High-resolution remote sensing image road extraction method based on centerline and road width detection algorithm
A high-resolution, remote sensing image technology, applied in computing, computer parts, character and pattern recognition, etc., can solve problems such as incomplete road extraction information and poor accuracy.
Active Publication Date: 2018-09-14
JILIN UNIV
View PDF6 Cites 11 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0010] In order to solve the problem that the road information extracted from high-resolution remote sensing images is easily affected by various surrounding objects, such as trees, vehicles, houses, etc., which will lead to incomplete and poor accuracy of road extraction information. The invention provides a method for extracting roads from high-resolution remote sensing images based on centerline and road width detection algorithms. The specific steps are as follows:
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 1
[0098] Example 1: Images after panchromatic and multispectral fusion after preprocessing with Quickbird ( figure 2 ), the resolution of the panchromatic image is 0.61m, the multispectral image contains four bands of blue, green, red and near-red with a resolution of 2.44m, and the fused image contains four bands of blue, green, red and near-red. The resolution is 0.61m. The experimental data were obtained from the website (http: / / www.cse.iitm.ac.in / ~vplab / satellite.html), with a size of 512*512 pixels. This data source is a common road extraction data source, and its results can be used for intuitive comparison with the results of other road extraction methods. The main features of this data are: highways, buildings and vegetation. The main disturbances in road extraction by using this data are: (1) some of the roads are overpasses, and the shadow of the overpass causes the road to be partially blocked by shadows, which makes the road extraction process break; (2) the spect...
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 high-resolution remote sensing image road extraction method based on a centerline and road width detection algorithm and belongs to the remote sensing image processing technical field. Since a road centerline directly extracted by a centerline detection algorithm will be affected by various surrounding ground objects such as trees, vehicles and houses, and as result, thecenterline is incomplete and will be interrupted, and the problems of incompleteness and poor precision of road extraction information can be brought about. According to the high-resolution remote sensing image road extraction method based on the centerline and road width detection algorithm of the invention, a tensor field is introduced; an interrupted part in centerline detection can be supplemented through a tensor field voting algorithm; calculation is carried out through using a centerline detection algorithm, so that a complete road centerline can be obtained; and road width which is corresponding to a centerline nearest to the interrupted part is adopted as actual road width, and complete road information can be extracted.
Description
technical field [0001] The invention belongs to the application technical field of remote sensing image processing. Background technique [0002] As the main body of the modern transportation system, the road has important geographical, political and economic significance. The road is also the main recording and marking object in the geographic information system and map. In the middle of the 20th century, due to the needs of intelligent transportation, related technologies for road extraction using images began to appear and gradually developed. In the past ten years, with the rapid development of remote sensing technology, high-resolution remote sensing images, radar images and UAV images have provided the possibility for road extraction using remote sensing images. The main links of road extraction include segmenting out road points; trimming road segment strips; linking road segments to generate road network, etc. Due to the diversity of road extraction applications, t...
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): G06K9/00G06K9/46
CPCG06V20/182G06V10/44
Inventor 顾玲嘉周婷婷任瑞治
Owner JILIN UNIV