Traffic participant position and action labeling method based on natural driving data
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for driving data and participants, applied in the input/output process of data processing, electrical digital data processing, other database indexing, etc., to improve quality and efficiency, reduce labeling errors, and facilitate manual viewing.
Pending Publication Date: 2022-02-01
CHINA FIRST AUTOMOBILE
View PDF0 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0007] The purpose of the present invention is to provide a manual marking method for traffic participants' positions and actions based on natural driving data, so as to solve the problem of maximizing the marking speed and marking accuracy. By playing back video and sensor data in real time, the Mark the key time points to ensure that the marked points coincide with the actual time points to the maximum extent, and the error is controlled within 0.1s; through the limitation of specific rules, the marking speed and marking accuracy are maximized to meet the scene extraction 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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0079] A method for labeling traffic participants' positions and actions based on natural driving data, specifically a process for establishing a traffic data retrieval table, including the following steps:
[0080] S1 structure setup:
[0081] S101: Data object classification
[0082] According to the collection content and actual situation of natural driving data, it is classified according to the objects described by the data. A common classification is as follows:
[0083] 1. Participants in natural driving traffic dynamics
[0084] a. This car
[0085] ⅰ. The vehicle lane number
[0086] ⅱ. The movement of the vehicle
[0087] b. Other objects
[0088] ⅰ. Target position - straight ahead
[0089] ⅱ. Target position - right behind
[0090] ⅲ. Position of the target - right on the left
[0091] ⅳ. Position of the target - directly on the right
[0092] ⅴ. Target type
[0093] ⅵ, target action
[0094] 2. Static participants in natural driving traffic
[0095] a....
Embodiment 2
[0166] The method of labeling the position and action of traffic participants based on natural driving data, the specific operation method is as follows:
[0167] 1. Play back historical data, which can be paused and played at any time;
[0168] 2. Enter the ID of the traffic participant, and click the location of the traffic participant in the location selection area. By default, from the current time to the end time, fill in the mark box on the corresponding time axis, and click the ongoing traffic participant in the data attribute selection area. Action and its type, add data attributes for the marker box;
[0169] 3. When the action of the traffic participant changes, click the corresponding action in the data attribute selection area, and at the same time mark the attribute switching sign at the corresponding moment in the mark box, switch and record the data attribute value of the current mark frame. The attribute switch flag can be adjusted by dragging up and down;
...
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 relates to a traffic participant position and action labeling method based on natural driving data. The method comprises the following steps of: classifying data objects, defining data attributes under each category, establishing an initial index table and a unified time axis and value of each data object classification in the initial table, keeping the time axis consistent with the time axis collected from natural driving data, setting an attribute switching mark, synchronously playing back data, acquiring actual data, automatically generating an initial index table of dynamic participants of natural driving traffic according to the actual data, filling natural environment information acquired by a public data source into the initial index table, carrying out manual correction on the automatically filled data attribute value; and reflecting the plurality of marking boxes of the marking correction area into the filled initial index table. According to the labeling method, manual checking is facilitated, the labeling speed is increased to the maximum extent, labeling errors are reduced to the maximum extent, and the errors are controlled within 0.1s.
Description
technical field [0001] The technical field of intelligent networked vehicles of the present invention specifically relates to a method for manually marking the positions and actions of traffic participants based on natural driving data. Background technique [0002] As domestic smart cars gradually reach the L3 / L4 level, mainly involving ADAS (Automatic Driving Assistance System) functions such as congestion follow-up, high-speed driving and valet parking, it is necessary to understand highway scenes, urban congestion scenes (express roads) and The scene data of the parking lot is analyzed to support the development of ADAS function control strategies and safety verification to ensure the highly anthropomorphic driving of smart cars. However, in the driving data, there are many other traffic participants around the vehicle that interact with the vehicle and change their position, for example, the vehicle in front cuts in front of the vehicle from the right. However, vehicle...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more