A non-motor vehicle detection and recognition method based on deep learning
A non-motor vehicle, deep learning technology, applied in the direction of character and pattern recognition, computer parts, instruments, etc., can solve the problems of non-motor vehicles with large differences in shape and prone to misjudgment, and achieve the effect of improving recognition accuracy
Inactive Publication Date: 2019-05-28
HEFEI ZHIXIN AUTOMOTIVE TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing vehicle detection and recognition are all aimed at motor vehicles, and non-motor vehicles have large differences in shape, so there are great difficulties in the process of detection and recognition of non-motor vehicles, and misjudgment is prone to occur.
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
[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0017] Such as figure 1 As shown, a non-motor vehicle detection and recognition method based on deep learning includes the following steps:
[0018] S1: Establish a basic database, input the found non-motor vehicle data parameters into the basic database, and use the above data parameters as feature data for judging whether there is a non-motor vehicle in the video image;
[0019] S2: Capture images, acquire road traffic information video images in the area, and enhance the ...
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 non-motor vehicle detection and recognition method based on deep learning. The non-motor vehicle detection and recognition method comprises the following operation steps of S1, establishing a basic database; S2, capturing an image, obtaining a road traffic information video image in the region, and performing moving target detection on the processed video image; S3, extracting features of the moving target, intercepting a video image of the moving target after the moving target is determined, extracting features of the moving target in the image, associating the features of the moving target with the moving target, comparing the extracted feature parameters with feature data in a basic database, and outputting a detection and identification result; and S4, carrying out the deep learning, evaluating the detection and recognition result, carrying out supplementary learning on the basic database according to the evaluation result, and establishing an auxiliary database; using the BFM to evaluate the judgment result and carries out feedback and deep learning on the basic database and the auxiliary database according to the evaluation result, so that the subsequent detection and recognition accuracy of the non-motor vehicle is improved.
Description
technical field [0001] The invention belongs to the technical field of non-motor vehicle detection, and in particular relates to a non-motor vehicle detection and identification method based on deep learning. Background technique [0002] At present, non-motor vehicles are still an important means of transportation for the people of our country to travel, and the market has a large amount and maintains a continuous growth trend. However, the existing vehicle detection and recognition are all aimed at motor vehicles, and non-motor vehicles have great differences in shape, so there are great difficulties in the process of detection and recognition of non-motor vehicles, and misjudgment is prone to occur. Therefore, it is necessary to propose a method for detecting and identifying non-motor vehicles capable of deep learning, so as to improve the efficiency of detection and recognition of non-motor vehicles. Contents of the invention [0003] The object of the present inventi...
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): G06K9/00
Inventor 许翔
Owner HEFEI ZHIXIN AUTOMOTIVE TECH CO LTD