公开(公告)号：US20190066493A1

公开(公告)日：2019-02-28

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 ,  G06T17/00 ,  G06N3/08 ,  G06N3/04 ,  G06N5/04 ,  G06N99/00

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：US20180268266A1

公开(公告)日：2018-09-20

申请号：US15889958

申请日：2018-02-06

Applicant: NEC Laboratories America, Inc.

Inventor： Kihyuk Sohn ,  Xiang Yu ,  Manmohan Chandraker

IPC: G06K9/66 ,  G06K9/00 ,  G06N3/08

CPC classification number: G06K9/66 ,  G06K9/00268 ,  G06K9/00288 ,  G06K9/00718 ,  G06K9/00744 ,  G06K9/00771 ,  G06K9/4628 ,  G06K9/6201 ,  G06K9/6217 ,  G06K9/6262 ,  G06K9/6274 ,  G06K2009/00738 ,  G06N3/02 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/088 ,  G06N20/00 ,  G06T7/70 ,  G06T9/002 ,  G06T2207/20081 ,  G08B13/196 ,  G08B13/19613

Abstract: A surveillance system is provided that includes a device configured to capture a video sequence, formed from a set of unlabeled testing video frames, of a target area. The surveillance system further includes a processor configured to pre-train a recognition engine formed from a reference set of CNNs on a still image domain that includes labeled training still image frames. The processor adapts the recognition engine to a video domain to form an adapted recognition engine, by applying a non-reference set of CNNs to domains including the still image and video domains and a degraded image domain. The degraded image domain includes labeled synthetically degraded versions of the frames included in the still image domain. The video domain includes random unlabeled training video frames. The processor recognizes, using the adapted engine, at least one object in the target area. A display device displays the recognized objects.

公开(公告)号：US20180268222A1

公开(公告)日：2018-09-20

申请号：US15890005

申请日：2018-02-06

Applicant: NEC Laboratories America, Inc.

Inventor： Kihyuk Sohn ,  Xiang Yu ,  Manmohan Chandraker

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06N3/02 ,  G06N99/00

CPC classification number: G06K9/66 ,  G06K9/00268 ,  G06K9/00288 ,  G06K9/00718 ,  G06K9/00744 ,  G06K9/00771 ,  G06K9/4628 ,  G06K9/6201 ,  G06K9/6217 ,  G06K9/6262 ,  G06K9/6274 ,  G06K2009/00738 ,  G06N3/02 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/088 ,  G06N20/00 ,  G06T7/70 ,  G06T9/002 ,  G06T2207/20081 ,  G08B13/196 ,  G08B13/19613

Abstract: An action recognition system is provided that includes a device configured to capture a video sequence formed from a set of unlabeled testing video frames. The system further includes a processor configured to pre-train a recognition engine formed from a reference set of CNNs on a still image domain that includes labeled training still image frames. The processor adapts the recognition engine to a video domain to form an adapted engine, by applying non-reference CNNs to domains that include the still image and video domains and a degraded image domain that includes labeled synthetically degraded versions of the frames in the still image domain. The video domain includes random unlabeled training video frames. The processor recognizes, using the adapted engine, an action performed by at least one object in the sequence, and controls a device to perform a response action in response to an action type of the action.

公开(公告)号：US20180130229A1

公开(公告)日：2018-05-10

申请号：US15709849

申请日：2017-09-20

Applicant: NEC Laboratories America, Inc.

Inventor： Muhammad Zeeshan Zia ,  Quoc-Huy Tran ,  Xiang Yu ,  Manmohan Chandraker ,  Chi Li

IPC: G06T7/73 ,  G06N3/08

CPC classification number: G06K9/6256 ,  B60T2201/022 ,  B60W30/00 ,  G05D1/0221 ,  G06F17/5009 ,  G06K9/00201 ,  G06K9/00208 ,  G06K9/00624 ,  G06K9/00771 ,  G06K9/00805 ,  G06K9/4628 ,  G06K9/6255 ,  G06N3/02 ,  G06N3/084 ,  G06T7/55 ,  G06T7/74 ,  G06T11/60 ,  G06T15/10 ,  G06T15/40 ,  G06T2207/20101 ,  G06T2207/30261 ,  G06T2210/22 ,  G08G1/0962 ,  G08G1/166 ,  H04N7/00

Abstract: A surveillance system and method are provided. The surveillance system includes an image capture device configured to capture an actual image of a target area depicting an object. The surveillance system further includes a processor. The processor is configured to render, based on a set of 3D Computer Aided Design (CAD) models, synthetic images with intermediate shape corresponding concept labels. The processor is further configured to form a multi-layer Convolutional Neural Network (CNN) which jointly models multiple intermediate shape concepts, based on the rendered synthetic images. The processor is also configured to perform an intra-class appearance variation-aware and occlusion-aware 3D object parsing on the actual image by applying the CNN to the actual image to generate an image pair including a 2D and 3D geometric structure of the object depicted in the actual image. The surveillance system further includes a display device configured to display the image pair.

公开(公告)号：US20170262736A1

公开(公告)日：2017-09-14

申请号：US15436199

申请日：2017-02-17

Applicant: NEC Laboratories America, Inc.

Inventor： Xiang Yu ,  Feng Zhou ,  Manmohan Chandrakar

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G06T7/60

Abstract: A system and method are provided. The system includes a processor. The processor is configured to generate a response map for an image, using a four stage convolutional structure. The processor is further configured to generate a plurality of landmark points for the image based on the response map, using a shape basis neural network. The processor is additionally configured to generate an optimal shape for the image based on the plurality of landmark points for the image and the response map, using a point deformation neural network. A recognition system configured to identify the image based on the generated optimal shape to generate a recognition result of the image. The processor is also configured to operate a hardware-based machine based on the recognition result.