Search

Paul N Vernaza

from Cupertino, CA
Age ~42
Get Report
Related to:
Alyson Dunaev, 40Colleen M Snyder, 55Robert Edward Snyder, 42Debra Lawrence, 53Dennis Argentieri, 70Jason Argentieri, 39Kevin Argentieri, 38
Connected to:
Geraldine R Vernazzaro, 79John D Vernazza, 70Marcelle W Vernazza, 115Paula Vernazza, 47Danielle Verne, 38Deirdre L Verne, 59Ryan J Verne, 72Sylvia J Vernedoe, 39Pratik N Vernekar, 37Sandeep Vernekar, 40

Paul Vernaza Phones & Addresses

  • Cupertino, CA
  • Sunnyvale, CA
  • Pittsburgh, PA
  • 122 Haines Rd, Mount Laurel, NJ 08054 (856) 273-9816
  • 122 Haines Rd, Mount Laurel, NJ 08054

Publications

Us Patents

Dense Three-Dimensional Correspondence Estimation With Multi-Level Metric Learning And Hierarchical Matching

View page
US Patent:
20200058156, Feb 20, 2020
Filed:
Jul 30, 2019
Appl. No.:
16/526306
Inventors:
- Princeton NJ, US
Mohammed E. Fathy Salem - Hyattsville MD, US
Muhammad Zeeshan Zia - San Jose CA, US
Paul Vernaza - Sunnyvale CA, US
Manmohan Chandraker - Santa Clara CA, US
International Classification:
G06T 15/08
G06K 9/62
G06K 9/72
G06N 3/04
G06N 3/08
G06T 15/10
Abstract:
A method for estimating dense 3D geometric correspondences between two input point clouds by employing a 3D convolutional neural network (CNN) architecture is presented. The method includes, during a training phase, transforming the two input point clouds into truncated distance function voxel grid representations, feeding the truncated distance function voxel grid representations into individual feature extraction layers with tied weights, extracting low-level features from a first feature extraction layer, extracting high-level features from a second feature extraction layer, normalizing the extracted low-level features and high-level features, and applying deep supervision of multiple contrastive losses and multiple hard negative mining modules at the first and second feature extraction layers. The method further includes, during a testing phase, employing the high-level features capturing high-level semantic information to obtain coarse matching locations, and refining the coarse matching locations with the low-level features to capture low-level geometric information for estimating precise matching locations.

Generating Occlusion-Aware Bird Eye View Representations Of Complex Road Scenes

View page
US Patent:
20190094875, Mar 28, 2019
Filed:
Sep 28, 2018
Appl. No.:
16/146202
Inventors:
- Princeton NJ, US
Paul Vernaza - Sunnyvale CA, US
Manmohan Chandraker - Santa Clara CA, US
Menghua Zhai - Lexington KY, US
International Classification:
G05D 1/02
G05D 1/00
G06T 17/05
G06T 7/514
G06T 7/194
Abstract:
Systems and methods for generating an occlusion-aware bird's eye view map of a road scene include identifying foreground objects and background objects in an input image to extract foreground features and background features corresponding to the foreground objects and the background objects, respectively. The foreground objects are masked from the input image with a mask. Occluded objects and depths of the occluded objects are inferred by predicting semantic features and depths in masked areas of the masked image according to contextual information related to the background features visible in the masked image. The foreground objects and the background objects are mapped to a three-dimensional space according to locations of each of the foreground objects, the background objects and occluded objects using the inferred depths. A bird's eye view is generated from the three-dimensional space and displayed with a display device.

Generating Occlusion-Aware Bird Eye View Representations Of Complex Road Scenes

View page
US Patent:
20190096125, Mar 28, 2019
Filed:
Sep 28, 2018
Appl. No.:
16/145621
Inventors:
- Princeton NJ, US
Paul Vernaza - Sunnyvale CA, US
Manmohan Chandraker - Santa Clara CA, US
Menghua Zhai - Lexington KY, US
International Classification:
G06T 17/05
G06T 15/40
G06T 7/11
G06T 7/194
G06T 3/00
Abstract:
Systems and methods for generating an occlusion-aware bird's eye view map of a road scene include identifying foreground objects and background objects in an input image to extract foreground features and background features corresponding to the foreground objects and the background objects, respectively. The foreground objects are masked from the input image with a mask. Occluded objects and depths of the occluded objects are inferred by predicting semantic features and depths in masked areas of the masked image according to contextual information related to the background features visible in the masked image. The foreground objects and the background objects are mapped to a three-dimensional space according to locations of each of the foreground objects, the background objects and occluded objects using the inferred depths. A bird's eye view is generated from the three-dimensional space and displayed with a display device.

Computer Aided Traffic Enforcement Using Dense Correspondence Estimation With Multi-Level Metric Learning And Hierarchical Matching

View page
US Patent:
20190065868, Feb 28, 2019
Filed:
Jul 6, 2018
Appl. No.:
16/029167
Inventors:
- Princeton NJ, US
Mohammed E.F. Salem - Hyattsville MD, US
Muhammad Zeeshan Zia - San Jose CA, US
Paul Vernaza - Sunnyvale CA, US
Manmohan Chandraker - Santa Clara CA, US
International Classification:
G06K 9/00
G06K 9/62
Abstract:
Systems and methods for detecting traffic scenarios include an image capturing device which captures two or more images of an area of a traffic environment with each image having a different view of vehicles and a road in the traffic environment. A hierarchical feature extractor concurrently extracts features at multiple neural network layers from each of the images, with the features including geometric features and semantic features, and for estimating correspondences between semantic features for each of the images and refining the estimated correspondences with correspondences between the geometric features of each of the images to generate refined correspondence estimates. A traffic localization module uses the refined correspondence estimates to determine locations of vehicles in the environment in three dimensions to automatically determine a traffic scenario according to the locations of vehicles. A notification device generates a notification of the traffic scenario.

Dense Correspondence Estimation With Multi-Level Metric Learning And Hierarchical Matching

View page
US Patent:
20190066373, Feb 28, 2019
Filed:
Jul 6, 2018
Appl. No.:
16/029126
Inventors:
- Princeton NJ, US
Mohammed E.F. Salem - Hyattsville MD, US
Muhammad Zeeshan Zia - San Jose CA, US
Paul Vernaza - Sunnyvale CA, US
Manmohan Chandraker - Santa Clara CA, US
International Classification:
G06T 17/05
G06K 9/62
G06K 9/46
G06K 9/66
G06N 3/08
Abstract:
Systems and methods for correspondence estimation and flexible ground modeling include communicating two-dimensional (2D) images of an environment to a correspondence estimation module, including a first image and a second image captured by an image capturing device. First features, including geometric features and semantic features, are hierarchically extract from the first image with a first convolutional neural network (CNN) according to activation map weights, and second features, including geometric features and semantic features, are hierarchically extracted from the second image with a second CNN according to the activation map weights. Correspondences between the first features and the second features are estimated, including hierarchical fusing of geometric correspondences and semantic correspondences. A 3-dimensional (3D) model of a terrain is estimated using the estimated correspondences belonging to the terrain surface. Relative locations of elements and objects in the environment are determined according to the 3D model of the terrain. A user is notified of the relative locations.

Deep Network Flow For Multi-Object Tracking

View page
US Patent:
20180130215, May 10, 2018
Filed:
Sep 5, 2017
Appl. No.:
15/695565
Inventors:
- Princeton NJ, US
Wongun Choi - Lexington MA, US
Paul Vernaza - Sunnyvale CA, US
Manmohan Chandraker - Santa Clara CA, US
International Classification:
G06T 7/20
G06T 7/77
Abstract:
A multi-object tracking system and method are provided. The multi-object tracking system includes at least one camera configured to capture a set of input images of a set of objects to be tracked. The multi-object tracking system further includes a memory storing a learning model configured to perform multi-object tracking by jointly learning arbitrarily parameterized and differentiable cost functions for all variables in a linear program that associates object detections with bounding boxes to form trajectories. The multi-object tracking system also includes a processor configured to (i) detect the objects and track locations of the objects by applying the learning model to the set of input images in a multi-object tracking task, and (ii), provide a listing of the objects and the locations of the objects for the multi-object tracking task. A bi-level optimization is used to minimize a loss defined on a solution of the linear program.

Surveillance System Using Deep Network Flow For Multi-Object Tracking

View page
US Patent:
20180130216, May 10, 2018
Filed:
Sep 5, 2017
Appl. No.:
15/695625
Inventors:
- Princeton NJ, US
Wongun Choi - Lexington MA, US
Paul Vernaza - Sunnyvale CA, US
Manmohan Chandraker - Santa Clara CA, US
International Classification:
G06T 7/20
G06T 7/70
H04N 7/18
Abstract:
A surveillance system and method are provided. The surveillance system includes at least one camera configured to capture a set of images of a given target area that includes a set of objects to be tracked. The surveillance system includes a memory storing a learning model configured to perform multi-object tracking by jointly learning arbitrarily parameterized and differentiable cost functions for all variables in a linear program that associates object detections with bounding boxes to form trajectories. The surveillance system includes a processor configured to perform surveillance of the target area to (i) detect the objects and track locations of the objects by applying the learning model to the images in a surveillance task that uses the multi-object tracking, and (ii), provide a listing of the objects and their locations for surveillance task. A bi-level optimization is used to minimize a loss defined on a solution of the linear program.

Dynamic Scene Prediction With Multiple Interacting Agents

View page
US Patent:
20180124423, May 3, 2018
Filed:
Oct 20, 2017
Appl. No.:
15/789098
Inventors:
- Princeton NJ, US
Paul Vernaza - Sunnyvale CA, US
Manmohan Chandraker - Santa Clara CA, US
Namhoon Lee - Oxford, GB
International Classification:
H04N 19/52
G06T 7/277
G06N 3/08
G08B 13/00
Abstract:
Methods and systems for predicting a trajectory include determining prediction samples for agents in a scene based on a past trajectory. The prediction samples are ranked according to a likelihood score that incorporates interactions between agents and semantic scene context. The prediction samples are iteratively refined using a regression function that accumulates scene context and agent interactions across iterations. A response activity is triggered when the prediction samples satisfy a predetermined condition.
Control profile
Paul N Vernaza from Cupertino, CA, age ~42 Get Report