Unlock instant, AI-driven research and patent intelligence for your innovation.
Automobile image scene library data complexity measurement method
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 measurement method and complexity technology, applied in the direction of measuring devices, vehicle testing, instruments, etc., can solve the problems of reducing the credibility of test results, the inability to compare the advantages and disadvantages of the scene library, and the inability to find performance defects of self-driving cars, etc.
Pending Publication Date: 2021-07-09
CHINA AUTOMOTIVE ENG RES INST
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
[0004] 1. The scene library may contain a large amount of repetitive and low-quality scene data, which leads to a long test time based on the scene library, and even the performance defects of the self-driving car cannot be found, which reduces the credibility of the test results;
[0005] 2. The pros and cons of different scene libraries cannot be compared, resulting in the inability to select the optimal scene library data for the autonomous vehicle scene library test
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
[0029] A data complexity measurement method for an automobile image scene database, basically as attached figure 1 Shown: Include the following steps:
[0030] S1. Layer the scene data corresponding to each scene in the scene library according to the scene elements; where the scene elements are road elements, traffic facility elements, temporary traffic event elements, traffic participant elements, environmental condition elements and information elements, respectively. The last layer of scenes is road layer, traffic facility layer, temporary traffic event layer, traffic participant layer, environmental condition layer and information layer.
[0031] The first layer: the road layer, the road elements include the geometric and topological structure of the protected road, etc.;
[0032] The second layer: traffic facilities layer, traffic facilities elements include traffic signs, traffic lights, etc.;
[0033] The third layer: temporary traffic event layer, the elements of tem...
Embodiment 2
[0102] Although automatic driving completely liberates the driver's hands, the driver does not need to pay attention to the current road conditions at all times. However, the cab still needs to be equipped with a driver. The reason is that the current automatic driving can only play an auxiliary role in the perception of road condition information. It is not completely automatic driving, and its reliability cannot completely replace the driver, especially in the face of complex road conditions. environment.
[0103] The difference between the second embodiment and the first embodiment is that it also includes the following steps:
[0104] S6. Set manual intervention thresholds for the layered road layer, traffic facility layer, temporary traffic event layer, and traffic participant layer respectively. Set the weight ratio of the above layers.
[0105] For example, in the road layer, in the suburban town road section, the lane line is blurred, the complexity value is 4, and t...
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 belongs to the technical field of automatic driving, and particularly relates to an automobile image scene librarydata complexity measurement method, which comprises the following steps of S1, layering scene data corresponding to each scene in a scene library according to scene elements; S2, assigning a complexity value to a scene element corresponding to each layer of scene after layering; S3, giving the scene probability of occurrence of the scene elements of each layer of scene; S4, comprehensively calculating the complexity of each layer of scene according to the complexity value of the scene element of each layer of scene and the scene probability; and S5, adding each layer of scene complexity to obtain the final scene complexity of the scene data. According to the invention, the quality of the scene data in the scene library can be quantified, so that advantages and disadvantages of different scene libraries can be compared.
Description
technical field [0001] The invention belongs to the technical field of automatic driving, and in particular relates to a data complexity measurement method of an automobile image scene database. Background technique [0002] Self-driving car testing and verification is an essential link in the development and pre-marketing of self-driving cars, and a supporting test and evaluation system is a prerequisite for promoting the development of self-driving car technology. The scene library of the real vehicle road test plays a very critical role in the intelligent networked vehicle test and evaluation system. It is the basis and starting point of the test and evaluation, and can sideways affect the complexity of the task. To ensure the sufficiency of test scenarios, the scenario library should make autonomous driving safer and more reliable than all scenarios encountered by human driving. [0003] At present, most enterprises and organizations focus on the collection of scene dat...
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