公开(公告)号：US11460544B2

公开(公告)日：2022-10-04

申请号：US16194461

申请日：2018-11-19

Applicant: Dalong Li ,  Andrew Chen ,  Ivan Roman

Inventor： Dalong Li ,  Andrew Chen ,  Ivan Roman

IPC: G06F11/30 ,  G01S7/48 ,  G01S13/931 ,  G01S13/42

Abstract: An advanced driver assistance system (ADAS) and method for a vehicle utilize a light detection and ranging (LIDAR) system configured to emit laser light pulses and capture reflected laser light pulses collectively forming three-dimensional (3D) LIDAR point cloud data and a controller configured to receive the 3D LIDAR point cloud data, convert the 3D LIDAR point cloud data to a two-dimensional (2D) birdview projection, detect a set of lines in the 2D birdview projection, filter the detected set of lines to remove lines having features that are not indicative of traffic signs to obtain a filtered set of lines, and detect one or more traffic signs using the filtered set of lines.

公开(公告)号：US20140146882A1

公开(公告)日：2014-05-29

申请号：US14126573

申请日：2011-08-08

Applicant: Steven J. Simske ,  Dalong Li

Inventor： Steven J. Simske ,  Dalong Li

IPC: H04N19/18 ,  H04N19/60

CPC classification number: H04N19/18 ,  G08B13/1961 ,  G08B13/19667 ,  H04N7/18 ,  H04N19/12 ,  H04N19/14 ,  H04N19/60 ,  H04N19/87

Abstract: An embodiment provides a method for compression of a real-time surveillance signal. This method includes receiving a signal from a monitoring device and analyzing the signal to be monitored to compute spectral content of the signal. This method also includes computing the information content of the signal and determining a count of a number of coefficients to be used to monitor the signal. This method includes deploying a strategy for computing a plurality of coefficients based on the spectral content of the signal and the count of the number of coefficients to be used for monitoring the signal. This method further includes monitoring the signal and resetting the system in the case of above-threshold changes in a selected portion of the plurality of coefficients.

Abstract translation: 实施例提供了一种压缩实时监视信号的方法。 该方法包括从监视设备接收信号并分析待监视的信号以计算信号的频谱内容。 该方法还包括计算信号的信息内容并确定要用于监视信号的系数数量的计数。 该方法包括基于信号的频谱内容和用于监视信号的系数数量的计数来部署用于计算多个系数的策略。 该方法还包括在多个系数的选定部分中的阈值上变化的情况下监视信号和重置系统。

公开(公告)号：US12198440B2

公开(公告)日：2025-01-14

申请号：US17872112

申请日：2022-07-25

Applicant: Dalong Li ,  Rohit S Paranjpe ,  Stephen Horton

Inventor： Dalong Li ,  Rohit S Paranjpe ,  Stephen Horton

IPC: G06V20/56 ,  G06V10/762 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/778 ,  G06V10/80

Abstract: Vehicle perception techniques include obtaining a training dataset represented by N training histograms, in an image feature space, corresponding to N training images, K-means clustering the N training histograms to determine K clusters with respective K respective cluster centers, wherein K and N are integers greater than or equal to one and K is less than or equal to N, comparing the N training histograms to their respective K cluster centers to determine maximum in-class distances for each of K clusters, applying a deep neural network (DNN) to input images of the set of inputs to output detected/classified objects with respective confidence scores, obtaining adjusted confidence scores by adjusting the confidence scores output by the DNN based on distance ratios of (i) minimal distances of input histograms representing the input images to the K cluster centers and (ii) the respective maximum in-class.

公开(公告)号：US20210133947A1

公开(公告)日：2021-05-06

申请号：US16670575

申请日：2019-10-31

Applicant: Dalong Li ,  Stephen Horton ,  Neil R Garbacik

Inventor： Dalong Li ,  Stephen Horton ,  Neil R Garbacik

IPC: G06T7/00 ,  G06K9/00 ,  G05D1/00 ,  G01S17/89 ,  G01S17/87 ,  G01S17/93 ,  G05D1/02

Abstract: An autonomous driving technique comprises determining an image quality metric for each image frame of a series of image frames of a scene outside of a vehicle captured by a camera system and determining an image quality threshold based on the image quality metrics for the series of image frames. The technique then determines whether the image quality metric for a current image frame satisfies the image quality threshold. When the image quality metric for the current image frame satisfies the image quality threshold, object detection is performed by at least utilizing a first deep neural network (DNN) with the current image frame. When the image quality metric for the current image frame fails to satisfy the image quality threshold, object detection is performed by utilizing a second, different DNN with the information captured by another sensor system and without utilizing the first DNN or the current image frame.

公开(公告)号：US10983215B2

公开(公告)日：2021-04-20

申请号：US16224978

申请日：2018-12-19

Applicant: Dalong Li ,  Alex M Smith ,  Stephen Horton

Inventor： Dalong Li ,  Alex M Smith ,  Stephen Horton

IPC: G01S17/66 ,  G01S7/48 ,  B60W30/09 ,  B60W30/14 ,  G01S17/931

Abstract: An advanced driver assistance system (ADAS) and method for a vehicle utilize a light detection and ranging (LIDAR) system configured to emit laser light pulses and capture reflected laser light pulses collectively forming three-dimensional (3D) LIDAR point cloud data and a controller configured to receive the 3D LIDAR point cloud data, convert the 3D LIDAR point cloud data to a two-dimensional (2D) birdview projection, obtain a template image for object detection, the template image being representative of a specific object, blur the 2D birdview projection and the template image to obtain a blurred 2D birdview projection and a blurred template image, and detect the specific object by matching a portion of the blurred 2D birdview projection to the blurred template image.

公开(公告)号：US10823855B2

公开(公告)日：2020-11-03

申请号：US16194465

申请日：2018-11-19

Applicant: Dalong Li ,  Andrew Chen

Inventor： Dalong Li ,  Andrew Chen

IPC: G01S17/89 ,  G06T7/73 ,  G06T7/521 ,  G06K9/00 ,  G01S17/04

Abstract: An advanced driver assistance system (ADAS) and method for a vehicle utilize a light detection and ranging (LIDAR) system configured to emit laser light pulses and capture reflected laser light pulses collectively forming three-dimensional (3D) LIDAR point cloud data and a controller configured to receive the 3D LIDAR point cloud data divide the 3D LIDAR point cloud data into a plurality of cells corresponding to distinct regions surrounding the vehicle, generate a histogram comprising a calculated height difference between a maximum height and a minimum height in the 3D LIDAR point cloud data for each cell of the plurality of cells, and using the histogram, perform at least one of adaptive ground removal from the 3D LIDAR point cloud data and traffic level recognition.

公开(公告)号：US20240046657A1

公开(公告)日：2024-02-08

申请号：US17881111

申请日：2022-08-04

Applicant: Dalong Li ,  Rohit S Paranjpe ,  Benjamin J Chappell

Inventor： Dalong Li ,  Rohit S Paranjpe ,  Benjamin J Chappell

IPC: G06V20/58 ,  G06V10/82 ,  G06V10/75 ,  G06V20/64 ,  G06V10/778 ,  G01S17/894 ,  G01S17/931

CPC classification number: G06V20/58 ,  G06V10/82 ,  G06V10/751 ,  G06V20/647 ,  G06V10/778 ,  G01S17/894 ,  G01S17/931

Abstract: Vehicle perception techniques include applying a 3D DNN to a set of inputs to generate 3D detection results including a set of 3D objects, transforming the set of 3D objects onto a set of images as a first set of 2D bounding boxes, applying a 2D DNN to the set of images to generate 2D detection results including a second set of 2D bounding boxes, calculating mean average precision (mAP) values based on a comparison between the first and second sets of 2D bounding boxes, identifying a set or corner cases based on the calculated mAP values, and re-training or updating the 3D DNN using the identified set of corner cases, wherein a performance of the 3D DNN is thereby increased without the use of expensive additional manually and/or automatically annotated training datasets.

公开(公告)号：US11702085B2

公开(公告)日：2023-07-18

申请号：US17092483

申请日：2020-11-09

Applicant: Ayyoub Rezaeian ,  Dalong Li

Inventor： Ayyoub Rezaeian ,  Dalong Li

IPC: B60W40/13 ,  G01M1/12 ,  G01G9/00 ,  G01G19/03 ,  B60W60/00

CPC classification number: B60W40/13 ,  B60W60/001 ,  G01G9/00 ,  G01G19/03 ,  G01M1/122 ,  B60W2040/1315 ,  B60W2420/52 ,  B60W2510/06 ,  B60W2510/08 ,  B60W2510/20 ,  B60W2510/222 ,  B60W2520/00

Abstract: Vehicle center of gravity (CoG) height and mass estimation techniques utilize a light detection and ranging (LIDAR) sensor configured to emit light pulses and capture reflected light pulses that collectively form LIDAR point cloud data and a controller configured to estimate the CoG height and the mass of the vehicle during a steady-state operating condition of the vehicle by processing the LIDAR point cloud data to identify a ground plane, identifying a height difference between (i) a nominal distance from the LIDAR sensor to the ground plane and (ii) an estimated distance from the LIDAR sensor to the ground plane using the processed LIDAR point cloud data, estimating the vehicle CoG height as a difference between (i) a nominal vehicle CoG height and the height difference, and estimating the vehicle mass based on one of (i) vehicle CoG metrics and (ii) dampening metrics of a suspension of the vehicle.

公开(公告)号：US10929986B2

公开(公告)日：2021-02-23

申请号：US16224946

申请日：2018-12-19

Applicant: Zijian Wang ,  Dalong Li ,  Ivan Roman

Inventor： Zijian Wang ,  Dalong Li ,  Ivan Roman

IPC: G06K9/00 ,  G06T7/246 ,  G06T7/73 ,  G06T7/277 ,  B60W30/09 ,  G05D1/02 ,  G05D1/00

Abstract: An advanced driver assistance system (ADAS) and corresponding method for a vehicle utilize a camera system configured to capture an image and a controller configured to receive the captured image, detect an object in the captured image using a simple neural network model, track the detected object using a tracking technique to obtain a tracked position, project a trajectory of the detected object using a trajectory projection technique to obtain a predicted position, determine a most likely position of the detected object based on at least one of the tracked and predicted positions, generate a two-dimensional (2D) birdview projection illustrating the detected object according to its determined most likely position, and control at least one ADAS feature of the vehicle using the generated 2D birdview projection.

公开(公告)号：US20200158874A1

公开(公告)日：2020-05-21

申请号：US16194465

申请日：2018-11-19

Applicant: Dalong Li ,  Andrew Chen

Inventor： Dalong Li ,  Andrew Chen

IPC: G01S17/89 ,  G01S17/02 ,  G06K9/00 ,  G06T7/73 ,  G06T7/521

Abstract: An advanced driver assistance system (ADAS) and method for a vehicle utilize a light detection and ranging (LIDAR) system configured to emit laser light pulses and capture reflected laser light pulses collectively forming three-dimensional (3D) LIDAR point cloud data and a controller configured to receive the 3D LIDAR point cloud data divide the 3D LIDAR point cloud data into a plurality of cells corresponding to distinct regions surrounding the vehicle, generate a histogram comprising a calculated height difference between a maximum height and a minimum height in the 3D LIDAR point cloud data for each cell of the plurality of cells, and using the histogram, perform at least one of adaptive ground removal from the 3D LIDAR point cloud data and traffic level recognition.