Pavement crack detection and classification method based on three-dimensional laser sensor and bounding box
A three-dimensional laser, classification method technology, applied in the direction of optical testing flaws/defects, instruments, characters and pattern recognition, etc., can solve the problems of regardless of impact, inappropriateness, regardless of crack characteristics, etc., to reduce cost and workload, Improve work efficiency and reduce labor intensity
Active Publication Date: 2019-06-11
FUJIAN AGRI & FORESTRY UNIV
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The detection based on ANN technology has satisfactory results for various types of cracks; however, there are still two limitations: 1) It is not suitable for large-scale road network surveys due to the difficulty in establishing a training library
2) It cannot distinguish between multiple cracks in the same image
[0007] Existing fracture classification techniques have several limitations: (1) do not consider fracture characteristics such as: length, width, perimeter, area
(2) Regardless of the complexity of cracks
(3) Longitudinal and transverse cracks cannot be easily separated
(4) Does not support the distinction of multiple cracks in the same image (5) Does not consider the influence of crack position on cracks
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
[0052] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0053] figure 1 It is the vehicle-mounted three-dimensional laser sensor of this embodiment. It can be used to collect two-dimensional or three-dimensional data of the whole lane at a speed of 100km / h on the expressway, and obtain a three-dimensional image of the road surface with an accuracy of 1mm / pixel, which makes up for the traditional two-dimensional image quality that is easily affected by lane markings, shadows and Defects such as oil pollution can significantly improve the quality of road surface images; its coverage length can reach 4m wide, and it can collect road surface image data of the entire lane at one time. In this embodiment, three-dimensional images are used as basic elements for detection and classification. Each 3D image has a size of 4096 mm and a width of 2048 mm. To detect and identify cracks, histogram equalization and adapt...
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 pavement crack detection and classification method based on a three-dimensional laser sensor and a bounding box. Two-dimensional or three-dimensional road image data of alllanes is acquired through two vehicle-mounted independent laser sensors and a three-dimensional laser scanning and imaging technology; after related data is acquired through vehicle-mounted equipment,a crack is identified through a multi-seed fusion algorithm; then, image processing technologies, such as expansion and corrosion, are introduced; in combination with wheel path and lane mark position reference, a final bounding box is generated; and finally, crack classification and severity grade evaluation are carried out by using the bounding box. By means of the pavement crack detection andclassification method based on the three-dimensional laser sensor and the bounding box in the invention, cracks can be identified and classified in the early days; the maintenance cost is greatly reduced; and the method has the advantages of being rapid, effective and high in correctness.
Description
technical field [0001] The invention relates to the technical field of automatic road detection, in particular to a road surface crack detection and classification method based on a three-dimensional laser sensor and a bounding box. Background technique [0002] At present, a large amount of research at home and abroad has been devoted to the development of available solutions for fully automatic fracture classification, but the field application of the results is still limited because of the many defects in the existing processing technology. [0003] For automatic classification techniques, they can be divided into three categories: wave transform-based computation, artificial neural network-based techniques, and statistical feature-based techniques. [0004] The pavement image can be decomposed into different frequency sub-bands by wavelet transform, in which the disease is transformed into high-amplitude wavelet coefficients, and the background is transformed into wavele...
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): G01N21/88G06K9/00G06K9/34
Inventor 李林罗文婷
Owner FUJIAN AGRI & FORESTRY UNIV