专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

AU2022201178A1 Method and apparatus for detecting corner points of lane lines, electronic device and storage medium 未知
公开(公告)号：AU2022201178A1
公开(公告)日：2022-09-08
申请号：AU2022201178
申请日：2022-02-22
申请人： BEIJING TUSEN ZHITU TECHNOLOGY CO LTD
发明人： SHEN ZHENWEI , HUANG ZEHAO , WANG NAIYAN
IPC分类号： G06V20/56 , G06K9/62 , G06T7/13 , G06T7/60 , G06V10/44 , G06V10/82
摘要： The present application relates to a method and an apparatus for detecting corner points of a lane line, an electronic device and a storage medium. The method comprises: obtaining a road image to be detected; inputting the road image into a pre-trained neural network model to obtain a heat map prediction result, wherein the heat map prediction result comprises a probability of each pixel belonging to a specific corner point category; determining a plurality of different categories of corner points in the road image according to the probability of each pixel belonging to a specific corner point category in the heat map prediction result; and grouping the plurality of different categories of corner points according to a predetermined rule to obtain at least one corner point group. The present application can solve the problem that the corner points of the lane lines cannot be accurately and quickly detected. DRAWINGS OF THE SPECIFICATION Driving system Sensor system Control system User interface system Computing system Eimotor Steering Display deviceM l GPS Poontroi Ser Procssor Spechanger Radar II IAutonomous Brake Mvlicrophone driving control Electronic system LIDAR unit Power Cameraat 148 -/150 Communication system 142 144 146 152

2. 发明专利

AU2022201649A1 Method and apparatus for detecting lane lines, electronic device and storage medium 未知
公开(公告)号：AU2022201649A1
公开(公告)日：2022-10-20
申请号：AU2022201649
申请日：2022-03-09
申请人： BEIJING TUSEN ZHITU TECHNOLOGY CO LTD
发明人： SHEN ZHENWEI , HUANG ZEHAO , WANG NAIYAN
IPC分类号： G06V20/56 , B60W30/12 , G05D1/02 , G06V10/26
摘要： The present application relates to a method and an apparatus for detecting lane lines, an electronic device and a non-transitory storage medium. The method comprises: acquiring an image to be detected; determining at least one initial point in the image; extracting a position 5 characteristic of at least one initial point; processing the position characteristic of the at least one initial point by using a first network model to obtain trend information of a corresponding lane line; and generating a target lane line containing the at least one initial point according to the trend information. In the present application, a network model is used to process a position characteristic of an initial point to obtain trend information of the lane line, and a 10 complete lane line of the road image is quickly generated according to the trend information. Acquiring an image to be detected Determining at least one initial point in the image Extracting a position characteristic of the at least one initial point S103 Processing the position characteristic of the at least one initial point by a first network model to obtain trend information of a corresponding lane line and S04 generating a target lane line containing the at least one initial point according to the trend information 5 Line Segment 2 First direction -; L 7 ,1Line - segment 3 Line segment 1 Second Line 13 direction segment 4

3. 发明专利

AU2022200537A1 Training method for multi-object tracking model and multi-object tracking method 未知
公开(公告)号：AU2022200537A1
公开(公告)日：2022-08-18
申请号：AU2022200537
申请日：2022-01-27
申请人： BEIJING TUSEN ZHITU TECHNOLOGY CO LTD
发明人： HE JIAWEI , HUANG ZEHAO , WANG NAIYAN
IPC分类号： G06V10/82 , G06K9/62 , G06N3/04 , G06T7/20
摘要： An embodiment of the present disclosure discloses a training method for a multi-object tracking model and a multi-object tracking method. The multi-object tracking method comprises: constructing an object graph according to objects to be tracked in a current frame, wherein the vertexes of the object graph correspond to the objects to be tracked, and edge features of the edges between the two vertexes comprise an attribute relationship between the two vertexes; performing graph matching on the object graph and an existing tracklet graph to calculate matching scores between the object to be tracked and the tracked tracklet in the tracklet graph, wherein the vertexes of the tracklet graph correspond to the existing tracked tracklets, and the edge features of the edges between the two vertexes comprise an attribute relationship between the two vertexes; and determining the matched tracklet of the object to be tracked according to the matching scores. Constructing al initial inulti-objectitracking iodel S110 Performing joint training on the networks in the multi-object tracking model according to a real matched tracklet and a predicted matched tracklet of the object to be tracked in training sample by adopting a preset loss 5120 function of the multi-object tracking model to obtain the trained multi-object tracking model BMulti-object tracking model Object graph Back propagation extrac-tion

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式