公开(公告)号：US10481267B2

公开(公告)日：2019-11-19

申请号：US15621918

申请日：2017-06-13

Applicant: TUSIMPLE

Inventor： Yi Wang ,  Yi Luo ,  Wentao Zhu ,  Panqu Wang

IPC: G01S17/89 ,  G05D1/02 ,  G01S17/02 ,  G01S17/93 ,  G01S7/48 ,  G05D1/00 ,  G06T7/33

Abstract: A method of generating a ground truth dataset for motion planning of a vehicle is disclosed. The method includes: obtaining undistorted LiDAR scans; identifying, for a pair of undistorted LiDAR scans, points belonging to a static object in an environment; aligning the close points based on pose estimates; and transforming a reference scan that is close in time to a target undistorted LiDAR scan so as to align the reference scan with the target undistorted LiDAR scan.

公开(公告)号：US20190333389A1

公开(公告)日：2019-10-31

申请号：US15965568

申请日：2018-04-27

Applicant: TuSimple

Inventor： Panqu Wang

IPC: G08G1/16 ,  G06K9/00 ,  G06T7/62 ,  G06T7/70

Abstract: A system and method for determining car to lane distance is provided. In one aspect, the system includes a camera configured to generate an image, a processor, and a computer-readable memory. The processor is configured to receive the image from the camera, generate a wheel segmentation map representative of one or more wheels detected in the image, and generate a lane segmentation map representative of one or more lanes detected in the image. For at least one of the wheels in the wheel segmentation map, the processor is also configured to determine a distance between the wheel and at least one nearby lane in the lane segmentation map. The processor is further configured to determine a distance between a vehicle in the image and the lane based on the distance between the wheel and the lane.

公开(公告)号：US10410055B2

公开(公告)日：2019-09-10

申请号：US15725747

申请日：2017-10-05

Applicant: TuSimple

Inventor： Yijie Wang ,  Panqu Wang ,  Pengfei Chen

IPC: G06K9/00 ,  G06K9/20 ,  G06K9/62 ,  B64D47/08 ,  B64C39/02 ,  G08G1/01

Abstract: A system and method for aerial video traffic analysis are disclosed. A particular embodiment is configured to: receive a captured video image sequence from an unmanned aerial vehicle (UAV); clip the video image sequence by removing unnecessary images; stabilize the video image sequence by choosing a reference image and adjusting other images to the reference image; extract a background image of the video image sequence for vehicle segmentation; perform vehicle segmentation to identify vehicles in the video image sequence on a pixel by pixel basis; determine a centroid, heading, and rectangular shape of each identified vehicle; perform vehicle tracking to detect a same identified vehicle in multiple image frames of the video image sequence; and produce output and visualization of the video image sequence including a combination of the background image and the images of each identified vehicle.

公开(公告)号：US10147193B2

公开(公告)日：2018-12-04

申请号：US15456294

申请日：2017-03-10

Applicant: TuSimple

Inventor： Zehua Huang ,  Pengfei Chen ,  Panqu Wang

IPC: G06K9/62 ,  G06T7/11 ,  G06K9/46 ,  G06N3/02 ,  G05D1/00 ,  B60W50/00

Abstract: A system and method for semantic segmentation using hybrid dilated convolution (HDC) are disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image; performing a convolution operation on the feature map and producing multiple convolution layers; grouping the multiple convolution layers into a plurality of groups; applying different dilation rates for different convolution layers in a single group of the plurality of groups; and applying a same dilation rate setting across all groups of the plurality of groups.

公开(公告)号：US09953236B1

公开(公告)日：2018-04-24

申请号：US15456219

申请日：2017-03-10

Applicant: TuSimple

Inventor： Zehua Huang ,  Pengfei Chen ,  Panqu Wang

IPC: G06K9/34 ,  G06K9/00 ,  G05D1/00 ,  G06K9/66 ,  G06K9/52 ,  G06K9/62 ,  G05D1/02

CPC classification number: G06K9/34 ,  G06K9/00791 ,  G06K9/52 ,  G06K9/6267 ,  G06K9/66

Abstract: A system and method for semantic segmentation using dense upsampling convolution (DUC) are disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image; performing a convolution operation on the feature map and reshape the feature map to produce a label map; dividing the label map into equal subparts, which have the same height and width as the feature map; stacking the subparts of the label map to produce a whole label map; and applying a convolution operation directly between the feature map and the whole label map without inserting extra values in deconvolutional layers to produce a semantic label map.