such as storm-related damage to the property.Type: GrantFiled: December 5, 2017Date of Patent: March 31, 2020Assignee: Conduent Business Services, LLCInventors: Pramod Sankar Kompalli, Arjun Sharma, Richard L. Howe
-
Patent number: 10511676Abstract: A system for assessing a property damage claim uses an imaging device to capture images of a property that has reportedly been damaged by an incident. The system receives a property damage incident type, along with image processing criteria for processing images that are associated with the incident type. The system automatically processes the images according to the image processing criteria to identify one or more characteristics in the images and, based on the identified characteristics, determines whether certain claim processing criteria are satisfied. The claim processing criteria may help the system determine whether the property actually was damaged by the reported incident. The system will generate a command to process the property damage claim only if the system determines that one or more images show that the claim processing criteria are satisfied.Type: GrantFiled: March 17, 2016Date of Patent: December 17, 2019Assignee: Conduent Business Services, LLCInventors: Richard L. Howe, Valerie J. Raburn, Edgar A. Bernal, Matthew Adam Shreve, Peter Paul, Pramod Sankar Kompalli
-
Publication number: 20180096473Abstract: A system estimates quality of a digital image by accessing a corpus of digital images of one or more subjects, such as a facet of a property. The system will receive, for at least a subset of the corpus, an indicator that one or more patches of each image in the subset is out of focus. The system will train a classifier by obtaining a feature representation of each pixel in each image, along with a focus value that represents an extent to which each pixel in the image is in focus or out of focus. The system will use the classifier to analyze pixels of a new digital image and assess whether each analyzed pixel in the new digital image is in focus or out of focus. The system may use the image to assess whether an incident occurred, such as storm-related damage to the property.Type: ApplicationFiled: December 5, 2017Publication date: April 5, 2018Inventors: Pramod Sankar Kompalli, Arjun Sharma, Richard L. Howe
-
Patent number: 9870609Abstract: A system estimates quality of a digital image by accessing a corpus of digital images of one or more subjects, such as a facet of a property. The system will receive, for at least a subset of the corpus, an indicator that one or more patches of each image in the subset is out of focus. The system will train a classifier by obtaining a feature representation of each pixel in each image, along with a focus value that represents an extent to which each pixel in the image is in focus or out of focus. The system will use the classifier to analyze pixels of a new digital image and assess whether each analyzed pixel in the new digital image is in focus or out of focus. The system may use the image to assess whether an incident occurred, such as storm-related damage to the property.Type: GrantFiled: June 3, 2016Date of Patent: January 16, 2018Assignee: Conduent Business Services, LLCInventors: Pramod Sankar Kompalli, Arjun Sharma, Richard L. Howe
-
Patent number: 9846915Abstract: A system for capturing property damage images includes an imaging device and a knowledge base of property damage incident types. The knowledge base also includes, for each category, one or more image acquisition parameters that are associated with the category. A processor receives a property damage incident type for a property damage claim that is associated with a property that reportedly experienced an incident, retrieves from the knowledge base one or more image acquisition parameters that are associated with the received incident type, and uses the one or more applicable image acquisition parameters to automatically cause the imaging device to capture digital images of the property using the retrieved one or more image acquisition parameters.Type: GrantFiled: March 24, 2016Date of Patent: December 19, 2017Assignee: Conduent Business Services, LLCInventors: Richard L. Howe, Valerie J. Raburn, Edgar A. Bernal, Matthew Adam Shreve, Peter Paul, Pramod Sankar Kompalli
-
Patent number: 9847974Abstract: Disclosed are devices and methods for processing an image document in a client-server environment such that privacy of text information contained in the image document is preserved. Specifically, in a client-server environment, an image document can be processed using a local computerized device of a client to create an obfuscated document by identifying word images in the image document and scrambling those word images. The obfuscated document can be received by a server of a service provider over a network (e.g., the Internet) and processed by previously trained software (e.g., a previously trained convolutional neural network (CNN)) to recognize specific words represented by the scrambled images in the obfuscated document without having to reconstruct the image document. Since the image document is neither communicated over the network, nor reconstructed and stored on the server, privacy concerns are minimized.Type: GrantFiled: April 28, 2016Date of Patent: December 19, 2017Assignee: Xerox CorporationInventor: Pramod Sankar Kompalli
-
Publication number: 20170352143Abstract: A system estimates quality of a digital image by accessing a corpus of digital images of one or more subjects, such as a facet of a property. The system will receive, for at least a subset of the corpus, an indicator that one or more patches of each image in the subset is out of focus. The system will train a classifier by obtaining a feature representation of each pixel in each image, along with a focus value that represents an extent to which each pixel in the image is in focus or out of focus. The system will use the classifier to analyze pixels of a new digital image and assess whether each analyzed pixel in the new digital image is in focus or out of focus. The system may use the image to assess whether an incident occurred, such as storm-related damage to the property.Type: ApplicationFiled: June 3, 2016Publication date: December 7, 2017Inventors: Pramod Sankar Kompalli, Arjun Sharma, Richard L. Howe
-
Publication number: 20170317983Abstract: Disclosed are devices and methods for processing an image document in a client-server environment such that privacy of text information contained in the image document is preserved. Specifically, in a client-server environment, an image document can be processed using a local computerized device of a client to create an obfuscated document by identifying word images in the image document and scrambling those word images. The obfuscated document can be received by a server of a service provider over a network (e.g., the Internet) and processed by previously trained software (e.g., a previously trained convolutional neural network (CNN)) to recognize specific words represented by the scrambled images in the obfuscated document without having to reconstruct the image document. Since the image document is neither communicated over the network, nor reconstructed and stored on the server, privacy concerns are minimized.Type: ApplicationFiled: April 28, 2016Publication date: November 2, 2017Applicant: XEROX CORPORATIONInventor: PRAMOD SANKAR KOMPALLI
-
Publication number: 20170300752Abstract: A method and a system are provided for creating a summarized multimedia content. The method extracts one or more frames from a plurality of frames in a multimedia content based on a measure of area occupied by a text content in a portion of each of the plurality of frames. The method selects one or more sentences from an audio content associated with the multimedia content based on at least a weight associated with a plurality of words present in the audio content. The method extracts one or more audio segments from the audio content associated with the multimedia content based on one or more parameters associated with the audio content. The method creates the summarized multimedia content based on the one or more frames, the one or more sentences, and the one or more audio segments.Type: ApplicationFiled: April 18, 2016Publication date: October 19, 2017Inventors: Arijit Biswas, Harish Arsikere, Pramod Sankar Kompalli, Kuldeep Yadav, Jagadeesh Chandra Bose Rantham Prabhakara, Kovendhan Ponnavaikko, Om D. Deshmukh, Mohana Prasad Sathya Moorthy
-
Publication number: 20170270650Abstract: A system for assessing a property damage claim uses an imaging device to capture images of a property that has reportedly been damaged by an incident. The system receives a property damage incident type, along with image processing criteria for processing images that are associated with the incident type. The system automatically processes the images according to the image processing criteria to identify one or more characteristics in the images and, based on the identified characteristics, determines whether certain claim processing criteria are satisfied. The claim processing criteria may help the system determine whether the property actually was damaged by the reported incident. The system will generate a command to process the property damage claim only if the system determines that one or more images show that the claim processing criteria are satisfied.Type: ApplicationFiled: March 17, 2016Publication date: September 21, 2017Inventors: Richard L. Howe, Valerie J. Raburn, Edgar A. Bernal, Matthew Adam Shreve, Peter Paul, Pramod Sankar Kompalli
-
Publication number: 20170270612Abstract: A system for capturing property damage images includes an imaging device and a knowledge base of property damage incident types. The knowledge base also includes, for each category, one or more image acquisition parameters that are associated with the category. A processor receives a property damage incident type for a property damage claim that is associated with a property that reportedly experienced an incident, retrieves from the knowledge base one or more image acquisition parameters that are associated with the received incident type, and uses the one or more applicable image acquisition parameters to automatically cause the imaging device to capture digital images of the property using the retrieved one or more image acquisition parameters.Type: ApplicationFiled: March 24, 2016Publication date: September 21, 2017Inventors: Richard L. Howe, Valerie J. Raburn, Edgar A. Bernal, Matthew Adam Shreve, Peter Paul, Pramod Sankar Kompalli
-
Patent number: 9633282Abstract: Embodiments of a computer-implemented method for training a convolutional neural network (CNN) that is pre-trained using a set of color images are disclosed. The method comprises receiving a training dataset including multiple multidimensional images, each multidimensional image including a color image and a depth image; performing a fine-tuning of the pre-trained CNN using the depth image for each of the plurality of multidimensional images; obtaining a depth CNN based on the pre-trained CNN, wherein the depth CNN is associated with a first set of parameters; replicating the depth CNN to obtain a duplicate depth CNN being initialized with the first set of parameters; and obtaining a depth-enhanced color CNN based on the duplicate depth CNN being fine-tuned using the color image for each of the plurality of multidimensional images, wherein the depth-enhanced color CNN is associated with a second set of parameters.Type: GrantFiled: July 30, 2015Date of Patent: April 25, 2017Assignee: Xerox CorporationInventors: Arjun Sharma, Pramod Sankar Kompalli
-
Patent number: 9594944Abstract: The disclosed embodiments illustrate methods and systems for monitoring a worker performing a crowdsourced task being presented on a computing device. The method comprises performing at least one of a facial detection processing or an eye tracking processing, on a video stream captured by a camera of the computing device. An inattention instance of the worker is determined based on at least one of the facial detection processing or the eye tracking processing. Further, the inattention instance is communicated to a crowdsourcing platform, wherein the crowdsourced task is received from the crowdsourcing platform.Type: GrantFiled: September 25, 2013Date of Patent: March 14, 2017Assignee: XEROX CORPORATIONInventors: Pramod Sankar Kompalli, Shailesh Vaya, Gregory M Youngblood
-
Publication number: 20170032222Abstract: Embodiments of a computer-implemented method for training a convolutional neural network (CNN) that is pre-trained using a set of color images are disclosed. The method comprises receiving a training dataset including multiple multidimensional images, each multidimensional image including a color image and a depth image; performing a fine-tuning of the pre-trained CNN using the depth image for each of the plurality of multidimensional images; obtaining a depth CNN based on the pre-trained CNN, wherein the depth CNN is associated with a first set of parameters; replicating the depth CNN to obtain a duplicate depth CNN being initialized with the first set of parameters; and obtaining a depth-enhanced color CNN based on the duplicate depth CNN being fine-tuned using the color image for each of the plurality of multidimensional images, wherein the depth-enhanced color CNN is associated with a second set of parameters.Type: ApplicationFiled: July 30, 2015Publication date: February 2, 2017Inventors: Arjun Sharma, Pramod Sankar Kompalli
-
Patent number: 9214137Abstract: A system and method of rendering in real time a virtual object onto a viewfinder display, the method comprising determining one or more scene properties of a scene on a viewfinder display of a device, receiving a virtual object for insertion into the scene, determining a location for placing the virtual object within the scene, determining a first appearance of the virtual object based on the one or more scene properties, and inserting the virtual object with the first appearance into the scene depicted on the viewfinder display of the device based on the location.Type: GrantFiled: June 18, 2012Date of Patent: December 15, 2015Assignee: XEROX CORPORATIONInventors: Raja Bala, Hengzhou Ding, Yonghui Zhao, Michael R. Furst, Pramod Sankar Kompalli