Ground target detection evaluation method
An evaluation method and ground target technology, applied in the field of intelligent transportation, can solve problems affecting the development process of unmanned driving, lack of evaluation methods, etc., and achieve the effects of solving evaluation method problems, promoting development, and optimizing detection networks
Pending Publication Date: 2020-11-03
上海智驾汽车科技有限公司
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] At present, more and more methods based on deep learning target detection realize the detection of ground targets, especially the detection of ground marking lines, but there is a lack of reasonable evaluation methods to evaluate the detection effect, which affects the development of unmanned driving to a certain extent. process
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
[0040] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention.
[0041] In some processes described in the specification and claims of the present invention and the above-mentioned drawings, a plurality of operations appearing in a specific order are contained, but it should be clearly understood that these operations may not be performed in the order in which they appear herein Execution or parallel execution, the sequence numbers of operations such as 202, 204, etc. are only used to distinguish different operations, and the sequence numbers themselves do not represent any execution sequence. Additionally, these processes can include more or fewer operations, and these operations can be performed sequentially or in parallel. It should be ...
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 ground target detection and evaluation method, which comprises the following steps: labeling a label on a detection image, and obtaining the total number of positive samples;taking the labeled label pixel point as a reference, and expanding the pixel points in the 8 neighborhood range of the pixel points into the same label; obtaining the total number of detection samples; taking the expanded pixel points marked with the labels as reference pixel points, judging whether at least one pixel point with the same label exists in a corresponding area with the same 8-neighborhood range position of each reference pixel point or not, and if so, adding 1 to the number of correct detection samples; if not, marking as a false detection target; dividing the correct detectionsample number by the total number of the positive samples to obtain a recall rate, dividing the false detection target number by the total number of the detection samples to obtain a false detection rate, and optimizing a preset convolutional neural network based on the recall rate and the false detection rate. According to the method, the detection network is optimized by calculating the recall rate and the false detection rate, and the problem of lack of an evaluation method for the detection effect is solved.
Description
technical field [0001] The invention relates to the field of intelligent transportation, in particular, the invention relates to a ground target detection and evaluation method. Background technique [0002] With the continuous increase in the number of cars, it brings convenience to human life, but also leads to unfavorable consequences such as traffic accidents and traffic jams. For this reason, intelligent transportation systems came into being. The most important thing in the intelligent transportation system is to realize unmanned driving. As one of the key technologies in the field of intelligent transportation, lane line detection technology is of great significance to the realization of vehicle intelligent driving, lane departure warning system and vehicle anti-collision system. [0003] At present, more and more methods based on deep learning target detection realize the detection of ground targets, especially the detection of ground marking lines, but there is a l...
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 IPC IPC(8): G06K9/00G06K9/32G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06V20/588G06V10/25G06N3/045G06F18/24
Inventor 谢冬梅叶春兰
Owner 上海智驾汽车科技有限公司