-
141.发明授权公开(公告)号：US11462112B2
公开(公告)日：2022-10-04
申请号：US16787727
申请日：2020-02-11
Applicant: NEC Laboratories America, Inc.
Inventor： Quoc-Huy Tran , Samuel Schulter , Paul Vernaza , Buyu Liu , Pan Ji , Yi-Hsuan Tsai , Manmohan Chandraker
Abstract: A method is provided in an Advanced Driver-Assistance System (ADAS). The method extracts, from an input video stream including a plurality of images using a multi-task Convolutional Neural Network (CNN), shared features across different perception tasks. The perception tasks include object detection and other perception tasks. The method concurrently solves, using the multi-task CNN, the different perception tasks in a single pass by concurrently processing corresponding ones of the shared features by respective different branches of the multi-task CNN to provide a plurality of different perception task outputs. Each respective different branch corresponds to a respective one of the different perception tasks. The method forms a parametric representation of a driving scene as at least one top-view map responsive to the plurality of different perception task outputs. The method controls an operation of the vehicle for collision avoidance responsive to the at least one top-view map indicating an impending collision.
-
公开(公告)号：US20220147761A1
公开(公告)日：2022-05-12
申请号：US17521057
申请日：2021-11-08
Applicant: NEC Laboratories America, Inc.
Inventor： Yi-Hsuan Tsai , Xiang Yu , Bingbing Zhuang , Manmohan Chandraker , Donghyun Kim
Abstract: Video methods and systems include extracting features of a first modality and a second modality from a labeled first training dataset in a first domain and an unlabeled second training dataset in a second domain. A video analysis model is trained using contrastive learning on the extracted features, including optimization of a loss function that includes a cross-domain regularization part and a cross-modality regularization part.
-
公开(公告)号：US20220067457A1
公开(公告)日：2022-03-03
申请号：US17412704
申请日：2021-08-26
Applicant: NEC Laboratories America, Inc.
Inventor： Francesco Pittaluga , Giovanni Milione , Xiang Yu , Manmohan Chandraker , Yi-Hsuan Tsai , Zaid Tasneem
Abstract: A method for acquiring privacy-enhancing encodings in an optical domain before image capture is presented. The method includes feeding a differentiable sensing model with a plurality of images to obtain encoded images, the differentiable sensing model including parameters for sensor optics, integrating the differentiable sensing model into an adversarial learning framework where parameters of attack networks, parameters of utility networks, and the parameters of the sensor optics are concurrently updated, and, once adversarial training is complete, validating efficacy of a learned sensor design by fixing the parameters of the sensor optics and training the attack networks and the utility networks to learn to estimate private and public attributes, respectively, from a set of the encoded images.
-
公开(公告)号：US20220063605A1
公开(公告)日：2022-03-03
申请号：US17408911
申请日：2021-08-23
Applicant: NEC Laboratories America, Inc.
Inventor： Pan Ji , Buyu Liu , Bingbing Zhuang , Manmohan Chandraker , Xiangyu Chen
Abstract: A method provided for 3D object localization predicts pairs of 2D bounding boxes. Each pair corresponds to a detected object in each of the two consecutive input monocular images. The method generates, for each detected object, a relative motion estimation specifying a relative motion between the two images. The method constructs an object cost volume by aggregating temporal features from the two images using the pairs of 2D bounding boxes and the relative motion estimation to predict a range of object depth candidates and a confidence score for each object depth candidate and an object depth from the object depth candidates. The method updates the relative motion estimation based on the object cost volume and the object depth to provide a refined object motion and a refined object depth. The method reconstructs a 3D bounding box for each detected object based on the refined object motion and refined object depth.
-
公开(公告)号：US20210374468A1
公开(公告)日：2021-12-02
申请号：US17330832
申请日：2021-05-26
Applicant: NEC Laboratories America, Inc.
Inventor： Manmohan Chandraker , Ting Wang , Xiang Xu , Francesco Pittaluga , Gaurav Sharma , Yi-Hsuan Tsai , Masoud Faraki , Yuheng Chen , Yue Tian , Ming-Fang Huang , Jian Fang
Abstract: Methods and systems for training a neural network include generate an image of a mask. A copy of an image is generated from an original set of training data. The copy is altered to add the image of a mask to a face detected within the copy. An augmented set of training data is generated that includes the original set of training data and the altered copy. A neural network model is trained to recognize masked faces using the augmented set of training data.
-
Patent Agency Ranking
公开(公告)号：US11055989B2
公开(公告)日：2021-07-06
申请号：US16051924
申请日：2018-08-01
Applicant: NEC Laboratories America, Inc.
Inventor： Kihyuk Sohn , Luan Tran , Xiang Yu , Manmohan Chandraker
IPC: G08G1/017 , G06K9/62 , G06K9/00 , G06N3/08 , G06N3/04 , G06N5/04 , G06T17/00 , G06N20/00 , G08G1/01 , G08G1/04 , G08G1/048 , G06K9/46
Abstract: Systems and methods for performing domain adaptation include collecting a labeled source image having a view of an object. Viewpoints of the object in the source image are synthesized to generate view augmented source images. Photometrics of each of the viewpoints of the object are adjusted to generate lighting and view augmented source images. Features are extracted from each of the lighting and view augmented source images with a first feature extractor and from captured images captured by an image capture device with a second feature extractor. The extracted features are classified using domain adaptation with domain adversarial learning between extracted features of the captured images and extracted features of the lighting and view augmented source images. Labeled target images are displayed corresponding to each of the captured images including labels corresponding to classifications of the extracted features of the captured images.
-
公开(公告)号：US20210150203A1
公开(公告)日：2021-05-20
申请号：US17096111
申请日：2020-11-12
Applicant: NEC Laboratories America, Inc.
Inventor： Buyu Liu , Bingbing Zhuang , Samuel Schulter , Manmohan Chandraker
Abstract: Systems and methods are provided for producing a road layout model. The method includes capturing digital images having a perspective view, converting each of the digital images into top-down images, and conveying a top-down image of time t to a neural network that performs a feature transform to form a feature map of time t. The method also includes transferring the feature map of the top-down image of time t to a feature transform module to warp the feature map to a time t+1, and conveying a top-down image of time t+1 to form a feature map of time t+1. The method also includes combining the warped feature map of time t with the feature map of time t+1 to form a combined feature map, transferring the combined feature map to a long short-term memory (LSTM) module to generate the road layout model, and displaying the road layout model.
-
公开(公告)号：US10991145B2
公开(公告)日：2021-04-27
申请号：US16673256
申请日：2019-11-04
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Feng-Ju Chang , Manmohan Chandraker
Abstract: A system is provided for pose-variant 3D facial attribute generation. A first stage has a hardware processor based 3D regression network for directly generating a space position map for a 3D shape and a camera perspective matrix from a single input image of a face and further having a rendering layer for rendering a partial texture map of the single input image based on the space position map and the camera perspective matrix. A second stage has a hardware processor based two-part stacked Generative Adversarial Network (GAN) including a Texture Completion GAN (TC-GAN) stacked with a 3D Attribute generation GAN (3DA-GAN). The TC-GAN completes the partial texture map to form a complete texture map based on the partial texture map and the space position map. The 3DA-GAN generates a target facial attribute for the single input image based on the complete texture map and the space position map.
-
公开(公告)号：US20210065391A1
公开(公告)日：2021-03-04
申请号：US16987705
申请日：2020-08-07
Applicant: NEC Laboratories America, Inc.
Inventor： Quoc-Huy Tran , Pan Ji , Manmohan Chandraker , Lokender Tiwari
Abstract: A method for improving geometry-based monocular structure from motion (SfM) by exploiting depth maps predicted by convolutional neural networks (CNNs) is presented. The method includes capturing a sequence of RGB images from an unlabeled monocular video stream obtained by a monocular camera, feeding the RGB images into a depth estimation/refinement module, outputting depth maps, feeding the depth maps and the RGB images to a pose estimation/refinement module, the depths maps and the RGB images collectively defining pseudo RGB-D images, outputting camera poses and point clouds, and constructing a 3D map of a surrounding environment displayed on a visualization device.
-
150.发明申请公开(公告)号：US20200372614A1
公开(公告)日：2020-11-26
申请号：US16867805
申请日：2020-05-06
Applicant: NEC Laboratories America, Inc.
Inventor： Quoc-Huy Tran , Bingbing Zhuang , Pan Ji , Manmohan Chandraker
Abstract: A method for correcting blur effects is presented. The method includes generating a plurality of images from a camera, synthesizing blurred images from sharp image counterparts to generate training data to train a structure-and-motion-aware convolutional neural network (CNN), and predicting a camera motion and a depth map from a single blurred image by employing the structure-and-motion-aware CNN to remove blurring from the single blurred image.
-
-
-
-
-
-
-
-
-
Search Results
223
records
(took 0.026 seconds)
