公开(公告)号：US20250131064A1

公开(公告)日：2025-04-24

申请号：US18901647

申请日：2024-09-30

Applicant: NEC Laboratories America, Inc.

Inventor： Yangmin DING ,  Yanchao WANG ,  Ting WANG

IPC: G06F18/241 ,  G06Q10/0639

Abstract: Disclosed are systems, methods, and structures that enhance advanced metering infrastructure (AMI) event classification with graph neural networks (GNNs) in which AMI data is represented as a graph, where each meter is a node and connections between nodes represent the physical or functional relationship between meters. As a result, our systems and methods capture dependency information between different meters and use this information to predict events and anomalies.

公开(公告)号：US20250130307A1

公开(公告)日：2025-04-24

申请号：US18901760

申请日：2024-09-30

Applicant: NEC Laboratories America, Inc.

Inventor： Jian FANG ,  Wataru KOHNO ,  Yaowen LI ,  Ting WANG

IPC: G01S5/22

Abstract: Disclosed are systems and methods directed to a MIMO method that detects and localizes an object without requiring the object to emit a sound. Operationally, multiple speakers generate tone signals at different frequencies, while multiple acoustic sensors demodulate the complex amplitude of each frequency. By monitoring the feature variation of the relative phase (or intensity) vector from the complex amplitude, our method detects or localizes movement of the object. For large-scale applications, a fiber-optic system and method that employs distributed acoustic sensing (DAS) in which an optical fiber is used as one or more acoustic sensors located at points along the length of the optical fiber. A single DAS system provides numerous sensors using only a single optical fiber thereby enabling perfect synchronization and centralized signal processing. Notably, with such a DAS arrangement, cost and complexity is significantly reduced, while privacy is preserved.

公开(公告)号：US20250130074A1

公开(公告)日：2025-04-24

申请号：US18901783

申请日：2024-09-30

Applicant: NEC Laboratories America, Inc.

Inventor： Yangmin DING ,  Sarper OZHARAR ,  Zhuocheng JIANG ,  Yue TIAN ,  Ting WANG

IPC: G01D5/353

Abstract: Disclosed are systems, methods, and structures that employ distributed fiber sensing that utilizes existing fiber cables for detecting tree events. Our inventive systems and methods can detect when a tree or other types of vibration occur on the telecom cable or poles, creating a high-resolution spatial profile of the cable. Systems and methods according to aspects of the present disclosure distinguish between tree events and other vibrations, such as hammer strikes on a utility pole, by employing Information Noise Contrastive Estimation (InfoNCE) and contrastive learning. Our inventive approach accurately differentiates between different types of vibrations and identifies patterns specific to tree events.

公开(公告)号：US20250123127A1

公开(公告)日：2025-04-17

申请号：US18890304

申请日：2024-09-19

Applicant: NEC Laboratories America, Inc.

Inventor： Junqiang HU ,  Ting WANG ,  Yue-Kai HUANG

IPC: G01D5/353 ,  G01H9/00 ,  H04B10/071

Abstract: Disclosed are systems, methods, and structures that increase overall sensing reach of a DFOS system and reduces system cost without sacrificing sensed signal quality by employing a cascaded arrangement of DFOS interrogators and operating method providing backscattering DFOS, maintaining each span within a desired length which can advantageously be determined by signal quality, pulse rate, or other factors such as physical layout. The cascaded DFOS interrogators work independently while sharing the pulse light produced by the first interrogator in a cascaded series of interrogators. The light is amplified in successive fiber spans and a circulator may be employed to cut-off any backscattered signal.

公开(公告)号：US20250118063A1

公开(公告)日：2025-04-10

申请号：US18891625

申请日：2024-09-20

Applicant: NEC Laboratories America, Inc.

Inventor： Jong-Chyi Su ,  Samuel Schulter ,  Sparsh Garg ,  Manmohan Chandraker ,  Mingfu Liang

IPC: G06V10/82 ,  G06V10/75 ,  G06V20/70

Abstract: Systems and methods include detecting one or more objects in an image and generating one or more captions for the image. One or more predicted categories of the one or more objects detected in the image and the one or more captions are matched. From the one or more predicted categories, a category that is not successfully predicted in the image is identified. Data is curated to improve the category that is not successfully predicted in the image. A perception model is finetuned using data curated.

公开(公告)号：US20250118009A1

公开(公告)日：2025-04-10

申请号：US18903348

申请日：2024-10-01

Applicant: NEC Laboratories America, Inc.

Inventor： Bingbing Zhuang ,  Ziyu Jiang ,  Buyu Liu ,  Manmohan Chandraker ,  Shanlin Sun

IPC: G06T15/08 ,  G01S17/89 ,  G06V10/774 ,  G06V20/52

Abstract: A computer-implemented method for synthesizing an image includes capturing data from a scene and fusing grid-based representations of the scene from different encodings to inherit beneficial properties of the different encodings, The encodings include Lidar encoding and a high definition map encoding. Rays are rendered from fused grid-based representations. A density and color are determined for points in the rays. A volume rendering is employed for the rays with the density and color. An image is synthesized from the volume rendered rays with the density and the color.

公开(公告)号：US20250117029A1

公开(公告)日：2025-04-10

申请号：US18905280

申请日：2024-10-03

Applicant: NEC Laboratories America, Inc.

Inventor： Tom Bu ,  Bingbing Zhuang ,  Manmohan Chandraker

IPC: G05D1/86 ,  G05D1/242 ,  G05D1/243 ,  G05D107/60 ,  G05D111/67

Abstract: Systems and methods for automatic multi-modality sensor calibration with near-infrared images (NIR). Image keypoints from collected images and NIR keypoints from NIR can be detected. A deep-learning-based neural network that learns relation graphs between the image keypoints and the NIR keypoints can match the image keypoints and the NIR keypoints. Three dimensional (3D) points from 3D point cloud data can be filtered based on corresponding 3D points from the NIR keypoints (NIR-to-3D points) to obtain filtered NIR-to-3D points. An extrinsic calibration can be optimized based on a reprojection error computed from the filtered NIR-to-3D points to obtain an optimized extrinsic calibration for an autonomous entity control system. An entity can be controlled by employing the optimized extrinsic calibration for the autonomous entity control system.

公开(公告)号：US20250115278A1

公开(公告)日：2025-04-10

申请号：US18905695

申请日：2024-10-03

Applicant: NEC Laboratories America, Inc.

Inventor： Francesco Pittaluga ,  Buyu Liu ,  Manmohan Chandraker ,  Kaiyuan Zhang

IPC: B60W60/00

Abstract: Systems and methods for generating adversarial driving scenarios for autonomous vehicles. An artificial intelligence model can compute an adversarial loss function by minimizing the distance between predicted adversarial perturbed trajectories and corresponding generated neighbor future trajectories from input data. A traffic violation loss function can be computed based on observed adversarial agents adhering to driving rules from the input data. A comfort loss function can be computed based on the predicted driving characteristics of adversarial vehicles relevant to comfort of hypothetical passengers from the input data. A planner module can be trained for autonomous vehicles based on a combined loss function of the adversarial loss function, the traffic violation loss function and the comfort loss function to generate adversarial driving scenarios. An autonomous vehicle can be controlled based on trajectories generated in the adversarial driving scenarios.

公开(公告)号：US20250115276A1

公开(公告)日：2025-04-10

申请号：US18904639

申请日：2024-10-02

Applicant: NEC Laboratories America, Inc.

Inventor： Samuel Schulter ,  Vijay Kumar Baikampady Gopalkrishna ,  Yumin Suh

IPC: B60W60/00 ,  G06T5/77 ,  G06V10/774 ,  G06V20/58

Abstract: Methods and systems for object detection include generating a negative description for an input image of a road scene, based on a positive description of the input image, using a language model. A negative image is generated based on the input image and the negative description by replacing a portion of the input image that is described by the positive description with content that is described by the negative description using a generative image model. An object detection model is trained with the input image, the positive description, the negative description, and the negative image. An object is identified within a driving scene using the trained object detection model. A driving action is performed in a self-driving vehicle responsive to the identified object.

公开(公告)号：US12263849B2

公开(公告)日：2025-04-01

申请号：US17961169

申请日：2022-10-06

Applicant: NEC Laboratories America, Inc. ,  NEC Corporation

Inventor： LuAn Tang ,  Yuncong Chen ,  Wei Cheng ,  Zhengzhang Chen ,  Haifeng Chen ,  Yuji Kobayashi ,  Yuxiang Ren

IPC: B60W40/09 ,  G06F18/25 ,  G06N3/084

Abstract: Systems and methods for data fusion and analysis of vehicle sensor data, including receiving a multiple modality input data stream from a plurality of different types of vehicle sensors, determining latent features by extracting modality-specific features from the input data stream, and aligning a distribution of the latent features of different modalities by feature-level data fusion. Classification probabilities can be determined for the latent features using a fused modality scene classifier. A tree-organized neural network can be trained to determine path probabilities and issue driving pattern judgments, with the tree-organized neural network including a soft tree model and a hard decision leaf. One or more driving pattern judgments can be issued based on a probability of possible driving patterns derived from the modality-specific features.