公开(公告)号：US20240312197A1

公开(公告)日：2024-09-19

申请号：US18605594

申请日：2024-03-14

Applicant: SRI International

Inventor： Han-Pang Chiu ,  Niluthpol C. Mithun ,  Supun Samarasekera ,  Abhinav Rajvanshi ,  Xingchen Zhao ,  Md Nazmul Karim

IPC: G06V10/82 ,  G06V10/771 ,  G06V10/774 ,  G06V10/776

CPC classification number: G06V10/82 ,  G06V10/771 ,  G06V10/7753 ,  G06V10/776

Abstract: In general, techniques are described for unsupervised domain adaptation of models with pseudo-label curation. In an example, a method includes generating a plurality of pseudo-labels for a dataset of unlabeled data using a source machine learning model; estimating a reliability of each pseudo-label of the plurality of pseudo-labels using one or more reliability measures; selecting a subset of the plurality of pseudo-labels having estimated reliabilities that satisfy a reliability threshold; and training, using one or more curriculum learning techniques, a target machine learning model starting with the selected subset of the plurality of pseudo-labels and the corresponding unlabeled data.

公开(公告)号：US11676296B2

公开(公告)日：2023-06-13

申请号：US16101201

申请日：2018-08-10

Applicant: SRI International

Inventor： Han-Pang Chiu ,  Supun Samarasekera ,  Rakesh Kumar ,  Ryan Villamil ,  Varun Murali ,  Gregory Drew Kessler

IPC: G06T7/579 ,  G06T19/00 ,  G06T7/136 ,  G06N3/08 ,  G06F16/903 ,  G06F16/583 ,  G06T7/521 ,  G06T7/143 ,  G06T7/11 ,  G06V20/58 ,  G06V20/56 ,  G06F18/24 ,  G06V20/20 ,  G01S17/89 ,  G01S17/86

CPC classification number: G06T7/579 ,  G06F16/5838 ,  G06F16/903 ,  G06F18/24 ,  G06N3/08 ,  G06T7/11 ,  G06T7/136 ,  G06T7/143 ,  G06T7/521 ,  G06T19/006 ,  G06V20/20 ,  G06V20/56 ,  G06V20/582 ,  G06V20/588 ,  G01S17/86 ,  G01S17/89 ,  G06T2207/10016 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/10032 ,  G06T2207/30212 ,  G06T2207/30244 ,  G06T2207/30248

Abstract: Techniques for augmenting a reality captured by an image capture device are disclosed. In one example, a system includes an image capture device that generates a two-dimensional frame at a local pose. The system further includes a computation engine executing on one or more processors that queries, based on an estimated pose prior, a reference database of three-dimensional mapping information to obtain an estimated view of the three-dimensional mapping information at the estimated pose prior. The computation engine processes the estimated view at the estimated pose prior to generate semantically segmented sub-views of the estimated view. The computation engine correlates, based on at least one of the semantically segmented sub-views of the estimated view, the estimated view to the two-dimensional frame. Based on the correlation, the computation engine generates and outputs data for augmenting a reality represented in at least one frame captured by the image capture device.

公开(公告)号：US11361470B2

公开(公告)日：2022-06-14

申请号：US16667047

申请日：2019-10-29

Applicant: SRI International

Inventor： Han-Pang Chiu ,  Zachary Seymour ,  Karan Sikka ,  Supun Samarasekera ,  Rakesh Kumar ,  Niluthpol Mithun

IPC: G01S17/89 ,  G01S7/48 ,  G06F16/583 ,  G06K9/62 ,  G06T7/00 ,  G06T7/73 ,  G06V10/44 ,  G06V10/82 ,  G06V20/00

Abstract: A method, apparatus and system for visual localization includes extracting appearance features of an image, extracting semantic features of the image, fusing the extracted appearance features and semantic features, pooling and projecting the fused features into a semantic embedding space having been trained using fused appearance and semantic features of images having known locations, computing a similarity measure between the projected fused features and embedded, fused appearance and semantic features of images, and predicting a location of the image associated with the projected, fused features. An image can include at least one image from a plurality of modalities such as a Light Detection and Ranging image, a Radio Detection and Ranging image, or a 3D Computer Aided Design modeling image, and an image from a different sensor, such as an RGB image sensor, captured from a same geo-location, which is used to determine the semantic features of the multi-modal image.

公开(公告)号：US20190114507A1

公开(公告)日：2019-04-18

申请号：US16163273

申请日：2018-10-17

Applicant: SRI International

Inventor： Han-Pang Chiu ,  Supun Samarasekera ,  Rakesh Kumar ,  Varun Murali

IPC: G06K9/62 ,  G06K9/72 ,  G06K9/46 ,  G01C21/16 ,  G01S19/13

Abstract: Techniques are disclosed for improving navigation accuracy for a mobile platform. In one example, a navigation system comprises an image sensor that generates a plurality of images, each image comprising one or more features. A computation engine executing on one or more processors of the navigation system processes each image of the plurality of images to determine a semantic class of each feature of the one or more features of the image. The computation engine determines, for each feature of the one or more features of each image and based on the semantic class of the feature, whether to include the feature as a constraint in a navigation inference engine. The computation engine generates, based at least on features of the one or more features included as constraints in the navigation inference engine, navigation information. The computation engine outputs the navigation information to improve navigation accuracy for the mobile platform.

公开(公告)号：US20190051056A1

公开(公告)日：2019-02-14

申请号：US16101201

申请日：2018-08-10

Applicant: SRI International

Inventor： Han-Pang Chiu ,  Supun Samarasekera ,  Rakesh Kumar ,  Ryan Villamil ,  Varun Murali ,  Gregory Drew Kessler

IPC: G06T19/00 ,  G06K9/62 ,  G06T7/136 ,  G06F17/30 ,  G06K9/00 ,  G06N3/08 ,  G01S17/89

Abstract: Techniques for augmenting a reality captured by an image capture device are disclosed. In one example, a system includes an image capture device that generates a two-dimensional frame at a local pose. The system further includes a computation engine executing on one or more processors that queries, based on an estimated pose prior, a reference database of three-dimensional mapping information to obtain an estimated view of the three-dimensional mapping information at the estimated pose prior. The computation engine processes the estimated view at the estimated pose prior to generate semantically segmented sub-views of the estimated view. The computation engine correlates, based on at least one of the semantically segmented sub-views of the estimated view, the estimated view to the two-dimensional frame. Based on the correlation, the computation engine generates and outputs data for augmenting a reality represented in at least one frame captured by the image capture device.