An unmanned aerial vehicle aerial photography-based pavement crack image identification method
A technology for pavement cracks and identification methods, applied in character and pattern recognition, computer parts, instruments, etc., can solve problems such as the inability of real-time fixed-point multiple inspections, hidden safety hazards for road inspectors, and affecting the normal use of roads, etc. The effect of disease detection efficiency, improving recognition accuracy, and reducing the probability of false detection and missed detection
Pending Publication Date: 2021-08-27
SOUTHEAST UNIV
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The manual visual detection method is the most traditional detection method, the detection efficiency of this method is low, and the evaluation of pavement damage given is subjective
And manual inspection needs to close the traffic, which not only affects the normal use of the road, but also brings safety hazards to road inspectors
The emergence of road inspection vehicles has improved the efficiency of road inspection, and can collect road condition data at a certain speed. However, to complete the inspection of the entire road section, multi-lane data collection is required to complete the inspection task of the road section.
And limited by the traffic flow, the detection task cannot be carried out on a fixed lane at a fixed speed, the detection frequency is low, and multiple patrol inspections cannot be performed in real time.
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] Such as figure 1 As shown, the present embodiment provides a recognition method based on unmanned aerial vehicle cracked images of pavement; the specific steps are:
[0039] Step 1: Build a UAV road image collection platform to obtain road images;
[0040] Step 2: Image dataset expansion;
[0041] Step 3: Manually mark the cracks in the image, and enhance the small target cracks;
[0042] Step 4: Build and train the Faster RCNN model;
[0043] Step 5: Classification and location of pavement cracks.
[0044] First, determine the flight state, flight parameters and camera parameters of the UAV through experiments. Specifically, it includes the focal ...
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 an unmanned aerial vehicle aerial photography-based pavement crack image identification method. Comprising the steps of firstly calculating required flight parameters according to quality requirements of aerial images of an unmanned aerial vehicle; then finishing flight path planning, finishing pavement crack image collection based on the unmanned aerial vehicle, and processing the collected images; performing targeted enhancement on small-scale cracks of aerial photography; and finally, according to the FasterRCNN network model, completing identification and positioning of the pavement crack, and outputting the category and the position of the disease in a document form, so that a basis is provided for maintenance management work. According to the invention, the identification precision is improved.
Description
technical field [0001] The invention relates to the field of road engineering detection and maintenance. Background technique [0002] With the development of our country's economy, the road mileage in our country is constantly increasing. As of the end of 2019, the total road mileage in the country is 5.0125 million kilometers, and the road density is 52.21 kilometers per 100 square kilometers. The scale of road construction is getting bigger and bigger. With the increase of road service life, various road surface diseases continue to appear on the road surface, and the inspection and maintenance work of the road surface is becoming increasingly heavy. Defects on the pavement not only affect the performance of the road, but also cause traffic safety accidents. The increasing development of cracks, potholes, ruts and other diseases on the road surface will continuously shorten the service life of the road and increase maintenance and repair costs. Therefore, it is very imp...
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): G06K9/00G06K9/32G06K9/62G06N3/04
CPCG06V20/182G06V10/25G06N3/045G06F18/214
Inventor 马涛钟靖涛朱俊清韩诚嘉张伟光
Owner SOUTHEAST UNIV