Method for marking traffic lights in prior map
A technology of traffic lights and maps, which is applied in the field of information perception and recognition, can solve problems such as difficult to meet practical requirements, and the description of traffic lights is not specific enough, so as to promote industrialization, improve accuracy and calculation efficiency, and accurately mark methods Effect
Pending Publication Date: 2021-11-19
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Especially at night, in extreme weather conditions, in complex road conditions such as intersections and multiple signal lights, this problem will become more difficult
A priori map is an effective way to improve the accuracy of traffic light recognition. However, the current high-precision map pays more attention to road information such as location, slope, and orientation, and the description of traffic lights is not specific enough to meet practical requirements.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0037] The drawings constituting a part of the present invention are used to provide a further understanding of the present invention, and the schematic embodiments and descriptions of the present invention are used to explain the present invention, and do not constitute an improper limitation of the present invention.
[0038] like figure 1 As shown, this embodiment provides a method for labeling traffic lights in a priori map, which specifically includes:
[0039] 1. Sensor joint calibration;
[0040] 2. Multi-sensor data acquisition and fusion preprocessing;
[0041] 3. Traffic signal fusion information extraction and labeling.
[0042] Joint Calibration of Sensors
[0043] The invention uses the self-driving vehicle as a data acquisition platform, mainly equipped with laser radar, IMU, BDS / GPS receiver, and visual sensor, and obtains the basic data of traffic lights through multi-sensor data fusion and preprocessing. Wherein, sensor calibration work is the basis of dat...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for marking traffic lights in a prior map, which comprises the following steps of: firstly, finishing multi-sensor online acquisition by using an automatic driving vehicle hardware platform; secondly, matching and aligning positions, postures, images, point clouds and data acquired by multiple sensors; and finally, obtaining the position and size information of the traffic lights in the prior map through data fusion. According to the method, the traffic signal lamp information can be more specifically and accurately marked and described, and assistance is provided for an automatic driving image online recognition algorithm.
Description
technical field [0001] The invention belongs to the technical field of information perception and identification. Background technique [0002] As DARPA restarted the research on unmanned vehicle technology, and held three smart car challenges in 2004, 2005 and 2007, Google invested heavily in the research of autonomous driving technology. upsurge. Participants include top Internet companies such as Google, Apple, Uber, and BAT, as well as traditional car companies such as Tesla, Mercedes-Benz, BMW, GM, and Cadillac. At the same time, component suppliers such as Intel, Nvidia, Bosch, and Mobileye also participated , In addition, start-up companies in the field of autonomous driving have sprung up like mushrooms after rain. [0003] After more than ten years of development, autonomous driving technology has gradually evolved from laboratory research, to closed environment technology competitions, and then to fixed-scene demonstration applications. Although considerable prog...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06T7/80G01C21/16G01S17/86G01S17/89G01S19/48G01S19/49
CPCG06T7/80G01S17/89G01S17/86G01C21/165G01C21/1656G01S19/48G01S19/485G01S19/49G06T2207/10028G06T2207/10044G06F18/25
Inventor 李子月曾庆化刘建业杨闯赖际舟吕品刘玉超
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS