Method for extracting road various information of multi-level knowledge driven panchromatic remote sensing image
A knowledge-driven, remote sensing image technology, applied in character and pattern recognition, instrumentation, computing, etc., can solve the problem of lack of automatic road change detection strategies and algorithms, and achieve the effect of improving the degree of automation
Inactive Publication Date: 2010-06-02
WUHAN UNIV
View PDF3 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] At present, there is no general automatic road change detection strategy and algorithm for all road types and various resolution images
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
[0082] In this embodiment, firstly, by processing old vector data and preprocessed remote sensing images, candidate road segments are extracted under the guidance of prior knowledge, and according to people's perceptual knowledge of road models, perceptual grouping is used to connect candidate road segments to form an initial road network , secondly, in the process of analyzing the buffer zone of the extracted road network and the old road network, the principle of knowledge judgment is added to obtain the disappearing and changing roads, and the reasoning and assumptions are combined with the road network model again to obtain the knowledge constraint rules that conform to the road model. From the point of view of visual segmentation to obtain segmented blocks reflecting image attributes, the candidate new roads are optimized and processed. Finally, human beings provide knowledge to drive the semi-automatic tracking process. Add road network to supplement and complete change d...
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 road-change information extraction method of a panchromatic remote sensing image, which is driven by multiple-level knowledge. Firstly, prior knowledge is fully applied in aroad extract layer, a multi-scale template is generated automatically, the automatic extraction of a road candidate section is realized, and an initial road network is formed by adopting a perceptualorganization to connect the road candidate section according to the cognition knowledge of people on a road model; secondly, a knowledge judging principle is added to a road-change detecting layer toconduct a buffer area analysis on the extracted road network and the original road network, to obtain a road-change detection result; thirdly, ratiocination and assumption are performed in a newly added road detecting layer through combining a road network model to obtain a knowledge constraint rule corresponding with the road model, and the newly added candidate road is optimized and processed from the standpoint that a partition is obtained through visual partition to reflect the video attributes; finally, aiming at the road complexity, the combined tracking of the newly added road is completed in a semiautomatic extraction layer through being driven by the knowledge of people, and an integrated newly added road network is formed.
Description
technical field [0001] The invention relates to a multi-level knowledge-driven method for extracting road change information from panchromatic remote sensing images, belonging to the field of image processing, in particular to the technical field of remote sensing image processing and target extraction. Background technique [0002] As the most important artificial geographic entity, road occupies a huge proportion in basic geographic information. Automatic detection of road changes from remote sensing images is not only a difficult problem in the field of photogrammetry and remote sensing, but also one of the focuses of computer vision and image understanding research. [0003] In the past two decades, people have proposed many methods for automatically or semi-automatically extracting road change information from remote sensing images, which can be roughly divided into three categories: the first category is based on the characteristics of the road itself, and establishes ...
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 Patents(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/62G06K9/64
Inventor 潘励郑宏王华邱枫董明
Owner WUHAN UNIV